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

by Dev Jain

The compaction_test memory selftest introduces fragmentation in memory and then tries to allocate as many hugepages as possible. This series addresses some problems. First off, correctly set the number of hugepages to zero before trying to set a large number of them. Now, consider a situation in which, at the start of the test, a non-zero number of hugepages have been already set (while running the entire selftests/mm suite, or manually by the admin). The test operates on 80% of memory to avoid OOM-killer invocation, and because some memory is already blocked by hugepages, it would increase the chance of OOM-killing. Also, since mem_free used in check_compaction() is the value before we set nr_hugepages to zero, the chance that the compaction_index will be small is very high if the preset nr_hugepages was high, leading to a bogus test success. This series applies on top of the stable 6.9 kernel. Dev Jain (2): selftests/mm: compaction_test: Fix incorrect write of zero to nr_hugepages selftests/mm: compaction_test: Fix trivial test success and reduce probability of OOM-killer invocation tools/testing/selftests/mm/compaction_test.c | 70 ++++++++++++++------ 1 file changed, 50 insertions(+), 20 deletions(-) -- 2.30.2

1 hour, 45 minutes

2
6
0 0

[PATCH] selftests/mm: va_high_addr_switch: Do not skip test and give warning message post FEAT_LPA2

by Dev Jain

Post FEAT_LPA2, Aarch64 extends the 4KB and 16KB translation granule to large virtual addresses. Currently, the test is being skipped for said granule sizes, because the page sizes have been statically defined; to work around that would mean breaking the nice array of structs used for adding testcases. Instead, don't skip the test, and encourage the user to manually change the macros. Signed-off-by: Dev Jain <dev.jain(a)arm.com> --- .../testing/selftests/mm/va_high_addr_switch.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/va_high_addr_switch.c b/tools/testing/selftests/mm/va_high_addr_switch.c index cfbc501290d3..ba862f51d395 100644 --- a/tools/testing/selftests/mm/va_high_addr_switch.c +++ b/tools/testing/selftests/mm/va_high_addr_switch.c @@ -292,12 +292,24 @@ static int supported_arch(void) #elif defined(__x86_64__) return 1; #elif defined(__aarch64__) - return getpagesize() == PAGE_SIZE; + return 1; #else return 0; #endif } +#if defined(__aarch64__) +void failure_message(void) +{ + printf("TEST MAY FAIL: Are you running on a pagesize other than 64K?\n"); + printf("If yes, please change macros manually. Ensure to change the\n"); + printf("address macros too if running defconfig on 16K pagesize,\n"); + printf("since userspace VA = 47 bits post FEAT_LPA2.\n"); +} +#else +void failure_message(void) {} +#endif + int main(int argc, char **argv) { int ret; @@ -308,5 +320,8 @@ int main(int argc, char **argv) ret = run_test(testcases, ARRAY_SIZE(testcases)); if (argc == 2 && !strcmp(argv[1], "--run-hugetlb")) ret = run_test(hugetlb_testcases, ARRAY_SIZE(hugetlb_testcases)); + + if (ret) + failure_message(); return ret; } -- 2.39.2

7 hours, 30 minutes

2
1
0 0

[PATCH v5 00/28] NT synchronization primitive driver

by Elizabeth Figura

This patch series implements a new char misc driver, /dev/ntsync, which is used to implement Windows NT synchronization primitives. NT synchronization primitives are unique in that the wait functions both are vectored, operate on multiple types of object with different behaviour (mutex, semaphore, event), and affect the state of the objects they wait on. This model is not compatible with existing kernel synchronization objects or interfaces, and therefore the ntsync driver implements its own wait queues and locking. This patch series is rebased against the "char-misc-next" branch of gregkh/char-misc.git. == Background == The Wine project emulates the Windows API in user space. One particular part of that API, namely the NT synchronization primitives, have historically been implemented via RPC to a dedicated "kernel" process. However, more recent applications use these APIs more strenuously, and the overhead of RPC has become a bottleneck. The NT synchronization APIs are too complex to implement on top of existing primitives without sacrificing correctness. Certain operations, such as NtPulseEvent() or the "wait-for-all" mode of NtWaitForMultipleObjects(), require direct control over the underlying wait queue, and implementing a wait queue sufficiently robust for Wine in user space is not possible. This proposed driver, therefore, implements the problematic interfaces directly in the Linux kernel. This driver was presented at Linux Plumbers Conference 2023. For those further interested in the history of synchronization in Wine and past attempts to solve this problem in user space, a recording of the presentation can be viewed here: https://www.youtube.com/watch?v=NjU4nyWyhU8 == Performance == The performance measurements described below are copied from earlier versions of the patch set. While some of the code has changed, I do not currently anticipate that it has changed drastically enough to affect those measurements. The gain in performance varies wildly depending on the application in question and the user's hardware. For some games NT synchronization is not a bottleneck and no change can be observed, but for others frame rate improvements of 50 to 150 percent are not atypical. The following table lists frame rate measurements from a variety of games on a variety of hardware, taken by users Dmitry Skvortsov, FuzzyQuils, OnMars, and myself: Game Upstream ntsync improvement =========================================================================== Anger Foot 69 99 43% Call of Juarez 99.8 224.1 125% Dirt 3 110.6 860.7 678% Forza Horizon 5 108 160 48% Lara Croft: Temple of Osiris 141 326 131% Metro 2033 164.4 199.2 21% Resident Evil 2 26 77 196% The Crew 26 51 96% Tiny Tina's Wonderlands 130 360 177% Total War Saga: Troy 109 146 34% =========================================================================== == Patches == The intended semantics of the patches are broadly intended to match those of the corresponding Windows functions. For those not already familiar with the Windows functions (or their undocumented behaviour), patch 27/28 provides a detailed specification, and individual patches also include a brief description of the API they are implementing. The patches making use of this driver in Wine can be retrieved or browsed here: https://repo.or.cz/wine/zf.git/shortlog/refs/heads/ntsync5 == Previous versions == Changes from v4: * Rework wait-all locking code to avoid taking more than one spinlock at a time, and also to fix a race where the wait-all lock would not be not correctly taken. The new locking mechanism involves taking a simple spinlock for normal "any" waits, and taking a device-wide mutex for "all" waits or when locking any object that is involved in an "all" wait. The mechanism was written by Peter Zijlstra. * Try to reword or clarify various parts of the documentation (patch 27), per Peter Zijlstra. * I did not rename NTSYNC_IOC_SEM_POST to RELEASE (like NT) although this was suggested by Peter Zijlstra, mostly because it's not clear to me that renaming an already committed ioctl would be fine. The API committed isn't actually usable yet, though, so if altering it would be fine on those grounds, I can revise this series to rename the function accordingly. * Similarly, I did not change the create ioctls to return the fd directly, although this was suggested and would be a bit simpler and cleaner, because NTSYNC_IOC_CREATE_SEM already exists upstream and returns the fd through a struct. I can make this change in the next revision if that'd be preferable. I also still would appreciate a clarification on the advice in [1]. [1] https://docs.kernel.org/driver-api/ioctl.html#return-code * Link to v4: https://lore.kernel.org/lkml/20240416010837.333694-1-zfigura@codeweavers.co… * Link to v3: https://lore.kernel.org/lkml/20240329000621.148791-1-zfigura@codeweavers.co… * Link to v2: https://lore.kernel.org/lkml/20240219223833.95710-1-zfigura@codeweavers.com/ * Link to v1: https://lore.kernel.org/lkml/20240214233645.9273-1-zfigura@codeweavers.com/ * Link to RFC v2: https://lore.kernel.org/lkml/20240131021356.10322-1-zfigura@codeweavers.com/ * Link to RFC v1: https://lore.kernel.org/lkml/20240124004028.16826-1-zfigura@codeweavers.com/ Elizabeth Figura (28): ntsync: Introduce NTSYNC_IOC_WAIT_ANY. ntsync: Introduce NTSYNC_IOC_WAIT_ALL. ntsync: Introduce NTSYNC_IOC_CREATE_MUTEX. ntsync: Introduce NTSYNC_IOC_MUTEX_UNLOCK. ntsync: Introduce NTSYNC_IOC_MUTEX_KILL. ntsync: Introduce NTSYNC_IOC_CREATE_EVENT. ntsync: Introduce NTSYNC_IOC_EVENT_SET. ntsync: Introduce NTSYNC_IOC_EVENT_RESET. ntsync: Introduce NTSYNC_IOC_EVENT_PULSE. ntsync: Introduce NTSYNC_IOC_SEM_READ. ntsync: Introduce NTSYNC_IOC_MUTEX_READ. ntsync: Introduce NTSYNC_IOC_EVENT_READ. ntsync: Introduce alertable waits. selftests: ntsync: Add some tests for semaphore state. selftests: ntsync: Add some tests for mutex state. selftests: ntsync: Add some tests for NTSYNC_IOC_WAIT_ANY. selftests: ntsync: Add some tests for NTSYNC_IOC_WAIT_ALL. selftests: ntsync: Add some tests for wakeup signaling with WINESYNC_IOC_WAIT_ANY. selftests: ntsync: Add some tests for wakeup signaling with WINESYNC_IOC_WAIT_ALL. selftests: ntsync: Add some tests for manual-reset event state. selftests: ntsync: Add some tests for auto-reset event state. selftests: ntsync: Add some tests for wakeup signaling with events. selftests: ntsync: Add tests for alertable waits. selftests: ntsync: Add some tests for wakeup signaling via alerts. selftests: ntsync: Add a stress test for contended waits. maintainers: Add an entry for ntsync. docs: ntsync: Add documentation for the ntsync uAPI. ntsync: No longer depend on BROKEN. Documentation/userspace-api/index.rst | 1 + Documentation/userspace-api/ntsync.rst | 398 +++++ MAINTAINERS | 9 + drivers/misc/Kconfig | 1 - drivers/misc/ntsync.c | 989 +++++++++++- include/uapi/linux/ntsync.h | 39 + tools/testing/selftests/Makefile | 1 + .../selftests/drivers/ntsync/.gitignore | 1 + .../testing/selftests/drivers/ntsync/Makefile | 7 + tools/testing/selftests/drivers/ntsync/config | 1 + .../testing/selftests/drivers/ntsync/ntsync.c | 1407 +++++++++++++++++ 11 files changed, 2850 insertions(+), 4 deletions(-) create mode 100644 Documentation/userspace-api/ntsync.rst create mode 100644 tools/testing/selftests/drivers/ntsync/.gitignore create mode 100644 tools/testing/selftests/drivers/ntsync/Makefile create mode 100644 tools/testing/selftests/drivers/ntsync/config create mode 100644 tools/testing/selftests/drivers/ntsync/ntsync.c base-commit: f5b335dc025cfee90957efa90dc72fada0d5abb4 -- 2.43.0

10 hours, 54 minutes

1
28
0 0

[PATCH 0/2] usercopy: Convert test_user_copy to KUnit test

by Kees Cook

Hi, This builds on the proposal[1] from Mark and lets me convert the existing usercopy selftest to KUnit. Besides adding this basic test to the KUnit collection, it also opens the door for execve testing (which depends on having a functional current->mm), and should provide the basic infrastructure for adding Mark's much more complete usercopy tests. -Kees [1] https://lore.kernel.org/lkml/20230321122514.1743889-2-mark.rutland@arm.com/ Kees Cook (2): kunit: test: Add vm_mmap() allocation resource manager usercopy: Convert test_user_copy to KUnit test MAINTAINERS | 1 + include/kunit/test.h | 17 ++ lib/Kconfig.debug | 21 +- lib/Makefile | 2 +- lib/kunit/test.c | 139 +++++++++++- lib/{test_user_copy.c => usercopy_kunit.c} | 252 ++++++++++----------- 6 files changed, 288 insertions(+), 144 deletions(-) rename lib/{test_user_copy.c => usercopy_kunit.c} (52%) -- 2.34.1

12 hours, 5 minutes

1
2
0 0

[PATCH] selftests: rtc: rtctest: Do not open-code TEST_HARNESS_MAIN

by Kees Cook

Argument processing is specific to the test harness code. Any optional information needs to be passed via environment variables. Move alternate path to the RTC_DEV environment variable. Also do not open-code TEST_HARNESS_MAIN because its definition may change. Additionally, setup checking can be done in the FIXTURE_SETUP(). With this adjustment, also improve the error reporting when the device cannot be opened. Signed-off-by: Kees Cook <keescook(a)chromium.org> --- Cc: Alexandre Belloni <alexandre.belloni(a)bootlin.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Masahiro Yamada <masahiroy(a)kernel.org> Cc: linux-rtc(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/rtc/Makefile | 2 +- tools/testing/selftests/rtc/rtctest.c | 66 +++++---------------------- 2 files changed, 13 insertions(+), 55 deletions(-) diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile index 55198ecc04db..654f9d58da3c 100644 --- a/tools/testing/selftests/rtc/Makefile +++ b/tools/testing/selftests/rtc/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -O3 -Wl,-no-as-needed -Wall +CFLAGS += -O3 -Wl,-no-as-needed -Wall $(KHDR_INCLUDES) LDLIBS += -lrt -lpthread -lm TEST_GEN_PROGS = rtctest diff --git a/tools/testing/selftests/rtc/rtctest.c b/tools/testing/selftests/rtc/rtctest.c index 63ce02d1d5cc..41cfefcc20e1 100644 --- a/tools/testing/selftests/rtc/rtctest.c +++ b/tools/testing/selftests/rtc/rtctest.c @@ -30,7 +30,18 @@ FIXTURE(rtc) { }; FIXTURE_SETUP(rtc) { + char *alternate = getenv("RTC_DEV"); + + if (alternate) + rtc_file = alternate; + self->fd = open(rtc_file, O_RDONLY); + + if (self->fd == -1 && errno == ENOENT) + SKIP(return, "Skipping test since %s does not exist", rtc_file); + EXPECT_NE(-1, self->fd) { + TH_LOG("%s: %s\n", rtc_file, strerror(errno)); + } } FIXTURE_TEARDOWN(rtc) { @@ -41,10 +52,6 @@ TEST_F(rtc, date_read) { int rc; struct rtc_time rtc_tm; - if (self->fd == -1 && errno == ENOENT) - SKIP(return, "Skipping test since %s does not exist", rtc_file); - ASSERT_NE(-1, self->fd); - /* Read the RTC time/date */ rc = ioctl(self->fd, RTC_RD_TIME, &rtc_tm); ASSERT_NE(-1, rc); @@ -88,10 +95,6 @@ TEST_F_TIMEOUT(rtc, date_read_loop, READ_LOOP_DURATION_SEC + 2) { struct rtc_time rtc_tm; time_t start_rtc_read, prev_rtc_read; - if (self->fd == -1 && errno == ENOENT) - SKIP(return, "Skipping test since %s does not exist", rtc_file); - ASSERT_NE(-1, self->fd); - TH_LOG("Continuously reading RTC time for %ds (with %dms breaks after every read).", READ_LOOP_DURATION_SEC, READ_LOOP_SLEEP_MS); @@ -126,10 +129,6 @@ TEST_F_TIMEOUT(rtc, uie_read, NUM_UIE + 2) { int i, rc, irq = 0; unsigned long data; - if (self->fd == -1 && errno == ENOENT) - SKIP(return, "Skipping test since %s does not exist", rtc_file); - ASSERT_NE(-1, self->fd); - /* Turn on update interrupts */ rc = ioctl(self->fd, RTC_UIE_ON, 0); if (rc == -1) { @@ -155,10 +154,6 @@ TEST_F(rtc, uie_select) { int i, rc, irq = 0; unsigned long data; - if (self->fd == -1 && errno == ENOENT) - SKIP(return, "Skipping test since %s does not exist", rtc_file); - ASSERT_NE(-1, self->fd); - /* Turn on update interrupts */ rc = ioctl(self->fd, RTC_UIE_ON, 0); if (rc == -1) { @@ -198,10 +193,6 @@ TEST_F(rtc, alarm_alm_set) { time_t secs, new; int rc; - if (self->fd == -1 && errno == ENOENT) - SKIP(return, "Skipping test since %s does not exist", rtc_file); - ASSERT_NE(-1, self->fd); - rc = ioctl(self->fd, RTC_RD_TIME, &tm); ASSERT_NE(-1, rc); @@ -256,10 +247,6 @@ TEST_F(rtc, alarm_wkalm_set) { time_t secs, new; int rc; - if (self->fd == -1 && errno == ENOENT) - SKIP(return, "Skipping test since %s does not exist", rtc_file); - ASSERT_NE(-1, self->fd); - rc = ioctl(self->fd, RTC_RD_TIME, &alarm.time); ASSERT_NE(-1, rc); @@ -308,10 +295,6 @@ TEST_F_TIMEOUT(rtc, alarm_alm_set_minute, 65) { time_t secs, new; int rc; - if (self->fd == -1 && errno == ENOENT) - SKIP(return, "Skipping test since %s does not exist", rtc_file); - ASSERT_NE(-1, self->fd); - rc = ioctl(self->fd, RTC_RD_TIME, &tm); ASSERT_NE(-1, rc); @@ -366,10 +349,6 @@ TEST_F_TIMEOUT(rtc, alarm_wkalm_set_minute, 65) { time_t secs, new; int rc; - if (self->fd == -1 && errno == ENOENT) - SKIP(return, "Skipping test since %s does not exist", rtc_file); - ASSERT_NE(-1, self->fd); - rc = ioctl(self->fd, RTC_RD_TIME, &alarm.time); ASSERT_NE(-1, rc); @@ -410,25 +389,4 @@ TEST_F_TIMEOUT(rtc, alarm_wkalm_set_minute, 65) { ASSERT_EQ(new, secs); } -static void __attribute__((constructor)) -__constructor_order_last(void) -{ - if (!__constructor_order) - __constructor_order = _CONSTRUCTOR_ORDER_BACKWARD; -} - -int main(int argc, char **argv) -{ - switch (argc) { - case 2: - rtc_file = argv[1]; - /* FALLTHROUGH */ - case 1: - break; - default: - fprintf(stderr, "usage: %s [rtcdev]\n", argv[0]); - return 1; - } - - return test_harness_run(argc, argv); -} +TEST_HARNESS_MAIN -- 2.34.1

1 day, 10 hours

2
2
0 0

[PATCH net-next v9 00/14] Device Memory TCP

by Mina Almasry

v9: === Major Changes: -------------- GVE queue API has been merged. Submitting this version as non-RFC after rebasing on top of the merged API, and dropped the out of tree queue API I was carrying on github. Addressed the little feedback v8 has received. Detailed changelog: ------------------ - Added new patch from David Wei to this series for netdev_rx_queue_restart() - Fixed sparse error. - Removed CONFIG_ checks in netmem_is_net_iov() - Flipped skb->readable to skb->unreadable - Minor fixes to selftests & docs. RFC v8: ======= Major Changes: -------------- - Fixed build error generated by patch-by-patch build. - Applied docs suggestions from Randy. RFC v7: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the feedback RFCv6 received from folks, namely Jakub, Yunsheng, Arnd, David, & Pavel. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v7/ Detailed changelog: - Use admin-perm in netlink API. - Addressed feedback from Jakub with regards to netlink API implementation. - Renamed devmem.c functions to something more appropriate for that file. - Improve the performance seen through the page_pool benchmark. - Fix the value definition of all the SO_DEVMEM_* uapi. - Various fixes to documentation. Perf - page-pool benchmark: --------------------------- Improved performance of bench_page_pool_simple.ko tests compared to v6: https://pastebin.com/raw/v5dYRg8L net-next base: 8 cycle fast path. RFC v6: 10 cycle fast path. RFC v7: 9 cycle fast path. RFC v7 with CONFIG_DMA_SHARED_BUFFER disabled: 8 cycle fast path, same as baseline. Perf - Devmem TCP benchmark: --------------------- Perf is about the same regardless of the changes in v7, namely the removal of the static_branch_unlikely to improve the page_pool benchmark performance: 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. RFC v6: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the little feedback RFCv5 received. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v6/ This version also comes with some performance data recorded in the cover letter (see below changelog). Detailed changelog: - Rebased on top of the merged netmem_ref changes. - Converted skb->dmabuf to skb->readable (Pavel). Pavel's original suggestion was to remove the skb->dmabuf flag entirely, but when I looked into it closely, I found the issue that if we remove the flag we have to dereference the shinfo(skb) pointer to obtain the first frag to tell whether an skb is readable or not. This can cause a performance regression if it dirties the cache line when the shinfo(skb) was not really needed. Instead, I converted the skb->dmabuf flag into a generic skb->readable flag which can be re-used by io_uring 0-copy RX. - Squashed a few locking optimizations from Eric Dumazet in the RX path and the DEVMEM_DONTNEED setsockopt. - Expanded the tests a bit. Added validation for invalid scenarios and added some more coverage. Perf - page-pool benchmark: --------------------------- bench_page_pool_simple.ko tests with and without these changes: https://pastebin.com/raw/ncHDwAbn AFAIK the number that really matters in the perf tests is the 'tasklet_page_pool01_fast_path Per elem'. This one measures at about 8 cycles without the changes but there is some 1 cycle noise in some results. With the patches this regresses to 9 cycles with the changes but there is 1 cycle noise occasionally running this test repeatedly. Lastly I tried disable the static_branch_unlikely() in netmem_is_net_iov() check. To my surprise disabling the static_branch_unlikely() check reduces the fast path back to 8 cycles, but the 1 cycle noise remains. Perf - Devmem TCP benchmark: --------------------- 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. Major changes in RFC v5: ======================== 1. Rebased on top of 'Abstract page from net stack' series and used the new netmem type to refer to LSB set pointers instead of re-using struct page. 2. Downgraded this series back to RFC and called it RFC v5. This is because this series is now dependent on 'Abstract page from net stack'[1] and the queue API. Both are removed from the series to reduce the patch # and those bits are fairly independent or pre-requisite work. 3. Reworked the page_pool devmem support to use netmem and for some more unified handling. 4. Reworked the reference counting of net_iov (renamed from page_pool_iov) to use pp_ref_count for refcounting. The full changes including the dependent series and GVE page pool support is here: https://github.com/mina/linux/commits/tcpdevmem-rfcv5/ [1] https://patchwork.kernel.org/project/netdevbpf/list/?series=810774 Major changes in v1: ==================== 1. Implemented MVP queue API ndos to remove the userspace-visible driver reset. 2. Fixed issues in the napi_pp_put_page() devmem frag unref path. 3. Removed RFC tag. Many smaller addressed comments across all the patches (patches have individual change log). Full tree including the rest of the GVE driver changes: https://github.com/mina/linux/commits/tcpdevmem-v1 Changes in RFC v3: ================== 1. Pulled in the memory-provider dependency from Jakub's RFC[1] to make the series reviewable and mergeable. 2. Implemented multi-rx-queue binding which was a todo in v2. 3. Fix to cmsg handling. The sticking point in RFC v2[2] was the device reset required to refill the device rx-queues after the dmabuf bind/unbind. The solution suggested as I understand is a subset of the per-queue management ops Jakub suggested or similar: https://lore.kernel.org/netdev/20230815171638.4c057dcd@kernel.org/ This is not addressed in this revision, because: 1. This point was discussed at netconf & netdev and there is openness to using the current approach of requiring a device reset. 2. Implementing individual queue resetting seems to be difficult for my test bed with GVE. My prototype to test this ran into issues with the rx-queues not coming back up properly if reset individually. At the moment I'm unsure if it's a mistake in the POC or a genuine issue in the virtualization stack behind GVE, which currently doesn't test individual rx-queue restart. 3. Our usecases are not bothered by requiring a device reset to refill the buffer queues, and we'd like to support NICs that run into this limitation with resetting individual queues. My thought is that drivers that have trouble with per-queue configs can use the support in this series, while drivers that support new netdev ops to reset individual queues can automatically reset the queue as part of the dma-buf bind/unbind. The same approach with device resets is presented again for consideration with other sticking points addressed. This proposal includes the rx devmem path only proposed for merge. For a snapshot of my entire tree which includes the GVE POC page pool support & device memory support: https://github.com/torvalds/linux/compare/master...mina:linux:tcpdevmem-v3 [1] https://lore.kernel.org/netdev/f8270765-a27b-6ccf-33ea-cda097168d79@redhat.… [2] https://lore.kernel.org/netdev/CAHS8izOVJGJH5WF68OsRWFKJid1_huzzUK+hpKbLcL4… Changes in RFC v2: ================== The sticking point in RFC v1[1] was the dma-buf pages approach we used to deliver the device memory to the TCP stack. RFC v2 is a proof-of-concept that attempts to resolve this by implementing scatterlist support in the networking stack, such that we can import the dma-buf scatterlist directly. This is the approach proposed at a high level here[2]. Detailed changes: 1. Replaced dma-buf pages approach with importing scatterlist into the page pool. 2. Replace the dma-buf pages centric API with a netlink API. 3. Removed the TX path implementation - there is no issue with implementing the TX path with scatterlist approach, but leaving out the TX path makes it easier to review. 4. Functionality is tested with this proposal, but I have not conducted perf testing yet. I'm not sure there are regressions, but I removed perf claims from the cover letter until they can be re-confirmed. 5. Added Signed-off-by: contributors to the implementation. 6. Fixed some bugs with the RX path since RFC v1. Any feedback welcome, but specifically the biggest pending questions needing feedback IMO are: 1. Feedback on the scatterlist-based approach in general. 2. Netlink API (Patch 1 & 2). 3. Approach to handle all the drivers that expect to receive pages from the page pool (Patch 6). [1] https://lore.kernel.org/netdev/dfe4bae7-13a0-3c5d-d671-f61b375cb0b4@gmail.c… [2] https://lore.kernel.org/netdev/CAHS8izPm6XRS54LdCDZVd0C75tA1zHSu6jLVO8nzTLX… ================== * TL;DR: Device memory TCP (devmem TCP) is a proposal for transferring data to and/or from device memory efficiently, without bouncing the data to a host memory buffer. * Problem: A large amount of data transfers have device memory as the source and/or destination. Accelerators drastically increased the volume of such transfers. Some examples include: - ML accelerators transferring large amounts of training data from storage into GPU/TPU memory. In some cases ML training setup time can be as long as 50% of TPU compute time, improving data transfer throughput & efficiency can help improving GPU/TPU utilization. - Distributed training, where ML accelerators, such as GPUs on different hosts, exchange data among them. - Distributed raw block storage applications transfer large amounts of data with remote SSDs, much of this data does not require host processing. Today, the majority of the Device-to-Device data transfers the network are implemented as the following low level operations: Device-to-Host copy, Host-to-Host network transfer, and Host-to-Device copy. The implementation is suboptimal, especially for bulk data transfers, and can put significant strains on system resources, such as host memory bandwidth, PCIe bandwidth, etc. One important reason behind the current state is the kernel’s lack of semantics to express device to network transfers. * Proposal: In this patch series we attempt to optimize this use case by implementing socket APIs that enable the user to: 1. send device memory across the network directly, and 2. receive incoming network packets directly into device memory. Packet _payloads_ go directly from the NIC to device memory for receive and from device memory to NIC for transmit. Packet _headers_ go to/from host memory and are processed by the TCP/IP stack normally. The NIC _must_ support header split to achieve this. Advantages: - Alleviate host memory bandwidth pressure, compared to existing network-transfer + device-copy semantics. - Alleviate PCIe BW pressure, by limiting data transfer to the lowest level of the PCIe tree, compared to traditional path which sends data through the root complex. * Patch overview: ** Part 1: netlink API Gives user ability to bind dma-buf to an RX queue. ** Part 2: scatterlist support Currently the standard for device memory sharing is DMABUF, which doesn't generate struct pages. On the other hand, networking stack (skbs, drivers, and page pool) operate on pages. We have 2 options: 1. Generate struct pages for dmabuf device memory, or, 2. Modify the networking stack to process scatterlist. Approach #1 was attempted in RFC v1. RFC v2 implements approach #2. ** part 3: page pool support We piggy back on page pool memory providers proposal: https://github.com/kuba-moo/linux/tree/pp-providers It allows the page pool to define a memory provider that provides the page allocation and freeing. It helps abstract most of the device memory TCP changes from the driver. ** part 4: support for unreadable skb frags Page pool iovs are not accessible by the host; we implement changes throughput the networking stack to correctly handle skbs with unreadable frags. ** Part 5: recvmsg() APIs We define user APIs for the user to send and receive device memory. Not included with this series is the GVE devmem TCP support, just to simplify the review. Code available here if desired: https://github.com/mina/linux/tree/tcpdevmem This series is built on top of net-next with Jakub's pp-providers changes cherry-picked. * NIC dependencies: 1. (strict) Devmem TCP require the NIC to support header split, i.e. the capability to split incoming packets into a header + payload and to put each into a separate buffer. Devmem TCP works by using device memory for the packet payload, and host memory for the packet headers. 2. (optional) Devmem TCP works better with flow steering support & RSS support, i.e. the NIC's ability to steer flows into certain rx queues. This allows the sysadmin to enable devmem TCP on a subset of the rx queues, and steer devmem TCP traffic onto these queues and non devmem TCP elsewhere. The NIC I have access to with these properties is the GVE with DQO support running in Google Cloud, but any NIC that supports these features would suffice. I may be able to help reviewers bring up devmem TCP on their NICs. * Testing: The series includes a udmabuf kselftest that show a simple use case of devmem TCP and validates the entire data path end to end without a dependency on a specific dmabuf provider. ** Test Setup Kernel: net-next with this series and memory provider API cherry-picked locally. Hardware: Google Cloud A3 VMs. NIC: GVE with header split & RSS & flow steering support. Cc: Pavel Begunkov <asml.silence(a)gmail.com> Cc: David Wei <dw(a)davidwei.uk> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Yunsheng Lin <linyunsheng(a)huawei.com> Cc: Shailend Chand <shailend(a)google.com> Cc: Harshitha Ramamurthy <hramamurthy(a)google.com> Cc: Shakeel Butt <shakeel.butt(a)linux.dev> Cc: Jeroen de Borst <jeroendb(a)google.com> Cc: Praveen Kaligineedi <pkaligineedi(a)google.com> Jakub Kicinski (1): net: page_pool: create hooks for custom page providers Mina Almasry (13): netdev: add netdev_rx_queue_restart() net: netdev netlink api to bind dma-buf to a net device netdev: support binding dma-buf to netdevice netdev: netdevice devmem allocator page_pool: convert to use netmem page_pool: devmem support memory-provider: dmabuf devmem memory provider net: support non paged skb frags net: add support for skbs with unreadable frags tcp: RX path for devmem TCP net: add SO_DEVMEM_DONTNEED setsockopt to release RX frags net: add devmem TCP documentation selftests: add ncdevmem, netcat for devmem TCP Documentation/netlink/specs/netdev.yaml | 57 +++ Documentation/networking/devmem.rst | 258 +++++++++++ Documentation/networking/index.rst | 1 + arch/alpha/include/uapi/asm/socket.h | 6 + arch/mips/include/uapi/asm/socket.h | 6 + arch/parisc/include/uapi/asm/socket.h | 6 + arch/sparc/include/uapi/asm/socket.h | 6 + include/linux/skbuff.h | 61 ++- include/linux/skbuff_ref.h | 11 +- include/linux/socket.h | 1 + include/net/devmem.h | 124 ++++++ include/net/netdev_rx_queue.h | 5 + include/net/netmem.h | 230 +++++++++- include/net/page_pool/helpers.h | 157 +++++-- include/net/page_pool/types.h | 33 +- include/net/sock.h | 2 + include/net/tcp.h | 5 +- include/trace/events/page_pool.h | 29 +- include/uapi/asm-generic/socket.h | 6 + include/uapi/linux/netdev.h | 19 + include/uapi/linux/uio.h | 17 + net/bpf/test_run.c | 5 +- net/core/Makefile | 3 +- net/core/datagram.c | 6 + net/core/dev.c | 6 +- net/core/devmem.c | 376 ++++++++++++++++ net/core/gro.c | 8 +- net/core/netdev-genl-gen.c | 23 + net/core/netdev-genl-gen.h | 6 + net/core/netdev-genl.c | 107 +++++ net/core/netdev_rx_queue.c | 74 ++++ net/core/page_pool.c | 364 +++++++++------- net/core/skbuff.c | 83 +++- net/core/sock.c | 61 +++ net/ipv4/esp4.c | 3 +- net/ipv4/tcp.c | 254 ++++++++++- net/ipv4/tcp_input.c | 13 +- net/ipv4/tcp_ipv4.c | 10 + net/ipv4/tcp_minisocks.c | 2 + net/ipv4/tcp_output.c | 5 +- net/ipv6/esp6.c | 3 +- net/packet/af_packet.c | 4 +- tools/include/uapi/linux/netdev.h | 19 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 5 + tools/testing/selftests/net/ncdevmem.c | 542 ++++++++++++++++++++++++ 46 files changed, 2756 insertions(+), 267 deletions(-) create mode 100644 Documentation/networking/devmem.rst create mode 100644 include/net/devmem.h create mode 100644 net/core/devmem.c create mode 100644 net/core/netdev_rx_queue.c create mode 100644 tools/testing/selftests/net/ncdevmem.c -- 2.45.0.118.g7fe29c98d7-goog

1 day, 12 hours

4
22
0 0

[PATCH 0/2] selftests: harness: refactor __constructor_order

by Masahiro Yamada

This series refactors __constructor_order because __constructor_order_last() is unneeded. BTW, the comments in kselftest_harness.h was confusing to me. As far as I tested, all arches executed constructors in the forward order. [test code] #include <stdio.h> static int x; static void __attribute__((constructor)) increment(void) { x += 1; } static void __attribute__((constructor)) multiply(void) { x *= 2; } int main(void) { printf("foo = %d\n", x); return 0; } It should print 2 for forward order systems, 1 for reverse order systems. I executed it on some archtes by using QEMU. I always got 2. Masahiro Yamada (2): selftests: harness: remove unneeded __constructor_order_last() selftests: harness: rename __constructor_order for clarification .../drivers/s390x/uvdevice/test_uvdevice.c | 6 ------ tools/testing/selftests/hid/hid_bpf.c | 6 ------ tools/testing/selftests/kselftest_harness.h | 18 ++++-------------- tools/testing/selftests/rtc/rtctest.c | 7 ------- 4 files changed, 4 insertions(+), 33 deletions(-) -- 2.40.1

1 day, 13 hours

2
6
0 0

[PATCH net v3] selftests: net: kill smcrouted in the cleanup logic in amt.sh

by Taehee Yoo

The amt.sh requires smcrouted for multicasting routing. So, it starts smcrouted before forwarding tests. It must be stopped after all tests, but it isn't. To fix this issue, it kills smcrouted in the cleanup logic. Fixes: c08e8baea78e ("selftests: add amt interface selftest script") Signed-off-by: Taehee Yoo <ap420073(a)gmail.com> --- The v1 patch is here: https://lore.kernel.org/netdev/20240508040643.229383-1-ap420073@gmail.com/ v3 - Do not change shebang. v2 - Headline change. - Kill smcrouted process only if amt.pid exists. - Do not remove the return value. - Remove timeout logic because it was already fixed by following commit 4c639b6a7b9d ("selftests: net: move amt to socat for better compatibility") - Fix shebang. tools/testing/selftests/net/amt.sh | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh index 5175a42cbe8a..7e7ed6c558da 100755 --- a/tools/testing/selftests/net/amt.sh +++ b/tools/testing/selftests/net/amt.sh @@ -77,6 +77,7 @@ readonly LISTENER=$(mktemp -u listener-XXXXXXXX) readonly GATEWAY=$(mktemp -u gateway-XXXXXXXX) readonly RELAY=$(mktemp -u relay-XXXXXXXX) readonly SOURCE=$(mktemp -u source-XXXXXXXX) +readonly SMCROUTEDIR="$(mktemp -d)" ERR=4 err=0 @@ -85,6 +86,11 @@ exit_cleanup() for ns in "$@"; do ip netns delete "${ns}" 2>/dev/null || true done + if [ -f "$SMCROUTEDIR/amt.pid" ]; then + smcpid=$(< $SMCROUTEDIR/amt.pid) + kill $smcpid + fi + rm -rf $SMCROUTEDIR exit $ERR } @@ -167,7 +173,7 @@ setup_iptables() setup_mcast_routing() { - ip netns exec "${RELAY}" smcrouted + ip netns exec "${RELAY}" smcrouted -P $SMCROUTEDIR/amt.pid ip netns exec "${RELAY}" smcroutectl a relay_src \ 172.17.0.2 239.0.0.1 amtr ip netns exec "${RELAY}" smcroutectl a relay_src \ -- 2.34.1

1 day, 17 hours

1
0
0 0

[PATCH] selftests: drivers/s390x: Use SKIP() during FIXTURE_SETUP

by Kees Cook

Instead of mixing selftest harness and ksft helpers, perform SKIP testing from the FIXTURE_SETUPs. This also means TEST_HARNESS_MAIN does not need to be open-coded. Signed-off-by: Kees Cook <keescook(a)chromium.org> --- Cc: Christian Borntraeger <borntraeger(a)linux.ibm.com> Cc: Janosch Frank <frankja(a)linux.ibm.com> Cc: Claudio Imbrenda <imbrenda(a)linux.ibm.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Masahiro Yamada <masahiroy(a)kernel.org> Cc: kvm(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org --- I wasn't able to build or run test this, since it's very s390 specific, it seems? --- .../drivers/s390x/uvdevice/test_uvdevice.c | 32 ++++++++----------- 1 file changed, 13 insertions(+), 19 deletions(-) diff --git a/tools/testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c b/tools/testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c index ea0cdc37b44f..9622fac42597 100644 --- a/tools/testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c +++ b/tools/testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c @@ -18,6 +18,16 @@ #define UV_PATH "/dev/uv" #define BUFFER_SIZE 0x200 + +#define open_uv() \ +do { \ + self->uv_fd = open(UV_PATH, O_ACCMODE); \ + if (self->uv_fd < 0) \ + SKIP(return, "No uv-device or cannot access " UV_PATH "\n" \ + "Enable CONFIG_S390_UV_UAPI and check the access rights on " \ + UV_PATH ".\n"); \ +} while (0) + FIXTURE(uvio_fixture) { int uv_fd; struct uvio_ioctl_cb uvio_ioctl; @@ -37,7 +47,7 @@ FIXTURE_VARIANT_ADD(uvio_fixture, att) { FIXTURE_SETUP(uvio_fixture) { - self->uv_fd = open(UV_PATH, O_ACCMODE); + open_uv(); self->uvio_ioctl.argument_addr = (__u64)self->buffer; self->uvio_ioctl.argument_len = variant->arg_size; @@ -159,7 +169,7 @@ FIXTURE(attest_fixture) { FIXTURE_SETUP(attest_fixture) { - self->uv_fd = open(UV_PATH, O_ACCMODE); + open_uv(); self->uvio_ioctl.argument_addr = (__u64)&self->uvio_attest; self->uvio_ioctl.argument_len = sizeof(self->uvio_attest); @@ -257,20 +267,4 @@ TEST_F(attest_fixture, att_inval_addr) att_inval_addr_test(&self->uvio_attest.meas_addr, _metadata, self); } -static void __attribute__((constructor)) __constructor_order_last(void) -{ - if (!__constructor_order) - __constructor_order = _CONSTRUCTOR_ORDER_BACKWARD; -} - -int main(int argc, char **argv) -{ - int fd = open(UV_PATH, O_ACCMODE); - - if (fd < 0) - ksft_exit_skip("No uv-device or cannot access " UV_PATH "\n" - "Enable CONFIG_S390_UV_UAPI and check the access rights on " - UV_PATH ".\n"); - close(fd); - return test_harness_run(argc, argv); -} +TEST_HARNESS_MAIN -- 2.34.1

2 days, 7 hours

1
0
0 0

[PATCH] selftests: hid: Do not open-code TEST_HARNESS_MAIN

by Kees Cook

Avoid open-coding TEST_HARNESS_MAIN. (It might change, for example.) Signed-off-by: Kees Cook <keescook(a)chromium.org> --- Cc: Jiri Kosina <jikos(a)kernel.org> Cc: Benjamin Tissoires <bentiss(a)kernel.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Masahiro Yamada <masahiroy(a)kernel.org> Cc: linux-input(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/hid/hid_bpf.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/hid/hid_bpf.c b/tools/testing/selftests/hid/hid_bpf.c index f825623e3edc..943fa62a4f78 100644 --- a/tools/testing/selftests/hid/hid_bpf.c +++ b/tools/testing/selftests/hid/hid_bpf.c @@ -961,17 +961,11 @@ static int libbpf_print_fn(enum libbpf_print_level level, return 0; } -static void __attribute__((constructor)) __constructor_order_last(void) -{ - if (!__constructor_order) - __constructor_order = _CONSTRUCTOR_ORDER_BACKWARD; -} - -int main(int argc, char **argv) +static void __attribute__((constructor)) __one_time_init(void) { /* Use libbpf 1.0 API mode */ libbpf_set_strict_mode(LIBBPF_STRICT_ALL); libbpf_set_print(libbpf_print_fn); - - return test_harness_run(argc, argv); } + +TEST_HARNESS_MAIN -- 2.34.1

2 days, 7 hours

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror