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

[PATCH bpf-next v4 2/4] selftests/bpf: Add Launch Time request to xdp_hw_metadata

by Song Yoong Siang

Add Launch Time hw offload request to xdp_hw_metadata. User can configure the delta of launch time to HW RX-time by using "-l" argument. The default delta is 100,000,000 nanosecond. Signed-off-by: Song Yoong Siang <yoong.siang.song(a)intel.com> --- tools/testing/selftests/bpf/xdp_hw_metadata.c | 30 +++++++++++++++++-- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 6f7b15d6c6ed..795c1d14e02d 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -13,6 +13,7 @@ * - UDP 9091 packets trigger TX reply * - TX HW timestamp is requested and reported back upon completion * - TX checksum is requested + * - TX launch time HW offload is requested for transmission */ #include <test_progs.h> @@ -64,6 +65,8 @@ int rxq; bool skip_tx; __u64 last_hw_rx_timestamp; __u64 last_xdp_rx_timestamp; +__u64 last_launch_time; +__u64 launch_time_delta_to_hw_rx_timestamp = 100000000; /* 0.1 second */ void test__fail(void) { /* for network_helpers.c */ } @@ -298,6 +301,8 @@ static bool complete_tx(struct xsk *xsk, clockid_t clock_id) if (meta->completion.tx_timestamp) { __u64 ref_tstamp = gettime(clock_id); + print_tstamp_delta("HW Launch-time", "HW TX-complete-time", + last_launch_time, meta->completion.tx_timestamp); print_tstamp_delta("HW TX-complete-time", "User TX-complete-time", meta->completion.tx_timestamp, ref_tstamp); print_tstamp_delta("XDP RX-time", "User TX-complete-time", @@ -395,6 +400,14 @@ static void ping_pong(struct xsk *xsk, void *rx_packet, clockid_t clock_id) xsk, ntohs(udph->check), ntohs(want_csum), meta->request.csum_start, meta->request.csum_offset); + /* Set the value of launch time */ + meta->flags |= XDP_TXMD_FLAGS_LAUNCH_TIME; + meta->request.launch_time = last_hw_rx_timestamp + + launch_time_delta_to_hw_rx_timestamp; + last_launch_time = meta->request.launch_time; + print_tstamp_delta("HW RX-time", "HW Launch-time", last_hw_rx_timestamp, + meta->request.launch_time); + memcpy(data, rx_packet, len); /* don't share umem chunk for simplicity */ tx_desc->options |= XDP_TX_METADATA; tx_desc->len = len; @@ -402,10 +415,14 @@ static void ping_pong(struct xsk *xsk, void *rx_packet, clockid_t clock_id) xsk_ring_prod__submit(&xsk->tx, 1); } +#define SLEEP_PER_ITERATION_IN_US 10 +#define SLEEP_PER_ITERATION_IN_NS (SLEEP_PER_ITERATION_IN_US * 1000) +#define MAX_ITERATION(x) (((x) / SLEEP_PER_ITERATION_IN_NS) + 500) static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t clock_id) { const struct xdp_desc *rx_desc; struct pollfd fds[rxq + 1]; + int max_iterations; __u64 comp_addr; __u64 addr; __u32 idx = 0; @@ -418,6 +435,9 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t fds[i].revents = 0; } + /* Calculate max iterations to wait for transmit completion */ + max_iterations = MAX_ITERATION(launch_time_delta_to_hw_rx_timestamp); + fds[rxq].fd = server_fd; fds[rxq].events = POLLIN; fds[rxq].revents = 0; @@ -477,10 +497,10 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t if (ret) printf("kick_tx ret=%d\n", ret); - for (int j = 0; j < 500; j++) { + for (int j = 0; j < max_iterations; j++) { if (complete_tx(xsk, clock_id)) break; - usleep(10); + usleep(SLEEP_PER_ITERATION_IN_US); } } } @@ -608,6 +628,7 @@ static void print_usage(void) " -h Display this help and exit\n\n" " -m Enable multi-buffer XDP for larger MTU\n" " -r Don't generate AF_XDP reply (rx metadata only)\n" + " -l Delta of launch time to HW RX-time in ns (default: 100,000,000ns)\n" "Generate test packets on the other machine with:\n" " echo -n xdp | nc -u -q1 <dst_ip> 9091\n"; @@ -618,7 +639,7 @@ static void read_args(int argc, char *argv[]) { int opt; - while ((opt = getopt(argc, argv, "chmr")) != -1) { + while ((opt = getopt(argc, argv, "chmrl:")) != -1) { switch (opt) { case 'c': bind_flags &= ~XDP_USE_NEED_WAKEUP; @@ -634,6 +655,9 @@ static void read_args(int argc, char *argv[]) case 'r': skip_tx = true; break; + case 'l': + launch_time_delta_to_hw_rx_timestamp = atoll(optarg); + break; case '?': if (isprint(optopt)) fprintf(stderr, "Unknown option: -%c\n", optopt); -- 2.34.1

5 months, 3 weeks

3
2
0 0

Re: [PATCH 3/3] selftests/mm: virtual_address_range: Dump to /dev/null

by David Hildenbrand

On 08.01.25 07:09, Dev Jain wrote: > > On 07/01/25 8:44 pm, Thomas Weißschuh wrote: >> During the execution of validate_complete_va_space() a lot of memory is >> on the VM subsystem. When running on a low memory subsystem an OOM may >> be triggered, when writing to the dump file as the filesystem may also >> require memory. >> >> On my test system with 1100MiB physical memory: >> >> Tasks state (memory values in pages): >> [ pid ] uid tgid total_vm rss rss_anon rss_file rss_shmem pgtables_bytes swapents oom_score_adj name >> [ 57] 0 57 34359215953 695 256 0 439 1064390656 0 0 virtual_address >> >> Out of memory: Killed process 57 (virtual_address) total-vm:137436863812kB, anon-rss:1024kB, file-rss:0kB, shmem-rss:1756kB, UID:0 pgtables:1039444kB oom_score_adj:0 >> <snip> >> fault_in_iov_iter_readable+0x4a/0xd0 >> generic_perform_write+0x9c/0x280 >> shmem_file_write_iter+0x86/0x90 >> vfs_write+0x29c/0x480 >> ksys_write+0x6c/0xe0 >> do_syscall_64+0x9e/0x1a0 >> entry_SYSCALL_64_after_hwframe+0x77/0x7f >> >> Write the dumped data into /dev/null instead which does not require >> additional memory during write(), making the code simpler as a >> side-effect. >> >> Signed-off-by: Thomas Weißschuh<thomas.weissschuh(a)linutronix.de> >> --- >> tools/testing/selftests/mm/virtual_address_range.c | 6 ++---- >> 1 file changed, 2 insertions(+), 4 deletions(-) >> >> diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c >> index 484f82c7b7c871f82a7d9ec6d6c649f2ab1eb0cd..4042fd878acd702d23da2c3293292de33bd48143 100644 >> --- a/tools/testing/selftests/mm/virtual_address_range.c >> +++ b/tools/testing/selftests/mm/virtual_address_range.c >> @@ -103,10 +103,9 @@ static int validate_complete_va_space(void) >> FILE *file; >> int fd; >> >> - fd = open("va_dump", O_CREAT | O_WRONLY, 0600); >> - unlink("va_dump"); >> + fd = open("/dev/null", O_WRONLY); >> if (fd < 0) { >> - ksft_test_result_skip("cannot create or open dump file\n"); >> + ksft_test_result_skip("cannot create or open /dev/null\n"); >> ksft_finished(); >> } >> >> @@ -152,7 +151,6 @@ static int validate_complete_va_space(void) >> while (start_addr + hop < end_addr) { >> if (write(fd, (void *)(start_addr + hop), 1) != 1) >> return 1; >> - lseek(fd, 0, SEEK_SET); >> >> hop += MAP_CHUNK_SIZE; >> } >> > > The reason I had not used /dev/null was that write() was succeeding to /dev/null > even from an address not in my VA space. I was puzzled about this behaviour of > /dev/null and I chose to ignore it and just use a real file. > > To test this behaviour, run the following program: > > #include <stdio.h> > #include <stdlib.h> > #include <unistd.h> > #include <fcntl.h> > #include <sys/mman.h> > intmain() > { > intfd; > fd = open("va_dump", O_CREAT| O_WRONLY, 0600); > unlink("va_dump"); > // fd = open("/dev/null", O_WRONLY); > intret = munmap((void*)(1UL<< 30), 100); > if(!ret) > printf("munmap succeeded\n"); > intres = write(fd, (void*)(1UL<< 30), 1); > if(res == 1) > printf("write succeeded\n"); > return0; > } > The write will fail as expected, but if you comment out the va_dump > lines and use /dev/null, the write will succeed. What exactly do we want to achieve with the write? Verify that the output of /proc/self/map is reasonable and we can actually resolve a fault / map a page? Why not access the memory directly+signal handler or using /proc/self/mem, so you can avoid the temp file completely? -- Cheers, David / dhildenb

5 months, 3 weeks

2
1
0 0

[PATCH net-next v2] selftests: drv-net: test drivers sleeping in ndo_get_stats64

by Jakub Kicinski

Most of our tests use rtnetlink to read device stats, so they don't expose the drivers much to paths in which device stats are read under RCU. Add tests which hammer profcs reads to make sure drivers: - don't sleep while reporting stats, - can handle parallel reads, - can handle device going down while reading. Set ifname on the env class in NetDrvEnv, we already do that in NetDrvEpEnv. KTAP version 1 1..7 ok 1 stats.check_pause ok 2 stats.check_fec ok 3 stats.pkt_byte_sum ok 4 stats.qstat_by_ifindex ok 5 stats.check_down ok 6 stats.procfs_hammer # completed up/down cycles: 6 ok 7 stats.procfs_downup_hammer # Totals: pass:7 fail:0 xfail:0 xpass:0 skip:0 error:0 Reviewed-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: linux-kselftest(a)vger.kernel.org v2: - fix spelling in a comment v1: https://lore.kernel.org/20250105011525.1718380-1-kuba@kernel.org --- .../selftests/drivers/net/lib/py/env.py | 1 + tools/testing/selftests/drivers/net/stats.py | 94 ++++++++++++++++++- tools/testing/selftests/net/lib/py/ksft.py | 5 + 3 files changed, 97 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index fea343f209ea..987e452d3a45 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -48,6 +48,7 @@ from .remote import Remote else: self._ns = NetdevSimDev(**kwargs) self.dev = self._ns.nsims[0].dev + self.ifname = self.dev['ifname'] self.ifindex = self.dev['ifindex'] def __enter__(self): diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 031ac9def6c0..efcc1e10575b 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -2,12 +2,15 @@ # SPDX-License-Identifier: GPL-2.0 import errno +import subprocess +import time from lib.py import ksft_run, ksft_exit, ksft_pr -from lib.py import ksft_ge, ksft_eq, ksft_in, ksft_true, ksft_raises, KsftSkipEx, KsftXfailEx +from lib.py import ksft_ge, ksft_eq, ksft_is, ksft_in, ksft_lt, ksft_true, ksft_raises +from lib.py import KsftSkipEx, KsftXfailEx from lib.py import ksft_disruptive from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError from lib.py import NetDrvEnv -from lib.py import ip, defer +from lib.py import cmd, ip, defer ethnl = EthtoolFamily() netfam = NetdevFamily() @@ -174,10 +177,95 @@ rtnl = RtnlFamily() netfam.qstats_get({"ifindex": cfg.ifindex, "scope": "queue"}, dump=True) +def __run_inf_loop(body): + body = body.strip() + if body[-1] != ';': + body += ';' + + return subprocess.Popen(f"while true; do {body} done", shell=True, + stdout=subprocess.PIPE, stderr=subprocess.PIPE) + + +def __stats_increase_sanely(old, new) -> None: + for k in old.keys(): + ksft_ge(new[k], old[k]) + ksft_lt(new[k] - old[k], 1 << 31, comment="likely wrapping error") + + +def procfs_hammer(cfg) -> None: + """ + Reading stats via procfs only holds the RCU lock, which is not an exclusive + lock, make sure drivers can handle parallel reads of stats. + """ + one = __run_inf_loop("cat /proc/net/dev") + defer(one.kill) + two = __run_inf_loop("cat /proc/net/dev") + defer(two.kill) + + time.sleep(1) + # Make sure the processes are running + ksft_is(one.poll(), None) + ksft_is(two.poll(), None) + + rtstat1 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + time.sleep(2) + rtstat2 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + __stats_increase_sanely(rtstat1, rtstat2) + # defers will kill the loops + + +@ksft_disruptive +def procfs_downup_hammer(cfg) -> None: + """ + Reading stats via procfs only holds the RCU lock, drivers often try + to sleep when reading the stats, or don't protect against races. + """ + # Max out the queues, we'll flip between max and 1 + channels = ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + if channels['combined-count'] == 0: + rx_type = 'rx' + else: + rx_type = 'combined' + cur_queue_cnt = channels[f'{rx_type}-count'] + max_queue_cnt = channels[f'{rx_type}-max'] + + cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}") + defer(cmd, f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}") + + # Real test stats + stats = __run_inf_loop("cat /proc/net/dev") + defer(stats.kill) + + ipset = f"ip link set dev {cfg.ifname}" + defer(ip, f"link set dev {cfg.ifname} up") + # The "echo -n 1" lets us count iterations below + updown = f"{ipset} down; sleep 0.05; {ipset} up; sleep 0.05; " + \ + f"ethtool -L {cfg.ifname} {rx_type} 1; " + \ + f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}; " + \ + "echo -n 1" + updown = __run_inf_loop(updown) + kill_updown = defer(updown.kill) + + time.sleep(1) + # Make sure the processes are running + ksft_is(stats.poll(), None) + ksft_is(updown.poll(), None) + + rtstat1 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + # We're looking for crashes, give it extra time + time.sleep(9) + rtstat2 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + __stats_increase_sanely(rtstat1, rtstat2) + + kill_updown.exec() + stdout, _ = updown.communicate(timeout=5) + ksft_pr("completed up/down cycles:", len(stdout.decode('utf-8'))) + + def main() -> None: with NetDrvEnv(__file__, queue_count=100) as cfg: ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex, - check_down], + check_down, procfs_hammer, procfs_downup_hammer], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 477ae76de93d..3efe005436cd 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -71,6 +71,11 @@ KSFT_DISRUPTIVE = True _fail("Check failed", a, "not in", b, comment) +def ksft_is(a, b, comment=""): + if a is not b: + _fail("Check failed", a, "is not", b, comment) + + def ksft_ge(a, b, comment=""): if a < b: _fail("Check failed", a, "<", b, comment) -- 2.47.1

5 months, 3 weeks

2
1
0 0

[PATCH v8 0/2] selftests: tmpfs: Add kselftest support

by Shivam Chaudhary

This version 8 patch series replace direct error handling methods with ksft macros, which provide better reporting.Currently, when the tmpfs test runs, it does not display any output if it passes,and if it fails (particularly when not run as root),it simply exits without any warning or message. This series of patch adds: 1. Add 'ksft_print_header()' and 'ksft_set_plan()' to structure test outputs more effectively. 2. skip if not run as root. 3. Replace direct error handling with 'ksft_test_result_*', macros for better reporting. v7->v8: - Remove extra Prints v7 v1: https://lore.kernel.org/all/20250102100459.1291426-2-cvam0000@gmail.com/ v7 v2: https://lore.kernel.org/all/20250102100459.1291426-3-cvam0000@gmail.com/ v6->v7: - Improve the handling of failure macros. v6 v1: https://lore.kernel.org/all/20241219152929.4005003-2-cvam0000@gmail.com/ v6 v2: https://lore.kernel.org/all/20241219152929.4005003-3-cvam0000@gmail.com/ v5->v6: - Skip if not run as root. v5 v1: https://lore.kernel.org/all/20241112143056.565122-2-cvam0000@gmail.com/ v5 v2: https://lore.kernel.org/all/20241112143056.565122-3-cvam0000@gmail.com/ v4->v5: - Remove unnecessary pass messages. - Remove unnecessary use of KSFT_SKIP. - Add appropriate use of ksft_exit_fail_msg. v4 v1: https://lore.kernel.org/all/8db9feab-0600-440b-b4b2-042695a100b5@linuxfound… v4 v2: https://lore.kernel.org/all/63d5e3bb-9817-4a34-98fe-823a9cac7c16@linuxfound… v3->v4: - Start a patchset - Split patch into smaller patches to make it easy to review. Patch1 Replace 'ksft_test_result_skip' with 'KSFT_SKIP' during root run check. Patch2 Replace 'ksft_test_result_fail' with 'KSFT_SKIP' where fail does not make sense, or failure could be due to not unsupported APIs with appropriate warnings. v3: https://lore.kernel.org/all/20241028185756.111832-1-cvam0000@gmail.com/ v2->v3: - Remove extra ksft_set_plan() - Remove function for unshare() - Fix the comment style v2: https://lore.kernel.org/all/20241026191621.2860376-1-cvam0000@gmail.com/ v1->v2: - Make the commit message more clear. v1: https://lore.kernel.org/all/20241024200228.1075840-1-cvam0000@gmail.com/T/#u thanks Shivam Shivam Chaudhary (2): selftests: tmpfs: Add Test-skip if not run as root selftests: tmpfs: Add kselftest support to tmpfs .../selftests/tmpfs/bug-link-o-tmpfile.c | 41 ++++++++++++------- 1 file changed, 26 insertions(+), 15 deletions(-) -- 2.34.1

5 months, 3 weeks

2
3
0 0

[PATCH] selftests: harness: fix printing of mismatch values in __EXPECT()

by Dmitry V. Levin

intptr_t and uintptr_t are not big enough types on 32-bit architectures when printing 64-bit values, resulting to the following incorrect diagnostic output: # get_syscall_info.c:209:get_syscall_info:Expected exp_args[2] (3134324433) == info.entry.args[1] (3134324433) Replace intptr_t and uintptr_t with intmax_t and uintmax_t, respectively. With this fix, the same test produces more usable diagnostic output: # get_syscall_info.c:209:get_syscall_info:Expected exp_args[2] (3134324433) == info.entry.args[1] (18446744072548908753) Fixes: b5bb6d3068ea ("selftests/seccomp: fix 32-bit build warnings") Signed-off-by: Dmitry V. Levin <ldv(a)strace.io> --- tools/testing/selftests/kselftest_harness.h | 24 ++++++++++----------- 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index a5a72415e37b..666c9fde76da 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -760,33 +760,33 @@ /* Report with actual signedness to avoid weird output. */ \ switch (is_signed_type(__exp) * 2 + is_signed_type(__seen)) { \ case 0: { \ - unsigned long long __exp_print = (uintptr_t)__exp; \ - unsigned long long __seen_print = (uintptr_t)__seen; \ - __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ + uintmax_t __exp_print = (uintmax_t)__exp; \ + uintmax_t __seen_print = (uintmax_t)__seen; \ + __TH_LOG("Expected %s (%ju) %s %s (%ju)", \ _expected_str, __exp_print, #_t, \ _seen_str, __seen_print); \ break; \ } \ case 1: { \ - unsigned long long __exp_print = (uintptr_t)__exp; \ - long long __seen_print = (intptr_t)__seen; \ - __TH_LOG("Expected %s (%llu) %s %s (%lld)", \ + uintmax_t __exp_print = (uintmax_t)__exp; \ + intmax_t __seen_print = (intmax_t)__seen; \ + __TH_LOG("Expected %s (%ju) %s %s (%jd)", \ _expected_str, __exp_print, #_t, \ _seen_str, __seen_print); \ break; \ } \ case 2: { \ - long long __exp_print = (intptr_t)__exp; \ - unsigned long long __seen_print = (uintptr_t)__seen; \ - __TH_LOG("Expected %s (%lld) %s %s (%llu)", \ + intmax_t __exp_print = (intmax_t)__exp; \ + uintmax_t __seen_print = (uintmax_t)__seen; \ + __TH_LOG("Expected %s (%jd) %s %s (%ju)", \ _expected_str, __exp_print, #_t, \ _seen_str, __seen_print); \ break; \ } \ case 3: { \ - long long __exp_print = (intptr_t)__exp; \ - long long __seen_print = (intptr_t)__seen; \ - __TH_LOG("Expected %s (%lld) %s %s (%lld)", \ + intmax_t __exp_print = (intmax_t)__exp; \ + intmax_t __seen_print = (intmax_t)__seen; \ + __TH_LOG("Expected %s (%jd) %s %s (%jd)", \ _expected_str, __exp_print, #_t, \ _seen_str, __seen_print); \ break; \ -- ldv

5 months, 3 weeks

3
2
0 0

[RFC PATCH RESEND v2 0/2] Add file seal to prevent future exec mappings

by Isaac J. Manjarres

* Resending because I accidentally forgot to include Lorenzo in the "to" list. Android uses the ashmem driver [1] for creating shared memory regions between processes. The ashmem driver exposes an ioctl command for processes to restrict the permissions an ashmem buffer can be mapped with. Buffers are created with the ability to be mapped as readable, writable, and executable. Processes remove the ability to map some ashmem buffers as executable to ensure that those buffers cannot be used to inject malicious code for another process to run. Other buffers retain their ability to be mapped as executable, as these buffers can be used for just-in-time (JIT) compilation. So there is a need to be able to remove the ability to map a buffer as executable on a per-buffer basis. Android is currently trying to migrate towards replacing its ashmem driver usage with memfd. Part of the transition involved introducing a library that serves to abstract away how shared memory regions are allocated (i.e. ashmem vs memfd). This allows clients to use a single interface for restricting how a buffer can be mapped without having to worry about how it is handled for ashmem (through the ioctl command mentioned earlier) or memfd (through file seals). While memfd has support for preventing buffers from being mapped as writable beyond a certain point in time (thanks to F_SEAL_FUTURE_WRITE), it does not have a similar interface to prevent buffers from being mapped as executable beyond a certain point. However, that could be implemented as a file seal (F_SEAL_FUTURE_EXEC) which works similarly to F_SEAL_FUTURE_WRITE. F_SEAL_FUTURE_WRITE was chosen as a template for how this new seal should behave, instead of F_SEAL_WRITE, for the following reasons: 1. Having the new seal behave like F_SEAL_FUTURE_WRITE matches the behavior that was present with ashmem. This aids in seamlessly transitioning clients away from ashmem to memfd. 2. Making the new seal behave like F_SEAL_WRITE would mean that no mappings that could become executable in the future (i.e. via mprotect()) can exist when the seal is applied. However, there are known cases (e.g. CursorWindow [2]) where restrictions are applied on how a buffer can be mapped after a mapping has already been made. That mapping may have VM_MAYEXEC set, which would not allow the seal to be applied successfully. Therefore, the F_SEAL_FUTURE_EXEC seal was designed to have the same semantics as F_SEAL_FUTURE_WRITE. Note: this series depends on Lorenzo's work [3], [4], [5] from Andrew Morton's mm-unstable branch [6], which reworks memfd's file seal checks, allowing for newer file seals to be implemented in a cleaner fashion. Changes from v1 ==> v2: - Changed the return code to be -EPERM instead of -EACCES when attempting to map an exec sealed file with PROT_EXEC to align to mmap()'s man page. Thank you Kalesh Singh for spotting this! - Rebased on top of Lorenzo's work to cleanup memfd file seal checks in mmap() ([3], [4], and [5]). Thank you for this Lorenzo! - Changed to deny PROT_EXEC mappings only if the mapping is shared, instead of for both shared and private mappings, after discussing this with Lorenzo. Opens: - Lorenzo brought up that this patch may negatively impact the usage of MFD_NOEXEC_SCOPE_NOEXEC_ENFORCED [7]. However, it is not clear to me why that is the case. At the moment, my intent is for the executable permissions of the file to be disjoint from the ability to create executable mappings. Links: [1] https://cs.android.com/android/kernel/superproject/+/common-android-mainlin… [2] https://developer.android.com/reference/android/database/CursorWindow [3] https://lore.kernel.org/all/cover.1732804776.git.lorenzo.stoakes@oracle.com/ [4] https://lkml.kernel.org/r/20241206212846.210835-1-lorenzo.stoakes@oracle.com [5] https://lkml.kernel.org/r/7dee6c5d-480b-4c24-b98e-6fa47dbd8a23@lucifer.local [6] https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git/tree/?h=mm-unst… [7] https://lore.kernel.org/all/3a53b154-1e46-45fb-a559-65afa7a8a788@lucifer.lo… Links to previous versions: v1: https://lore.kernel.org/all/20241206010930.3871336-1-isaacmanjarres@google.… Isaac J. Manjarres (2): mm/memfd: Add support for F_SEAL_FUTURE_EXEC to memfd selftests/memfd: Add tests for F_SEAL_FUTURE_EXEC include/uapi/linux/fcntl.h | 1 + mm/memfd.c | 39 ++++++++++- tools/testing/selftests/memfd/memfd_test.c | 79 ++++++++++++++++++++++ 3 files changed, 118 insertions(+), 1 deletion(-) -- 2.47.1.613.gc27f4b7a9f-goog

5 months, 3 weeks

6
14
0 0

[PATCH v6] riscv: selftests: Fix warnings pointer masking test

by Charlie Jenkins

When compiling the pointer masking tests with -Wall this warning is present: pointer_masking.c: In function ‘test_tagged_addr_abi_sysctl’: pointer_masking.c:203:9: warning: ignoring return value of ‘pwrite’ declared with attribute ‘warn_unused_result’ [-Wunused-result] 203 | pwrite(fd, &value, 1, 0); | ^~~~~~~~~~~~~~~~~~~~~~~~ pointer_masking.c:208:9: warning: ignoring return value of ‘pwrite’ declared with attribute ‘warn_unused_result’ [-Wunused-result] 208 | pwrite(fd, &value, 1, 0); I came across this on riscv64-linux-gnu-gcc (Ubuntu 11.4.0-1ubuntu1~22.04). Fix this by checking that the number of bytes written equal the expected number of bytes written. Fixes: 7470b5afd150 ("riscv: selftests: Add a pointer masking test") Signed-off-by: Charlie Jenkins <charlie(a)rivosinc.com> Reviewed-by: Andrew Jones <ajones(a)ventanamicro.com> --- Changes in v6: - Add back ksft_test_result() (Samuel) - Link to v5: https://lore.kernel.org/r/20241206-fix_warnings_pointer_masking_tests-v5-1-… Changes in v5: - No longer skip second pwrite if first one fails - Use wrapper function instead of goto (Drew) - Link to v4: https://lore.kernel.org/r/20241205-fix_warnings_pointer_masking_tests-v4-1-… Changes in v4: - Skip sysctl_enabled test if first pwrite failed - Link to v3: https://lore.kernel.org/r/20241205-fix_warnings_pointer_masking_tests-v3-1-… Changes in v3: - Fix sysctl enabled test case (Drew/Alex) - Move pwrite err condition into goto (Drew) - Link to v2: https://lore.kernel.org/r/20241204-fix_warnings_pointer_masking_tests-v2-1-… Changes in v2: - I had ret != 2 for testing, I changed it to be ret != 1. - Link to v1: https://lore.kernel.org/r/20241204-fix_warnings_pointer_masking_tests-v1-1-… --- .../testing/selftests/riscv/abi/pointer_masking.c | 28 +++++++++++++++++----- 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/riscv/abi/pointer_masking.c b/tools/testing/selftests/riscv/abi/pointer_masking.c index dee41b7ee3e323150d55523c8acbf3ec38857b87..059d2e87eb1f737caf44f692b239bf3e49c233b4 100644 --- a/tools/testing/selftests/riscv/abi/pointer_masking.c +++ b/tools/testing/selftests/riscv/abi/pointer_masking.c @@ -185,8 +185,20 @@ static void test_fork_exec(void) } } +static bool pwrite_wrapper(int fd, void *buf, size_t count, const char *msg) +{ + int ret = pwrite(fd, buf, count, 0); + + if (ret != count) { + ksft_perror(msg); + return false; + } + return true; +} + static void test_tagged_addr_abi_sysctl(void) { + char *err_pwrite_msg = "failed to write to /proc/sys/abi/tagged_addr_disabled\n"; char value; int fd; @@ -200,14 +212,18 @@ static void test_tagged_addr_abi_sysctl(void) } value = '1'; - pwrite(fd, &value, 1, 0); - ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL, - "sysctl disabled\n"); + if (!pwrite_wrapper(fd, &value, 1, "write '1'")) + ksft_test_result_fail(err_pwrite_msg); + else + ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL, + "sysctl disabled\n"); value = '0'; - pwrite(fd, &value, 1, 0); - ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0, - "sysctl enabled\n"); + if (!pwrite_wrapper(fd, &value, 1, "write '0'")) + ksft_test_result_fail(err_pwrite_msg); + else + ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0, + "sysctl enabled\n"); set_tagged_addr_ctrl(0, false); --- base-commit: 40384c840ea1944d7c5a392e8975ed088ecf0b37 change-id: 20241204-fix_warnings_pointer_masking_tests-3860e4f35429 -- - Charlie

5 months, 4 weeks

2
1
0 0

[PATCH net-next v7 00/11] net: Improve netns handling in rtnetlink

by Xiao Liang

This patch series includes some netns-related improvements and fixes for rtnetlink, to make link creation more intuitive: 1) Creating link in another net namespace doesn't conflict with link names in current one. 2) Refector rtnetlink link creation. Create link in target namespace directly. So that # ip link add netns ns1 link-netns ns2 tun0 type gre ... will create tun0 in ns1, rather than create it in ns2 and move to ns1. And don't conflict with another interface named "tun0" in current netns. Patch 01 serves for 1) to avoids link name conflict in different netns. To achieve 2), there're mainly 3 steps: - Patch 02 packs newlink() parameters into a struct, including the original "src_net" along with more netns context. No semantic changes are introduced. - Patch 03 ~ 07 converts device drivers to use the explicit netns extracted from params. - Patch 08 ~ 09 removes the old netns parameter, and converts rtnetlink to create device in target netns directly. Patch 10 ~ 11 adds some tests for link name and link netns. BTW please note there're some issues found in current code: - In amt_newlink() drivers/net/amt.c: amt->net = net; ... amt->stream_dev = dev_get_by_index(net, ... Uses net, but amt_lookup_upper_dev() only searches in dev_net. So the AMT device may not be properly deleted if it's in a different netns from lower dev. - In gtp_newlink() in drivers/net/gtp.c: gtp->net = src_net; ... gn = net_generic(dev_net(dev), gtp_net_id); list_add_rcu(&gtp->list, &gn->gtp_dev_list); Uses src_net, but priv is linked to list in dev_net. So it may not be properly deleted on removal of link netns. - In pfcp_newlink() in drivers/net/pfcp.c: pfcp->net = net; ... pn = net_generic(dev_net(dev), pfcp_net_id); list_add_rcu(&pfcp->list, &pn->pfcp_dev_list); Same as above. - In lowpan_newlink() in net/ieee802154/6lowpan/core.c: wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK])); Looks for IFLA_LINK in dev_net, but in theory the ifindex is defined in link netns. --- v7: - Add selftest kconfig. - Remove a duplicated test of ip6gre. v6: link: https://lore.kernel.org/all/20241218130909.2173-1-shaw.leon@gmail.com/ - Split prototype, driver and rtnetlink changes. - Add more tests for link netns. - Fix IPv6 tunnel net overwriten in ndo_init(). - Reorder variable declarations. - Exclude a ip_tunnel-specific patch. v5: link: https://lore.kernel.org/all/20241209140151.231257-1-shaw.leon@gmail.com/ - Fix function doc in batman-adv. - Include peer_net in rtnl newlink parameters. v4: link: https://lore.kernel.org/all/20241118143244.1773-1-shaw.leon@gmail.com/ - Pack newlink() parameters to a single struct. - Use ynl async_msg_queue.empty() in selftest. v3: link: https://lore.kernel.org/all/20241113125715.150201-1-shaw.leon@gmail.com/ - Drop "netns_atomic" flag and module parameter. Add netns parameter to newlink() instead, and convert drivers accordingly. - Move python NetNSEnter helper to net selftest lib. v2: link: https://lore.kernel.org/all/20241107133004.7469-1-shaw.leon@gmail.com/ - Check NLM_F_EXCL to ensure only link creation is affected. - Add self tests for link name/ifindex conflict and notifications in different netns. - Changes in dummy driver and ynl in order to add the test case. v1: link: https://lore.kernel.org/all/20241023023146.372653-1-shaw.leon@gmail.com/ Xiao Liang (11): rtnetlink: Lookup device in target netns when creating link rtnetlink: Pack newlink() params into struct net: Use link netns in newlink() of rtnl_link_ops ieee802154: 6lowpan: Use link netns in newlink() of rtnl_link_ops net: ip_tunnel: Use link netns in newlink() of rtnl_link_ops net: ipv6: Use link netns in newlink() of rtnl_link_ops net: xfrm: Use link netns in newlink() of rtnl_link_ops rtnetlink: Remove "net" from newlink params rtnetlink: Create link directly in target net namespace selftests: net: Add python context manager for netns entering selftests: net: Add test cases for link and peer netns drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 11 +- drivers/net/amt.c | 16 +- drivers/net/bareudp.c | 11 +- drivers/net/bonding/bond_netlink.c | 8 +- drivers/net/can/dev/netlink.c | 4 +- drivers/net/can/vxcan.c | 9 +- .../ethernet/qualcomm/rmnet/rmnet_config.c | 11 +- drivers/net/geneve.c | 11 +- drivers/net/gtp.c | 9 +- drivers/net/ipvlan/ipvlan.h | 4 +- drivers/net/ipvlan/ipvlan_main.c | 15 +- drivers/net/ipvlan/ipvtap.c | 10 +- drivers/net/macsec.c | 15 +- drivers/net/macvlan.c | 8 +- drivers/net/macvtap.c | 11 +- drivers/net/netkit.c | 9 +- drivers/net/pfcp.c | 11 +- drivers/net/ppp/ppp_generic.c | 10 +- drivers/net/team/team_core.c | 7 +- drivers/net/veth.c | 9 +- drivers/net/vrf.c | 11 +- drivers/net/vxlan/vxlan_core.c | 11 +- drivers/net/wireguard/device.c | 11 +- drivers/net/wireless/virtual/virt_wifi.c | 14 +- drivers/net/wwan/wwan_core.c | 25 +++- include/net/ip_tunnels.h | 5 +- include/net/rtnetlink.h | 44 +++++- net/8021q/vlan_netlink.c | 15 +- net/batman-adv/soft-interface.c | 16 +- net/bridge/br_netlink.c | 12 +- net/caif/chnl_net.c | 6 +- net/core/rtnetlink.c | 35 +++-- net/hsr/hsr_netlink.c | 14 +- net/ieee802154/6lowpan/core.c | 9 +- net/ipv4/ip_gre.c | 27 ++-- net/ipv4/ip_tunnel.c | 10 +- net/ipv4/ip_vti.c | 10 +- net/ipv4/ipip.c | 14 +- net/ipv6/ip6_gre.c | 42 ++++-- net/ipv6/ip6_tunnel.c | 20 ++- net/ipv6/ip6_vti.c | 16 +- net/ipv6/sit.c | 18 ++- net/xfrm/xfrm_interface_core.c | 15 +- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/config | 5 + .../testing/selftests/net/lib/py/__init__.py | 2 +- tools/testing/selftests/net/lib/py/netns.py | 18 +++ tools/testing/selftests/net/link_netns.py | 141 ++++++++++++++++++ tools/testing/selftests/net/netns-name.sh | 10 ++ 49 files changed, 550 insertions(+), 226 deletions(-) create mode 100755 tools/testing/selftests/net/link_netns.py -- 2.47.1

5 months, 4 weeks

3
18
0 0

[PATCH 0/3] tun: Unify vnet implementation and fill full vnet header

by Akihiko Odaki

When I implemented virtio's hash-related features to tun/tap [1], I found tun/tap does not fill the entire region reserved for the virtio header, leaving some uninitialized hole in the middle of the buffer after read()/recvmesg(). This series fills the uninitialized hole. More concretely, the num_buffers field will be initialized with 1, and the other fields will be inialized with 0. Setting the num_buffers field to 1 is mandated by virtio 1.0 [2]. The change to virtio header is preceded by another change that refactors tun and tap to unify their virtio-related code. [1]: https://lore.kernel.org/r/20241008-rss-v5-0-f3cf68df005d@daynix.com [2]: https://lore.kernel.org/r/20241227084256-mutt-send-email-mst@kernel.org/ Signed-off-by: Akihiko Odaki <akihiko.odaki(a)daynix.com> --- Akihiko Odaki (3): tun: Unify vnet implementation tun: Pad virtio header with zero tun: Set num_buffers for virtio 1.0 MAINTAINERS | 1 + drivers/net/Kconfig | 5 ++ drivers/net/Makefile | 1 + drivers/net/tap.c | 174 ++++++---------------------------------- drivers/net/tun.c | 212 ++++++++----------------------------------------- drivers/net/tun_vnet.c | 191 ++++++++++++++++++++++++++++++++++++++++++++ drivers/net/tun_vnet.h | 24 ++++++ 7 files changed, 281 insertions(+), 327 deletions(-) --- base-commit: a32e14f8aef69b42826cf0998b068a43d486a9e9 change-id: 20241230-tun-66e10a49b0c7 Best regards, -- Akihiko Odaki <akihiko.odaki(a)daynix.com>

5 months, 4 weeks

1
3
0 0

[PATCH net-next v2 0/4] netconsole: selftest for userdata overflow

by Breno Leitao

Implement comprehensive testing for netconsole userdata entry handling, demonstrating correct behavior when creating maximum entries and preventing unauthorized overflow. Refactor existing test infrastructure to support modular, reusable helper functions that validate strict entry limit enforcement. Also, add a warning if update_userdata() sees more than MAX_USERDATA_ITEMS entries. This shouldn't happen and it is a bug that shouldn't be silently ignored. Signed-off-by: Breno Leitao <leitao(a)debian.org> --- Changes in v2: - Add the new script (netcons_overflow.sh) in tools/testing/selftests/drivers/net/Makefile as suggested by Simon Horman - Link to v1: https://lore.kernel.org/r/20241204-netcons_overflow_test-v1-0-a85a8d0ace21@… --- Breno Leitao (4): netconsole: Warn if MAX_USERDATA_ITEMS limit is exceeded netconsole: selftest: Split the helpers from the selftest netconsole: selftest: Delete all userdata keys netconsole: selftest: verify userdata entry limit MAINTAINERS | 3 +- drivers/net/netconsole.c | 2 +- tools/testing/selftests/drivers/net/Makefile | 1 + .../selftests/drivers/net/lib/sh/lib_netcons.sh | 225 +++++++++++++++++++++ .../testing/selftests/drivers/net/netcons_basic.sh | 218 +------------------- .../selftests/drivers/net/netcons_overflow.sh | 67 ++++++ 6 files changed, 297 insertions(+), 219 deletions(-) --- base-commit: 94c16fd4df9089931f674fb9aaec41ea20b0fd7a change-id: 20241204-netcons_overflow_test-eaf735d1f743 Best regards, -- Breno Leitao <leitao(a)debian.org>

5 months, 4 weeks

2
6
0 0

[PATCH v1] selftests/mm: Set allocated memory to non-zero content in cow test

by Ryan Roberts

After commit b1f202060afe ("mm: remap unused subpages to shared zeropage when splitting isolated thp"), cow test cases involving swapping out THPs via madvise(MADV_PAGEOUT) started to be skipped due to the subsequent check via pagemap determining that the memory was not actually swapped out. Logs similar to this were emitted: ... # [RUN] Basic COW after fork() ... with swapped-out, PTE-mapped THP (16 kB) ok 2 # SKIP MADV_PAGEOUT did not work, is swap enabled? # [RUN] Basic COW after fork() ... with single PTE of swapped-out THP (16 kB) ok 3 # SKIP MADV_PAGEOUT did not work, is swap enabled? # [RUN] Basic COW after fork() ... with swapped-out, PTE-mapped THP (32 kB) ok 4 # SKIP MADV_PAGEOUT did not work, is swap enabled? ... The commit in question introduces the behaviour of scanning THPs and if their content is predominantly zero, it splits them and replaces the pages which are wholly zero with the zero page. These cow test cases were getting caught up in this. So let's avoid that by filling the contents of all allocated memory with a non-zero value. With this in place, the tests are passing again. Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> --- Applies on top of mm-unstable (f349e79bfbf3) Thanks, Ryan tools/testing/selftests/mm/cow.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 32c6ccc2a6be..1238e1c5aae1 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -758,7 +758,7 @@ static void do_run_with_base_page(test_fn fn, bool swapout) } /* Populate a base page. */ - memset(mem, 0, pagesize); + memset(mem, 1, pagesize); if (swapout) { madvise(mem, pagesize, MADV_PAGEOUT); @@ -824,12 +824,12 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize) * Try to populate a THP. Touch the first sub-page and test if * we get the last sub-page populated automatically. */ - mem[0] = 0; + mem[0] = 1; if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { ksft_test_result_skip("Did not get a THP populated\n"); goto munmap; } - memset(mem, 0, thpsize); + memset(mem, 1, thpsize); size = thpsize; switch (thp_run) { @@ -1012,7 +1012,7 @@ static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize) } /* Populate an huge page. */ - memset(mem, 0, hugetlbsize); + memset(mem, 1, hugetlbsize); /* * We need a total of two hugetlb pages to handle COW/unsharing -- 2.43.0

5 months, 4 weeks

3
3
0 0

Re: [PATCH 3/3] selftests/mm: virtual_address_range: Dump to /dev/null

by Thomas Weißschuh

On Wed, Jan 08, 2025 at 11:39:40AM +0530, Dev Jain wrote: > > On 07/01/25 8:44 pm, Thomas Weißschuh wrote: > > During the execution of validate_complete_va_space() a lot of memory is > > on the VM subsystem. When running on a low memory subsystem an OOM may > > be triggered, when writing to the dump file as the filesystem may also > > require memory. > > > > On my test system with 1100MiB physical memory: > > > > Tasks state (memory values in pages): > > [ pid ] uid tgid total_vm rss rss_anon rss_file rss_shmem pgtables_bytes swapents oom_score_adj name > > [ 57] 0 57 34359215953 695 256 0 439 1064390656 0 0 virtual_address > > > > Out of memory: Killed process 57 (virtual_address) total-vm:137436863812kB, anon-rss:1024kB, file-rss:0kB, shmem-rss:1756kB, UID:0 pgtables:1039444kB oom_score_adj:0 > > <snip> > > fault_in_iov_iter_readable+0x4a/0xd0 > > generic_perform_write+0x9c/0x280 > > shmem_file_write_iter+0x86/0x90 > > vfs_write+0x29c/0x480 > > ksys_write+0x6c/0xe0 > > do_syscall_64+0x9e/0x1a0 > > entry_SYSCALL_64_after_hwframe+0x77/0x7f > > > > Write the dumped data into /dev/null instead which does not require > > additional memory during write(), making the code simpler as a > > side-effect. > > > > Signed-off-by: Thomas Weißschuh<thomas.weissschuh(a)linutronix.de> > > --- > > tools/testing/selftests/mm/virtual_address_range.c | 6 ++---- > > 1 file changed, 2 insertions(+), 4 deletions(-) > > > > diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c > > index 484f82c7b7c871f82a7d9ec6d6c649f2ab1eb0cd..4042fd878acd702d23da2c3293292de33bd48143 100644 > > --- a/tools/testing/selftests/mm/virtual_address_range.c > > +++ b/tools/testing/selftests/mm/virtual_address_range.c > > @@ -103,10 +103,9 @@ static int validate_complete_va_space(void) > > FILE *file; > > int fd; > > - fd = open("va_dump", O_CREAT | O_WRONLY, 0600); > > - unlink("va_dump"); > > + fd = open("/dev/null", O_WRONLY); > > if (fd < 0) { > > - ksft_test_result_skip("cannot create or open dump file\n"); > > + ksft_test_result_skip("cannot create or open /dev/null\n"); > > ksft_finished(); > > } > > @@ -152,7 +151,6 @@ static int validate_complete_va_space(void) > > while (start_addr + hop < end_addr) { > > if (write(fd, (void *)(start_addr + hop), 1) != 1) > > return 1; > > - lseek(fd, 0, SEEK_SET); > > hop += MAP_CHUNK_SIZE; > > } > > > > The reason I had not used /dev/null was that write() was succeeding to /dev/null > even from an address not in my VA space. I was puzzled about this behaviour of > /dev/null and I chose to ignore it and just use a real file. That makes sense and I can reproduce your example. Switching to another dummy file which reads the written data like /dev/random also leads to OOM, so wouldn't help either. Thanks for the explanation. @Andrew, could you drop this patch? > To test this behaviour, run the following program: [..] PS: Your mail contained HTML and did not make it to the list archives. (And the text variant of the example program was corrupted)

5 months, 4 weeks

1
0
0 0

[PATCH v7 00/30] 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/ntsync7 == Previous versions == Changes from v6: * rename NTSYNC_IOC_SEM_POST to NTSYNC_IOC_SEM_RELEASE (matching the NT terminology instead of POSIX), * change object creation ioctls to return the fds directly in the return value instead of through the args struct, which simplifies the API a bit. * Link to v6: https://lore.kernel.org/lkml/20241209185904.507350-1-zfigura@codeweavers.co… * Link to v5: https://lore.kernel.org/lkml/20240519202454.1192826-1-zfigura@codeweavers.c… * 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 (30): ntsync: Return the fd from NTSYNC_IOC_CREATE_SEM. ntsync: Rename NTSYNC_IOC_SEM_POST to NTSYNC_IOC_SEM_RELEASE. 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 | 385 +++++ MAINTAINERS | 9 + drivers/misc/Kconfig | 1 - drivers/misc/ntsync.c | 992 +++++++++++- include/uapi/linux/ntsync.h | 42 +- 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 | 1343 +++++++++++++++++ 11 files changed, 2767 insertions(+), 16 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: cdd30ebb1b9f36159d66f088b61aee264e649d7a -- 2.45.2

5 months, 4 weeks

3
33
0 0

[PATCH 0/3] selftests: bpf: Migrate test_xdp_redirect.sh to test_progs

by Bastien Curutchet (eBPF Foundation)

Hi all, This patch series continues the work to migrate the *.sh tests into prog_tests. test_xdp_redirect.sh tests the XDP redirections done through bpf_redirect(). These XDP redirections are already tested by prog_tests/xdp_do_redirect.c but IMO it doesn't cover the exact same code path because xdp_do_redirect.c uses bpf_prog_test_run_opts() to trigger redirections of 'fake packets' while test_xdp_redirect.sh redirects packets coming from the network. Also, the test_xdp_redirect.sh script tests the redirections with both SKB and DRV modes while xdp_do_redirect.c only tests the DRV mode. The patch series adds two new test cases in prog_tests/xdp_do_redirect.c to replace the test_xdp_redirect.sh script. Signed-off-by: Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com> --- Bastien Curutchet (eBPF Foundation) (3): selftests/bpf: test_xdp_redirect: Rename BPF sections selftests/bpf: Migrate test_xdp_redirect.sh to xdp_do_redirect.c selftests/bpf: Migrate test_xdp_redirect.c to test_xdp_do_redirect.c tools/testing/selftests/bpf/Makefile | 1 - .../selftests/bpf/prog_tests/xdp_do_redirect.c | 192 +++++++++++++++++++++ .../selftests/bpf/progs/test_xdp_do_redirect.c | 12 ++ .../selftests/bpf/progs/test_xdp_redirect.c | 26 --- tools/testing/selftests/bpf/test_xdp_redirect.sh | 79 --------- 5 files changed, 204 insertions(+), 106 deletions(-) --- base-commit: da86bde1e6d1b887efc46af5ee1f9bbccd27233e change-id: 20241219-xdp_redirect-2b8ec79dc24e Best regards, -- Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com>

5 months, 4 weeks

4
10
0 0

[PATCH v4 0/9] arm64: Support 2024 dpISA extensions

by Mark Brown

The 2024 architecture release includes a number of data processing extensions, mostly SVE and SME additions with a few others. These are all very straightforward extensions which add instructions but no architectural state so only need hwcaps and exposing of the ID registers to KVM guests and userspace. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v4: - Fix encodings for ID_AA64ISAR3_EL1. - Link to v3: https://lore.kernel.org/r/20241203-arm64-2024-dpisa-v3-0-a6c78b1aa297@kerne… Changes in v3: - Commit log update for the hwcap test. - Link to v2: https://lore.kernel.org/r/20241030-arm64-2024-dpisa-v2-0-b6601a15d2a5@kerne… Changes in v2: - Filter KVM guest visible bitfields in ID_AA64ISAR3_EL1 to only those we make writeable. - Link to v1: https://lore.kernel.org/r/20241028-arm64-2024-dpisa-v1-0-a38d08b008a8@kerne… --- Mark Brown (9): arm64/sysreg: Update ID_AA64PFR2_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64ISAR3_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64FPFR0_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64ZFR0_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64SMFR0_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64ISAR2_EL1 to DDI0601 2024-09 arm64/hwcap: Describe 2024 dpISA extensions to userspace KVM: arm64: Allow control of dpISA extensions in ID_AA64ISAR3_EL1 kselftest/arm64: Add 2024 dpISA extensions to hwcap test Documentation/arch/arm64/elf_hwcaps.rst | 51 ++++++ arch/arm64/include/asm/hwcap.h | 17 ++ arch/arm64/include/uapi/asm/hwcap.h | 17 ++ arch/arm64/kernel/cpufeature.c | 35 ++++ arch/arm64/kernel/cpuinfo.c | 17 ++ arch/arm64/kvm/sys_regs.c | 6 +- arch/arm64/tools/sysreg | 87 +++++++++- tools/testing/selftests/arm64/abi/hwcap.c | 273 +++++++++++++++++++++++++++++- 8 files changed, 493 insertions(+), 10 deletions(-) --- base-commit: 40384c840ea1944d7c5a392e8975ed088ecf0b37 change-id: 20241008-arm64-2024-dpisa-8091074a7f48 Best regards, -- Mark Brown <broonie(a)kernel.org>

5 months, 4 weeks

3
15
0 0

[PATCH 00/14] pkeys kselftests improvements

by Kevin Brodsky

This series brings various cleanups and fixes for the mm (mostly pkeys) kselftests. The original goal was to make the pkeys tests work out of the box and without build warning - it turned out to be more involved than expected. The most important change is enabling -O2 when building all mm kselftests (patch 5). This is actually needed for the pkeys tests to run successfully (see gcc command line at the top of protection_keys.c and pkey_sighandler_tests.c), and seems to have no negative impact on the other tests. It certainly can't hurt performance! The following patches address a few obvious issues in the pkeys tests (unused code, bad scope for functions/variables, etc.) and finally make a couple of small improvements. There is one ugliness that this series does not fix: some functions in pkey-<arch>.h call functions that are actually defined in protection_keys.c. For instance, expect_fault_on_read_execonly_key() in pkey-x86.h calls expected_pkey_fault(). This means that other test programs that use pkey-helpers.h (namely pkey_sighandler_tests) would fail to link if they called such functions defined in pkey-<arch>.h. Fixing this would require a more comprehensive reorganisation of the pkey-* headers, which doesn't seem worth it (patch 9 adds a comment to pkey-helpers.h to clarify the situation). Some more details on the patches: - Patch 1 is an unrelated fix that was revealed by inspecting a warning. It seems fairly harmless though, so I thought I'd just post it as part of this series. - Patch 2-5 fix various warnings that come up by building the mm tests at -O2 and finally enable -O2. - Patch 6-12 are various cleanups for the pkeys tests. Patch 11 in particular enables is_pkeys_supported() to be called from outside protection_keys.c (patch 13 relies on this). - Patch 13-14 are small improvements to pkey_sighandler_tests.c. Many thanks to Ryan Roberts for checking that the mm tests still run fine on arm64 with those patches applied. I've also checked that the pkeys tests run fine on arm64 and x86. - Kevin --- Cc: akpm(a)linux-foundation.org Cc: aruna.ramakrishna(a)oracle.com Cc: catalin.marinas(a)arm.com Cc: dave.hansen(a)linux.intel.com Cc: joey.gouly(a)arm.com Cc: keith.lucas(a)oracle.com Cc: ryan.roberts(a)arm.com Cc: shuah(a)kernel.org Cc: linux-arm-kernel(a)lists.infradead.org Cc: linux-kselftest(a)vger.kernel.org Cc: x86(a)kernel.org --- Kevin Brodsky (14): selftests/mm: Fix condition in uffd_move_test_common() selftests/mm: Fix -Wmaybe-uninitialized warnings selftests/mm: Fix strncpy() length selftests/mm: Fix -Warray-bounds warnings in pkey_sighandler_tests selftests/mm: Build with -O2 selftests/mm: Remove unused pkey helpers selftests/mm: Define types using typedef in pkey-helpers.h selftests/mm: Ensure pkey-*.h define inline functions only selftests/mm: Remove empty pkey helper definition selftests/mm: Ensure non-global pkey symbols are marked static selftests/mm: Use sys_pkey helpers consistently selftests/mm: Rename pkey register macro selftests/mm: Skip pkey_sighandler_tests if support is missing selftests/mm: Remove X permission from sigaltstack mapping tools/testing/selftests/mm/Makefile | 6 +- tools/testing/selftests/mm/ksm_tests.c | 2 +- tools/testing/selftests/mm/mremap_test.c | 2 +- tools/testing/selftests/mm/pkey-arm64.h | 6 +- tools/testing/selftests/mm/pkey-helpers.h | 61 ++--- tools/testing/selftests/mm/pkey-powerpc.h | 4 +- tools/testing/selftests/mm/pkey-x86.h | 6 +- .../selftests/mm/pkey_sighandler_tests.c | 32 +-- tools/testing/selftests/mm/pkey_util.c | 40 ++++ tools/testing/selftests/mm/protection_keys.c | 212 +++++++----------- tools/testing/selftests/mm/soft-dirty.c | 2 +- tools/testing/selftests/mm/uffd-unit-tests.c | 4 +- .../testing/selftests/mm/write_to_hugetlbfs.c | 2 +- 13 files changed, 163 insertions(+), 216 deletions(-) create mode 100644 tools/testing/selftests/mm/pkey_util.c -- 2.47.0

5 months, 4 weeks

2
18
0 0

[PATCH v1] selftests/mm: static process_madvise() wrapper for guard-pages

by Ryan Roberts

The recently introduced guard-pages mm selftest uses the process_madvise() syscall, a wrapper for which was added to glibc v2.36. For those of us stuck with older distributions this causes a compile error when compiling the mm selftests. For example Ubuntu 22.04 uses glibc 2.35, which does not have the wrapper. To workaround the issue, let's introduce our own static process_madvise() wrapper that uses glibc's syscall() helper. While we are at it, add the guard-page test suite to run_vmtests.sh so that it can be automatically run by CI systems. Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> --- Applies on top of mm-unstable (f349e79bfbf3) Thanks, Ryan tools/testing/selftests/mm/guard-pages.c | 10 ++++++++-- tools/testing/selftests/mm/run_vmtests.sh | 5 +++++ 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/mm/guard-pages.c b/tools/testing/selftests/mm/guard-pages.c index d8f8dee9ebbd..ece37212a8a2 100644 --- a/tools/testing/selftests/mm/guard-pages.c +++ b/tools/testing/selftests/mm/guard-pages.c @@ -55,6 +55,12 @@ static int pidfd_open(pid_t pid, unsigned int flags) return syscall(SYS_pidfd_open, pid, flags); } +static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, + size_t n, int advice, unsigned int flags) +{ + return syscall(__NR_process_madvise, pidfd, iovec, n, advice, flags); +} + /* * Enable our signal catcher and try to read/write the specified buffer. The * return value indicates whether the read/write succeeds without a fatal @@ -419,7 +425,7 @@ TEST_F(guard_pages, process_madvise) ASSERT_EQ(munmap(&ptr_region[99 * page_size], page_size), 0); /* Now guard in one step. */ - count = process_madvise(pidfd, vec, 6, MADV_GUARD_INSTALL, 0); + count = sys_process_madvise(pidfd, vec, 6, MADV_GUARD_INSTALL, 0); /* OK we don't have permission to do this, skip. */ if (count == -1 && errno == EPERM) @@ -440,7 +446,7 @@ TEST_F(guard_pages, process_madvise) ASSERT_FALSE(try_read_write_buf(&ptr3[19 * page_size])); /* Now do the same with unguard... */ - count = process_madvise(pidfd, vec, 6, MADV_GUARD_REMOVE, 0); + count = sys_process_madvise(pidfd, vec, 6, MADV_GUARD_REMOVE, 0); /* ...and everything should now succeed. */ diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 2fc290d9430c..00c3f07ea100 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -45,6 +45,8 @@ separated by spaces: vmalloc smoke tests - hmm hmm smoke tests +- madv_guard + test madvise(2) MADV_GUARD_INSTALL and MADV_GUARD_REMOVE options - madv_populate test memadvise(2) MADV_POPULATE_{READ,WRITE} options - memfd_secret @@ -375,6 +377,9 @@ CATEGORY="mremap" run_test ./mremap_dontunmap CATEGORY="hmm" run_test bash ./test_hmm.sh smoke +# MADV_GUARD_INSTALL and MADV_GUARD_REMOVE tests +CATEGORY="madv_guard" run_test ./guard-pages + # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate -- 2.43.0

5 months, 4 weeks

2
2
0 0

[PATCH v2 0/2] update kselftest framework to check for required configs

by Siddharth Menon

Currently, kselftests does not have a generalised mechanism to skip compilation and run tests when required kernel configuration options are disabled. This patch series adresses this issue by checking whether all required configs from selftest/<test>/config are enabled in the current kernel Siddharth Menon (2): selftests: Introduce script to validate required configs selftests/lib.mk: Introduce check to validate required configs tools/testing/selftests/lib.mk | 11 ++- tools/testing/selftests/mktest.pl | 138 ++++++++++++++++++++++++++++++ 2 files changed, 147 insertions(+), 2 deletions(-) mode change 100644 => 100755 tools/testing/selftests/lib.mk create mode 100755 tools/testing/selftests/mktest.pl -- 2.39.5

5 months, 4 weeks

2
4
0 0

[PATCH net-next] selftests/net: packetdrill: report benign debug flakes as xfail

by Willem de Bruijn

From: Willem de Bruijn <willemb(a)google.com> A few recently added packetdrill tests that are known time sensitive (e.g., because testing timestamping) occasionally fail in debug mode: https://netdev.bots.linux.dev/contest.html?executor=vmksft-packetdrill-dbg These failures are well understood. Correctness of the tests is verified in non-debug mode. Continue running in debug mode also, to keep coverage with debug instrumentation. But, only in debug mode, mark these tests with well understood timing issues as XFAIL (known failing) rather than FAIL when failing. Introduce an allow list xfail_list with known cases. Expand the ktap infrastructure with XFAIL support. Fixes: eab35989cc37 ("selftests/net: packetdrill: import tcp/fast_recovery, tcp/nagle, tcp/timestamping") Reported-by: Jakub Kicinski <kuba(a)kernel.org> Closes: https://lore.kernel.org/netdev/20241218100013.0c698629@kernel.org/ Signed-off-by: Willem de Bruijn <willemb(a)google.com> --- .../selftests/kselftest/ktap_helpers.sh | 15 ++++++++++-- .../selftests/net/packetdrill/ksft_runner.sh | 23 +++++++++++++++---- 2 files changed, 31 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/kselftest/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh index 79a125eb24c2..05a461890671 100644 --- a/tools/testing/selftests/kselftest/ktap_helpers.sh +++ b/tools/testing/selftests/kselftest/ktap_helpers.sh @@ -7,6 +7,7 @@ KTAP_TESTNO=1 KTAP_CNT_PASS=0 KTAP_CNT_FAIL=0 +KTAP_CNT_XFAIL=0 KTAP_CNT_SKIP=0 KSFT_PASS=0 @@ -69,6 +70,16 @@ ktap_test_skip() { KTAP_CNT_SKIP=$((KTAP_CNT_SKIP+1)) } +ktap_test_xfail() { + description="$1" + + result="ok" + directive="XFAIL" + __ktap_test "$result" "$description" "$directive" + + KTAP_CNT_XFAIL=$((KTAP_CNT_XFAIL+1)) +} + ktap_test_fail() { description="$1" @@ -99,7 +110,7 @@ ktap_exit_fail_msg() { ktap_finished() { ktap_print_totals - if [ $((KTAP_CNT_PASS + KTAP_CNT_SKIP)) -eq "$KSFT_NUM_TESTS" ]; then + if [ $((KTAP_CNT_PASS + KTAP_CNT_SKIP + KTAP_CNT_XFAIL)) -eq "$KSFT_NUM_TESTS" ]; then exit "$KSFT_PASS" else exit "$KSFT_FAIL" @@ -107,5 +118,5 @@ ktap_finished() { } ktap_print_totals() { - echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:0 xpass:0 skip:$KTAP_CNT_SKIP error:0" + echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:$KTAP_CNT_XFAIL xpass:0 skip:$KTAP_CNT_SKIP error:0" } diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh index 4071c133f29e..ff989c325eef 100755 --- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh +++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh @@ -23,7 +23,7 @@ if [ $# -ne 1 ]; then ktap_exit_fail_msg "usage: $0 <script>" exit "$KSFT_FAIL" fi -script="$1" +script="$(basename $1)" if [ -z "$(which packetdrill)" ]; then ktap_skip_all "packetdrill not found in PATH" @@ -31,16 +31,29 @@ if [ -z "$(which packetdrill)" ]; then fi declare -a optargs +failfunc=ktap_test_fail + if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then optargs+=('--tolerance_usecs=14000') + + # xfail tests that are known flaky with dbg config, not fixable. + # still run them for coverage (and expect 100% pass without dbg). + declare -ar xfail_list=( + "tcp_fast_recovery_prr-ss.*.pkt" + "tcp_timestamping.*.pkt" + "tcp_user_timeout_user-timeout-probe.pkt" + "tcp_zerocopy_epoll_.*.pkt" + ) + readonly xfail_regex="^($(printf '%s|' "${xfail_list[@]}"))$" + [[ "$script" =~ ${xfail_regex} ]] && failfunc=ktap_test_xfail fi ktap_print_header ktap_set_plan 2 -unshare -n packetdrill ${ipv4_args[@]} ${optargs[@]} $(basename $script) > /dev/null \ - && ktap_test_pass "ipv4" || ktap_test_fail "ipv4" -unshare -n packetdrill ${ipv6_args[@]} ${optargs[@]} $(basename $script) > /dev/null \ - && ktap_test_pass "ipv6" || ktap_test_fail "ipv6" +unshare -n packetdrill ${ipv4_args[@]} ${optargs[@]} $script > /dev/null \ + && ktap_test_pass "ipv4" || $failfunc "ipv4" +unshare -n packetdrill ${ipv6_args[@]} ${optargs[@]} $script > /dev/null \ + && ktap_test_pass "ipv6" || $failfunc "ipv6" ktap_finished -- 2.47.1.613.gc27f4b7a9f-goog

5 months, 4 weeks

2
1
0 0

[PATCH v6 0/5] introduce PIDFD_SELF* sentinels

by Lorenzo Stoakes

If you wish to utilise a pidfd interface to refer to the current process or thread it is rather cumbersome, requiring something like: int pidfd = pidfd_open(getpid(), 0 or PIDFD_THREAD); ... close(pidfd); Or the equivalent call opening /proc/self. It is more convenient to use a sentinel value to indicate to an interface that accepts a pidfd that we simply wish to refer to the current process thread. This series introduces sentinels for this purposes which can be passed as the pidfd in this instance rather than having to establish a dummy fd for this purpose. It is useful to refer to both the current thread from the userland's perspective for which we use PIDFD_SELF, and the current process from the userland's perspective, for which we use PIDFD_SELF_PROCESS. There is unfortunately some confusion between the kernel and userland as to what constitutes a process - a thread from the userland perspective is a process in userland, and a userland process is a thread group (more specifically the thread group leader from the kernel perspective). We therefore alias things thusly: * PIDFD_SELF_THREAD aliased by PIDFD_SELF - use PIDTYPE_PID. * PIDFD_SELF_THREAD_GROUP alised by PIDFD_SELF_PROCESS - use PIDTYPE_TGID. In all of the kernel code we refer to PIDFD_SELF_THREAD and PIDFD_SELF_THREAD_GROUP. However we expect users to use PIDFD_SELF and PIDFD_SELF_PROCESS. This matters for cases where, for instance, a user unshare()'s FDs or does thread-specific signal handling and where the user would be hugely confused if the FDs referenced or signal processed referred to the thread group leader rather than the individual thread. We ensure that pidfd_send_signal() and pidfd_getfd() work correctly, and assert as much in selftests. All other interfaces except setns() will work implicitly with this new interface, however it doesn't make sense to test waitid(P_PIDFD, ...) as waiting on ourselves is a blocking operation. In the case of setns() we explicitly disallow use of PIDFD_SELF* as it doesn't make sense to obtain the namespaces of our own process, and it would require work to implement this functionality there that would be of no use. We also do not provide the ability to utilise PIDFD_SELF* in ordinary fd operations such as open() or poll(), as this would require extensive work and be of no real use. v6: * Avoid static inline in UAPI header as suggested by Pedro. * Place PIDFD_SELF values out of range of errors and any other sentinel as suggested by Pedro. v5: * Fixup self test dependencies on pidfd/pidfd.h. https://lore.kernel.org/linux-mm/cover.1729848252.git.lorenzo.stoakes@oracl… v4: * Avoid returning an fd in the __pidfd_get_pid() function as pointed out by Christian, instead simply always pin the pid and maintain fd scope in the helper alone. * Add wrapper header file in tools/include/linux to allow for import of UAPI pidfd.h header without encountering the collision between system fcntl.h and linux/fcntl.h as discussed with Shuah and John. * Fixup tests to import the UAPI pidfd.h header working around conflicts between system fcntl.h and linux/fcntl.h which the UAPI pidfd.h imports, as reported by Shuah. * Use an int for pidfd_is_self_sentinel() to avoid any dependency on stdbool.h in userland. https://lore.kernel.org/linux-mm/cover.1729198898.git.lorenzo.stoakes@oracl… v3: * Do not fput() an invalid fd as reported by kernel test bot. * Fix unintended churn from moving variable declaration. https://lore.kernel.org/linux-mm/cover.1729073310.git.lorenzo.stoakes@oracl… v2: * Fix tests as reported by Shuah. * Correct RFC version lore link. https://lore.kernel.org/linux-mm/cover.1728643714.git.lorenzo.stoakes@oracl… Non-RFC v1: * Removed RFC tag - there seems to be general consensus that this change is a good idea, but perhaps some debate to be had on implementation. It seems sensible then to move forward with the RFC flag removed. * Introduced PIDFD_SELF_THREAD, PIDFD_SELF_THREAD_GROUP and their aliases PIDFD_SELF and PIDFD_SELF_PROCESS respectively. * Updated testing accordingly. https://lore.kernel.org/linux-mm/cover.1728578231.git.lorenzo.stoakes@oracl… RFC version: https://lore.kernel.org/linux-mm/cover.1727644404.git.lorenzo.stoakes@oracl… Lorenzo Stoakes (5): pidfd: extend pidfd_get_pid() and de-duplicate pid lookup pidfd: add PIDFD_SELF_* sentinels to refer to own thread/process tools: testing: separate out wait_for_pid() into helper header selftests: pidfd: add pidfd.h UAPI wrapper selftests: pidfd: add tests for PIDFD_SELF_* include/linux/pid.h | 34 ++++- include/uapi/linux/pidfd.h | 10 ++ kernel/exit.c | 4 +- kernel/nsproxy.c | 1 + kernel/pid.c | 65 +++++--- kernel/signal.c | 29 +--- tools/include/linux/pidfd.h | 14 ++ tools/testing/selftests/cgroup/test_kill.c | 2 +- .../pid_namespace/regression_enomem.c | 2 +- tools/testing/selftests/pidfd/Makefile | 3 +- tools/testing/selftests/pidfd/pidfd.h | 28 +--- .../selftests/pidfd/pidfd_getfd_test.c | 141 ++++++++++++++++++ tools/testing/selftests/pidfd/pidfd_helpers.h | 39 +++++ .../selftests/pidfd/pidfd_setns_test.c | 11 ++ tools/testing/selftests/pidfd/pidfd_test.c | 76 ++++++++-- 15 files changed, 371 insertions(+), 88 deletions(-) create mode 100644 tools/include/linux/pidfd.h create mode 100644 tools/testing/selftests/pidfd/pidfd_helpers.h -- 2.47.0

5 months, 4 weeks

3
13
0 0

[PATCH v4 00/14] iommufd: Add vIOMMU infrastructure (Part-3: vEVENTQ)

by Nicolin Chen

As the vIOMMU infrastructure series part-3, this introduces a new vEVENTQ object. The existing FAULT object provides a nice notification pathway to the user space with a queue already, so let vEVENTQ reuse that. Mimicing the HWPT structure, add a common EVENTQ structure to support its derivatives: IOMMUFD_OBJ_FAULT (existing) and IOMMUFD_OBJ_VEVENTQ (new). An IOMMUFD_CMD_VEVENTQ_ALLOC is introduced to allocate vEVENTQ object for vIOMMUs. One vIOMMU can have multiple vEVENTQs in different types but can not support multiple vEVENTQs in the same type. The forwarding part is fairly simple but might need to replace a physical device ID with a virtual device ID in a driver-level event data structure. So, this also adds some helpers for drivers to use. As usual, this series comes with the selftest coverage for this new ioctl and with a real world use case in the ARM SMMUv3 driver. This is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_veventq-v4 Testing with RMR patches for MSI: https://github.com/nicolinc/iommufd/commits/iommufd_veventq-v4-with-rmr Paring QEMU branch for testing: https://github.com/nicolinc/qemu/commits/wip/for_iommufd_veventq-v4 Changelog v4 * Rename "vIRQ" to "vEVENTQ" * Use flexible array in struct iommufd_vevent * Add the new ioctl command to union ucmd_buffer * Fix the alphabetical order in union ucmd_buffer too * Rename _TYPE_NONE to _TYPE_DEFAULT aligning with vIOMMU naming v3 https://lore.kernel.org/all/cover.1734477608.git.nicolinc@nvidia.com/ * Rebase on Will's for-joerg/arm-smmu/updates for arm_smmu_event series * Add "Reviewed-by" lines from Kevin * Fix typos in comments, kdocs, and jump tags * Add a patch to sort struct iommufd_ioctl_op * Update iommufd's userpsace-api documentation * Update uAPI kdoc to quote SMMUv3 offical spec * Drop the unused workqueue in struct iommufd_virq * Drop might_sleep() in iommufd_viommu_report_irq() helper * Add missing "break" in iommufd_viommu_get_vdev_id() helper * Shrink the scope of the vmaster's read lock in SMMUv3 driver * Pass in two arguments to iommufd_eventq_virq_handler() helper * Move "!ops || !ops->read" validation into iommufd_eventq_init() * Move "fault->ictx = ictx" closer to iommufd_ctx_get(fault->ictx) * Update commit message for arm_smmu_attach_prepare/commit_vmaster() * Keep "iommufd_fault" as-is and rename "iommufd_eventq_virq" to just "iommufd_virq" v2 https://lore.kernel.org/all/cover.1733263737.git.nicolinc@nvidia.com/ * Rebase on v6.13-rc1 * Add IOPF and vIRQ in iommufd.rst (userspace-api) * Add a proper locking in iommufd_event_virq_destroy * Add iommufd_event_virq_abort with a lockdep_assert_held * Rename "EVENT_*" to "EVENTQ_*" to describe the objects better * Reorganize flows in iommufd_eventq_virq_alloc for abort() to work * Adde struct arm_smmu_vmaster to store vSID upon attaching to a nested domain, calling a newly added iommufd_viommu_get_vdev_id helper * Adde an arm_vmaster_report_event helper in arm-smmu-v3-iommufd file to simplify the routine in arm_smmu_handle_evt() of the main driver v1 https://lore.kernel.org/all/cover.1724777091.git.nicolinc@nvidia.com/ Thanks! Nicolin Nicolin Chen (14): iommufd: Keep IOCTL list in an alphabetical order iommufd/fault: Add an iommufd_fault_init() helper iommufd/fault: Move iommufd_fault_iopf_handler() to header iommufd: Abstract an iommufd_eventq from iommufd_fault iommufd: Rename fault.c to eventq.c iommufd: Add IOMMUFD_OBJ_VEVENTQ and IOMMUFD_CMD_VEVENTQ_ALLOC iommufd/viommu: Add iommufd_viommu_get_vdev_id helper iommufd/viommu: Add iommufd_viommu_report_event helper iommufd/selftest: Require vdev_id when attaching to a nested domain iommufd/selftest: Add IOMMU_TEST_OP_TRIGGER_VEVENT for vEVENTQ coverage iommufd/selftest: Add IOMMU_VEVENTQ_ALLOC test coverage Documentation: userspace-api: iommufd: Update FAULT and VEVENTQ iommu/arm-smmu-v3: Introduce struct arm_smmu_vmaster iommu/arm-smmu-v3: Report events that belong to devices attached to vIOMMU drivers/iommu/iommufd/Makefile | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 30 ++ drivers/iommu/iommufd/iommufd_private.h | 116 ++++++- drivers/iommu/iommufd/iommufd_test.h | 10 + include/linux/iommufd.h | 22 ++ include/uapi/linux/iommufd.h | 46 +++ tools/testing/selftests/iommu/iommufd_utils.h | 65 ++++ .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 65 ++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 90 ++++-- drivers/iommu/iommufd/driver.c | 60 ++++ drivers/iommu/iommufd/{fault.c => eventq.c} | 298 ++++++++++++++---- drivers/iommu/iommufd/hw_pagetable.c | 6 +- drivers/iommu/iommufd/main.c | 23 +- drivers/iommu/iommufd/selftest.c | 53 ++++ drivers/iommu/iommufd/viommu.c | 2 + tools/testing/selftests/iommu/iommufd.c | 27 ++ .../selftests/iommu/iommufd_fail_nth.c | 7 + Documentation/userspace-api/iommufd.rst | 16 + 18 files changed, 820 insertions(+), 118 deletions(-) rename drivers/iommu/iommufd/{fault.c => eventq.c} (55%) base-commit: e94dc6ddda8dd3770879a132d577accd2cce25f9 -- 2.43.0

5 months, 4 weeks

2
30
0 0

[PATCH] selftests/nolibc: start qemu with 1 GiB of memory

by Thomas Weißschuh

Recently the loongarch defconfig stopped working with the default 128 MiB of memory. The VM just spins infinitively. Increasing the available memory to 1 GiB, similar to s390, fixes the issue. To avoid having to do this for each architecture on its own, proactively apply to all architectures. Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- tools/testing/selftests/nolibc/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 8de98ea7af8071caa0597aa7b86d91a2d1d50e68..e92e0b88586111072a0e043cb15f3b59cf42c3a6 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -130,9 +130,9 @@ QEMU_ARGS_ppc = -M g3beige -append "console=ttyS0 panic=-1 $(TEST:%=NOLIB QEMU_ARGS_ppc64 = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_ppc64le = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_s390 = -M s390-ccw-virtio -m 1G -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_s390 = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS = $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_BIOS) $(QEMU_ARGS_EXTRA) +QEMU_ARGS = -m 1G $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_BIOS) $(QEMU_ARGS_EXTRA) # OUTPUT is only set when run from the main makefile, otherwise # it defaults to this nolibc directory. --- base-commit: 8cf0b93919e13d1e8d4466eb4080a4c4d9d66d7b change-id: 20241007-nolibc-qemu-mem-5ed605520472 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

5 months, 4 weeks

3
2
0 0

[PATCH v2 0/8] mm/damon: remove DAMON debugfs interface

by SeongJae Park

DAMON debugfs interface was the only user interface of DAMON at the beginning[1]. However, it turned out the interface would be not good enough for long-term flexibility and stability. In Feb 2022[2], we therefore introduced DAMON sysfs interface as an alternative user interface that aims long-term flexibility and stability. With its introduction, DAMON debugfs interface has announced to be deprecated in near future. In Feb 2023[3], we announced the official deprecation of DAMON debugfs interface. In Jan 2024[4], we further made the deprecation difficult to be ignored. In Oct 2024[5], we posted an RFC version of this patch series as the last notice. And as of this writing, no problem or concerns about the removal plan have reported. Apparently users are already moved to the alternative, or made good plans for the change. Remove the DAMON debugfs interface code from the tree. Given the past timeline and the absence of reported problems or concerns, it is safe enough to be done. [1] https://lore.kernel.org/20210716081449.22187-1-sj38.park@gmail.com [2] https://lore.kernel.org/20220228081314.5770-1-sj@kernel.org [3] https://lore.kernel.org/20230209192009.7885-1-sj@kernel.org [4] https://lore.kernel.org/20240130013549.89538-1-sj@kernel.org [5] https://lore.kernel.org/20241015175412.60563-1-sj@kernel.org Revision History ---------------- Changes from v1 (https://lore.kernel.org/20250101213527.74203-1-sj@kernel.org) - Remove debugfs usage section and references from translations (https://lore.kernel.org/20250106183944.103569-1-sj@kernel.org) Changes from RFC (https://lore.kernel.org/20241015175412.60563-1-sj@kernel.org) - Rebased on latest mm-unstable - Update and wordsmith commit messages SeongJae Park (8): Docs/translations/*/admin-guide/mm/damon/usage: remove DAMON debugfs interface documentation Docs/admin-guide/mm/damon/usage: remove DAMON debugfs interface documentation Docs/mm/damon/design: update for removal of DAMON debugfs interface selftests/damon/config: remove configs for DAMON debugfs interface selftests selftests/damon: remove tests for DAMON debugfs interface kunit: configs: remove configs for DAMON debugfs interface tests mm/damon: remove DAMON debugfs interface kunit tests mm/damon: remove DAMON debugfs interface Documentation/admin-guide/mm/damon/usage.rst | 309 ----- Documentation/mm/damon/design.rst | 23 +- .../zh_CN/admin-guide/mm/damon/usage.rst | 248 +--- .../zh_TW/admin-guide/mm/damon/usage.rst | 248 +--- mm/damon/Kconfig | 30 - mm/damon/Makefile | 1 - mm/damon/dbgfs.c | 1148 ----------------- mm/damon/tests/.kunitconfig | 7 - mm/damon/tests/dbgfs-kunit.h | 173 --- tools/testing/kunit/configs/all_tests.config | 3 - tools/testing/selftests/damon/.gitignore | 3 - tools/testing/selftests/damon/Makefile | 11 +- tools/testing/selftests/damon/config | 1 - .../testing/selftests/damon/debugfs_attrs.sh | 17 - .../debugfs_duplicate_context_creation.sh | 27 - .../selftests/damon/debugfs_empty_targets.sh | 21 - .../damon/debugfs_huge_count_read_write.sh | 22 - .../damon/debugfs_rm_non_contexts.sh | 19 - .../selftests/damon/debugfs_schemes.sh | 19 - .../selftests/damon/debugfs_target_ids.sh | 19 - .../damon/debugfs_target_ids_pid_leak.c | 68 - .../damon/debugfs_target_ids_pid_leak.sh | 22 - ...fs_target_ids_read_before_terminate_race.c | 80 -- ...s_target_ids_read_before_terminate_race.sh | 14 - .../selftests/damon/huge_count_read_write.c | 46 - 25 files changed, 13 insertions(+), 2566 deletions(-) delete mode 100644 mm/damon/dbgfs.c delete mode 100644 mm/damon/tests/dbgfs-kunit.h delete mode 100755 tools/testing/selftests/damon/debugfs_attrs.sh delete mode 100755 tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh delete mode 100755 tools/testing/selftests/damon/debugfs_empty_targets.sh delete mode 100755 tools/testing/selftests/damon/debugfs_huge_count_read_write.sh delete mode 100755 tools/testing/selftests/damon/debugfs_rm_non_contexts.sh delete mode 100755 tools/testing/selftests/damon/debugfs_schemes.sh delete mode 100755 tools/testing/selftests/damon/debugfs_target_ids.sh delete mode 100644 tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c delete mode 100755 tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh delete mode 100644 tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c delete mode 100755 tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh delete mode 100644 tools/testing/selftests/damon/huge_count_read_write.c -- 2.39.5

5 months, 4 weeks

1
4
0 0

[RFC PATCH 0/2] ptp: add PTP_SYS_OFFSET_STAT ioctl, support it in virtio_rtc

by Peter Hilber

This RFC patch series proposes a new ioctl PTP_SYS_OFFSET_STAT and adds support for it in the proposed virtio_rtc driver [1]. The new PTP_SYS_OFFSET_STAT ioctl provides a cross-timestamp like PTP_SYS_OFFSET_PRECISE2, plus any the following status information (for now): - for UTC timescale clocks: leap second related status, - clock accuracy. The second commit adds support for the ioctl in the proposed virtio_rtc driver, and hence depends on the patch series "Add virtio_rtc module" [1]. [1] https://lore.kernel.org/lkml/20241219201118.2233-1-quic_philber@quicinc.com… Signed-off-by: Peter Hilber <quic_philber(a)quicinc.com> Peter Hilber (2): ptp: add PTP_SYS_OFFSET_STAT for xtstamping with status virtio_rtc: Support PTP_SYS_OFFSET_STAT ioctl drivers/ptp/ptp_chardev.c | 39 ++++++++ drivers/ptp/ptp_clock.c | 9 ++ drivers/virtio/Kconfig | 4 +- drivers/virtio/virtio_rtc_driver.c | 122 +++++++++++++++++++++++- drivers/virtio/virtio_rtc_internal.h | 3 +- drivers/virtio/virtio_rtc_ptp.c | 25 +++-- include/linux/ptp_clock_kernel.h | 31 ++++++ include/uapi/linux/ptp_clock.h | 130 +++++++++++++++++++++++++- tools/testing/selftests/ptp/Makefile | 2 +- tools/testing/selftests/ptp/testptp.c | 126 ++++++++++++++++++++++++- 10 files changed, 471 insertions(+), 20 deletions(-) base-commit: 8a8009abbfa04e58f1b01b20534cac9e8fe61a46 -- 2.43.0

6 months

2
8
0 0

[PATCH net-next] selftests: drv-net: test drivers sleeping in ndo_get_stats64

by Jakub Kicinski

Most of our tests use rtnetlink to read device stats, so they don't expose the drivers much to paths in which device stats are read under RCU. Add tests which hammer profcs reads to make sure drivers: - don't sleep while reporting stats, - can handle parallel reads, - can handle device going down while reading. Set ifname on the env class in NetDrvEnv, we already do that in NetDrvEpEnv. KTAP version 1 1..7 ok 1 stats.check_pause ok 2 stats.check_fec ok 3 stats.pkt_byte_sum ok 4 stats.qstat_by_ifindex ok 5 stats.check_down ok 6 stats.procfs_hammer # completed up/down cycles: 6 ok 7 stats.procfs_downup_hammer # Totals: pass:7 fail:0 xfail:0 xpass:0 skip:0 error:0 Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: willemb(a)google.com CC: petrm(a)nvidia.com CC: linux-kselftest(a)vger.kernel.org --- .../selftests/drivers/net/lib/py/env.py | 1 + tools/testing/selftests/drivers/net/stats.py | 94 ++++++++++++++++++- tools/testing/selftests/net/lib/py/ksft.py | 5 + 3 files changed, 97 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index fea343f209ea..987e452d3a45 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -48,6 +48,7 @@ from .remote import Remote else: self._ns = NetdevSimDev(**kwargs) self.dev = self._ns.nsims[0].dev + self.ifname = self.dev['ifname'] self.ifindex = self.dev['ifindex'] def __enter__(self): diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 031ac9def6c0..55d647c006ed 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -2,12 +2,15 @@ # SPDX-License-Identifier: GPL-2.0 import errno +import subprocess +import time from lib.py import ksft_run, ksft_exit, ksft_pr -from lib.py import ksft_ge, ksft_eq, ksft_in, ksft_true, ksft_raises, KsftSkipEx, KsftXfailEx +from lib.py import ksft_ge, ksft_eq, ksft_is, ksft_in, ksft_lt, ksft_true, ksft_raises +from lib.py import KsftSkipEx, KsftXfailEx from lib.py import ksft_disruptive from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError from lib.py import NetDrvEnv -from lib.py import ip, defer +from lib.py import cmd, ip, defer ethnl = EthtoolFamily() netfam = NetdevFamily() @@ -174,10 +177,95 @@ rtnl = RtnlFamily() netfam.qstats_get({"ifindex": cfg.ifindex, "scope": "queue"}, dump=True) +def __run_inf_loop(body): + body = body.strip() + if body[-1] != ';': + body += ';' + + return subprocess.Popen(f"while true; do {body} done", shell=True, + stdout=subprocess.PIPE, stderr=subprocess.PIPE) + + +def __stats_increase_sanely(old, new) -> None: + for k in old.keys(): + ksft_ge(new[k], old[k]) + ksft_lt(new[k] - old[k], 1 << 31, comment="likely wrapping error") + + +def procfs_hammer(cfg) -> None: + """ + Reading stats via procfs only holds the RCU lock, which is not an exclusive + lock, make sure drivers can handle parallel reads of stats. + """ + one = __run_inf_loop("cat /proc/net/dev") + defer(one.kill) + two = __run_inf_loop("cat /proc/net/dev") + defer(two.kill) + + time.sleep(1) + # Make sure the processes are running + ksft_is(one.poll(), None) + ksft_is(two.poll(), None) + + rtstat1 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + time.sleep(2) + rtstat2 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + __stats_increase_sanely(rtstat1, rtstat2) + # defers will kill the loops + + +@ksft_disruptive +def procfs_downup_hammer(cfg) -> None: + """ + Reading stats via procfs only holds the RCU lock, drivers often try + to sleep when reading the stats, or don't protect against races. + """ + # Max out the queues, we'll flip between max an 1 + channels = ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + if channels['combined-count'] == 0: + rx_type = 'rx' + else: + rx_type = 'combined' + cur_queue_cnt = channels[f'{rx_type}-count'] + max_queue_cnt = channels[f'{rx_type}-max'] + + cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}") + defer(cmd, f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}") + + # Real test stats + stats = __run_inf_loop("cat /proc/net/dev") + defer(stats.kill) + + ipset = f"ip link set dev {cfg.ifname}" + defer(ip, f"link set dev {cfg.ifname} up") + # The "echo -n 1" lets us count iterations below + updown = f"{ipset} down; sleep 0.05; {ipset} up; sleep 0.05; " + \ + f"ethtool -L {cfg.ifname} {rx_type} 1; " + \ + f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}; " + \ + "echo -n 1" + updown = __run_inf_loop(updown) + kill_updown = defer(updown.kill) + + time.sleep(1) + # Make sure the processes are running + ksft_is(stats.poll(), None) + ksft_is(updown.poll(), None) + + rtstat1 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + # We're looking for crashes, give it extra time + time.sleep(9) + rtstat2 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + __stats_increase_sanely(rtstat1, rtstat2) + + kill_updown.exec() + stdout, _ = updown.communicate(timeout=5) + ksft_pr("completed up/down cycles:", len(stdout.decode('utf-8'))) + + def main() -> None: with NetDrvEnv(__file__, queue_count=100) as cfg: ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex, - check_down], + check_down, procfs_hammer, procfs_downup_hammer], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 477ae76de93d..3efe005436cd 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -71,6 +71,11 @@ KSFT_DISRUPTIVE = True _fail("Check failed", a, "not in", b, comment) +def ksft_is(a, b, comment=""): + if a is not b: + _fail("Check failed", a, "is not", b, comment) + + def ksft_ge(a, b, comment=""): if a < b: _fail("Check failed", a, "<", b, comment) -- 2.47.1

6 months

3
3
0 0

[PATCH v3 00/14] iommufd: Add vIOMMU infrastructure (Part-3: vIRQ)

by Nicolin Chen

As the part-3 of the vIOMMU infrastructure, this series introduces a vIRQ object. The existing FAULT object provides a nice notification pathway to the user space already, so let vIRQ reuse the infrastructure. Mimicing the HWPT structure, add a common EVENTQ structure to support its derivatives: IOMMUFD_OBJ_FAULT (existing) and IOMMUFD_OBJ_VIRQ (new). IOMMUFD_CMD_VIRQ_ALLOC is introduced to allocate vIRQ objects for vIOMMUs. One vIOMMU can have multiple vIRQs in different types but can not support multiple vIRQs with the same types. The forwarding part is fairly simple but might need to replace a physical device ID with a virtual device ID in a driver-level IRQ data structure. So, this comes with some helpers for drivers to use. As usual, this series comes with the selftest coverage for this new vIRQ, and with a real world use case in the ARM SMMUv3 driver. This is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_virq-v3 Testing with RMR patches for MSI: https://github.com/nicolinc/iommufd/commits/iommufd_virq-v3-with-rmr Paring QEMU branch for testing: https://github.com/nicolinc/qemu/commits/wip/for_iommufd_virq-v3 Changelog v3 * Rebase on Will's for-joerg/arm-smmu/updates for arm_smmu_event series * Add "Reviewed-by" lines from Kevin * Fix typos in comments, kdocs, and jump tags * Add a patch to sort struct iommufd_ioctl_op * Update iommufd's userpsace-api documentation * Update uAPI kdoc to quote SMMUv3 offical spec * Drop the unused workqueue in struct iommufd_virq * Drop might_sleep() in iommufd_viommu_report_irq() helper * Add missing "break" in iommufd_viommu_get_vdev_id() helper * Shrink the scope of the vmaster's read lock in SMMUv3 driver * Pass in two arguments to iommufd_eventq_virq_handler() helper * Move "!ops || !ops->read" validation into iommufd_eventq_init() * Move "fault->ictx = ictx" closer to iommufd_ctx_get(fault->ictx) * Update commit message for arm_smmu_attach_prepare/commit_vmaster() * Keep "iommufd_fault" as-is and rename "iommufd_eventq_virq" to just "iommufd_virq" v2 https://lore.kernel.org/all/cover.1733263737.git.nicolinc@nvidia.com/ * Rebase on v6.13-rc1 * Add IOPF and vIRQ in iommufd.rst (userspace-api) * Add a proper locking in iommufd_event_virq_destroy * Add iommufd_event_virq_abort with a lockdep_assert_held * Rename "EVENT_*" to "EVENTQ_*" to describe the objects better * Reorganize flows in iommufd_eventq_virq_alloc for abort() to work * Adde struct arm_smmu_vmaster to store vSID upon attaching to a nested domain, calling a newly added iommufd_viommu_get_vdev_id helper * Adde an arm_vmaster_report_event helper in arm-smmu-v3-iommufd file to simplify the routine in arm_smmu_handle_evt() of the main driver v1 https://lore.kernel.org/all/cover.1724777091.git.nicolinc@nvidia.com/ Thanks! Nicolin Nicolin Chen (14): iommufd: Keep IOCTL list in an alphabetical order iommufd/fault: Add an iommufd_fault_init() helper iommufd/fault: Move iommufd_fault_iopf_handler() to header iommufd: Abstract an iommufd_eventq from iommufd_fault iommufd: Rename fault.c to eventq.c iommufd: Add IOMMUFD_OBJ_VIRQ and IOMMUFD_CMD_VIRQ_ALLOC iommufd/viommu: Add iommufd_viommu_get_vdev_id helper iommufd/viommu: Add iommufd_viommu_report_irq helper iommufd/selftest: Require vdev_id when attaching to a nested domain iommufd/selftest: Add IOMMU_TEST_OP_TRIGGER_VIRQ for vIRQ coverage iommufd/selftest: Add IOMMU_VIRQ_ALLOC test coverage Documentation: userspace-api: iommufd: Update FAULT and VIRQ iommu/arm-smmu-v3: Introduce struct arm_smmu_vmaster iommu/arm-smmu-v3: Report IRQs that belong to devices attached to vIOMMU drivers/iommu/iommufd/Makefile | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 30 ++ drivers/iommu/iommufd/iommufd_private.h | 115 ++++++- drivers/iommu/iommufd/iommufd_test.h | 10 + include/linux/iommufd.h | 20 ++ include/uapi/linux/iommufd.h | 46 +++ tools/testing/selftests/iommu/iommufd_utils.h | 63 ++++ .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 65 ++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 90 ++++-- drivers/iommu/iommufd/driver.c | 57 ++++ drivers/iommu/iommufd/{fault.c => eventq.c} | 298 ++++++++++++++---- drivers/iommu/iommufd/hw_pagetable.c | 6 +- drivers/iommu/iommufd/main.c | 20 +- drivers/iommu/iommufd/selftest.c | 53 ++++ drivers/iommu/iommufd/viommu.c | 2 + tools/testing/selftests/iommu/iommufd.c | 27 ++ .../selftests/iommu/iommufd_fail_nth.c | 6 + Documentation/userspace-api/iommufd.rst | 16 + 18 files changed, 809 insertions(+), 117 deletions(-) rename drivers/iommu/iommufd/{fault.c => eventq.c} (55%) base-commit: 376ce8b35ed15d5deee57bdecd8449f6a4df4c42 -- 2.43.0

6 months

3
27
0 0

[PATCH AUTOSEL 6.12 1/8] selftests/sched_ext: fix build after renames in sched_ext API

by Sasha Levin

From: Ihor Solodrai <ihor.solodrai(a)pm.me> [ Upstream commit ef7009decc30eb2515a64253791d61b72229c119 ] The selftests are falining to build on current tip of bpf-next and sched_ext [1]. This has broken BPF CI [2] after merge from upstream. Use appropriate function names in the selftests according to the recent changes in the sched_ext API [3]. [1] https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit/?id… [2] https://github.com/kernel-patches/bpf/actions/runs/11959327258/job/33340923… [3] https://lore.kernel.org/all/20241109194853.580310-1-tj@kernel.org/ Signed-off-by: Ihor Solodrai <ihor.solodrai(a)pm.me> Acked-by: Andrea Righi <arighi(a)nvidia.com> Acked-by: David Vernet <void(a)manifault.com> Signed-off-by: Tejun Heo <tj(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- .../testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c | 2 +- .../selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c | 4 ++-- tools/testing/selftests/sched_ext/dsp_local_on.bpf.c | 2 +- .../selftests/sched_ext/enq_select_cpu_fails.bpf.c | 2 +- tools/testing/selftests/sched_ext/exit.bpf.c | 4 ++-- tools/testing/selftests/sched_ext/maximal.bpf.c | 4 ++-- tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c | 2 +- .../selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c | 2 +- .../testing/selftests/sched_ext/select_cpu_dispatch.bpf.c | 2 +- .../selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c | 2 +- .../selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c | 4 ++-- tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c | 8 ++++---- 12 files changed, 19 insertions(+), 19 deletions(-) diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c index 37d9bf6fb745..6f4c3f5a1c5d 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c @@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p, * If we dispatch to a bogus DSQ that will fall back to the * builtin global DSQ, we fail gracefully. */ - scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL, + scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL, p->scx.dsq_vtime, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c index dffc97d9cdf1..e4a55027778f 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c @@ -17,8 +17,8 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p, if (cpu >= 0) { /* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */ - scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, - p->scx.dsq_vtime, 0); + scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, + p->scx.dsq_vtime, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index 6a7db1502c29..6325bf76f47e 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -45,7 +45,7 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) target = bpf_get_prandom_u32() % nr_cpus; - scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); bpf_task_release(p); } diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c index 1efb50d61040..a7cf868d5e31 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c @@ -31,7 +31,7 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p, /* Can only call from ops.select_cpu() */ scx_bpf_select_cpu_dfl(p, 0, 0, &found); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c index d75d4faf07f6..4bc36182d3ff 100644 --- a/tools/testing/selftests/sched_ext/exit.bpf.c +++ b/tools/testing/selftests/sched_ext/exit.bpf.c @@ -33,7 +33,7 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags) if (exit_point == EXIT_ENQUEUE) EXIT_CLEANLY(); - scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) @@ -41,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) if (exit_point == EXIT_DISPATCH) EXIT_CLEANLY(); - scx_bpf_consume(DSQ_ID); + scx_bpf_dsq_move_to_local(DSQ_ID); } void BPF_STRUCT_OPS(exit_enable, struct task_struct *p) diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c index 4d4cd8d966db..4c005fa71810 100644 --- a/tools/testing/selftests/sched_ext/maximal.bpf.c +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags) { - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) @@ -28,7 +28,7 @@ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev) { - scx_bpf_consume(SCX_DSQ_GLOBAL); + scx_bpf_dsq_move_to_local(SCX_DSQ_GLOBAL); } void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags) diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c index f171ac470970..13d0f5be788d 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c @@ -30,7 +30,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p, } scx_bpf_put_idle_cpumask(idle_mask); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c index 9efdbb7da928..815f1d5d61ac 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c @@ -67,7 +67,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p, saw_local = true; } - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags); } s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task, diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c index 59bfc4f36167..4bb99699e920 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c @@ -29,7 +29,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p, cpu = prev_cpu; dispatch: - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c index 3bbd5fcdfb18..2a75de11b2cf 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c @@ -18,7 +18,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching to a random DSQ should fail. */ - scx_bpf_dispatch(p, 0xcafef00d, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0); return prev_cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c index 0fda57fe0ecf..99d075695c97 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c @@ -18,8 +18,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching twice in a row is disallowed. */ - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); return prev_cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c index e6c67bcf5e6e..bfcb96cd4954 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c @@ -2,8 +2,8 @@ /* * A scheduler that validates that enqueue flags are properly stored and * applied at dispatch time when a task is directly dispatched from - * ops.select_cpu(). We validate this by using scx_bpf_dispatch_vtime(), and - * making the test a very basic vtime scheduler. + * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(), + * and making the test a very basic vtime scheduler. * * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. * Copyright (c) 2024 David Vernet <dvernet(a)meta.com> @@ -47,13 +47,13 @@ s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p, cpu = prev_cpu; scx_bpf_test_and_clear_cpu_idle(cpu); ddsp: - scx_bpf_dispatch_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); + scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); return cpu; } void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p) { - if (scx_bpf_consume(VTIME_DSQ)) + if (scx_bpf_dsq_move_to_local(VTIME_DSQ)) consumed = true; } -- 2.39.5

6 months

1
2
0 0

[PATCH bpf-next v4 4/4] igc: Add launch time support to XDP ZC

by Song Yoong Siang

Enable Launch Time Control (LTC) support to XDP zero copy via XDP Tx metadata framework. This patch is tested with tools/testing/selftests/bpf/xdp_hw_metadata on Intel Tiger Lake platform. Below are the test steps and result. Test Steps: 1. Add mqprio qdisc: $ sudo tc qdisc add dev enp2s0 handle 8001: parent root mqprio num_tc 4 map 3 2 1 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@0 1@1 1@2 1@3 hw 0 2. Enable launch time hardware offload on hardware queue 1: $ sudo tc qdisc replace dev enp2s0 parent 8001:2 etf offload clockid CLOCK_TAI delta 500000 3. Change RSS to route all incoming IP packets into hardware queue 1: $ sudo ethtool -X enp2s0 start 1 equal 1 4. Start xdp_hw_metadata selftest application: $ sudo ./xdp_hw_metadata enp2s0 -l 1000000000 5. Send an UDP packet to port 9091 of DUT. $ echo -n xdp | nc -u -q0 169.254.1.1 9091 When launch time is set to 1s in the future, the delta between launch time and transmit hardware timestamp is equal to 0.016us, as shown in result below: 0x562ff5dc8880: rx_desc[4]->addr=84110 addr=84110 comp_addr=84110 EoP rx_hash: 0xE343384 with RSS type:0x1 HW RX-time: 1734578015467548904 (sec:1734578015.4675) delta to User RX-time sec:0.0002 (183.103 usec) XDP RX-time: 1734578015467651698 (sec:1734578015.4677) delta to User RX-time sec:0.0001 (80.309 usec) No rx_vlan_tci or rx_vlan_proto, err=-95 0x562ff5dc8880: ping-pong with csum=561c (want c7dd) csum_start=34 csum_offset=6 HW RX-time: 1734578015467548904 (sec:1734578015.4675) delta to HW Launch-time sec:1.0000 (1000000.000 usec) 0x562ff5dc8880: complete tx idx=4 addr=4018 HW Launch-time: 1734578016467548904 (sec:1734578016.4675) delta to HW TX-complete-time sec:0.0000 (0.016 usec) HW TX-complete-time: 1734578016467548920 (sec:1734578016.4675) delta to User TX-complete-time sec:0.0000 (32.546 usec) XDP RX-time: 1734578015467651698 (sec:1734578015.4677) delta to User TX-complete-time sec:0.9999 (999929.768 usec) HW RX-time: 1734578015467548904 (sec:1734578015.4675) delta to HW TX-complete-time sec:1.0000 (1000000.016 usec) 0x562ff5dc8880: complete rx idx=132 addr=84110 Signed-off-by: Song Yoong Siang <yoong.siang.song(a)intel.com> --- drivers/net/ethernet/intel/igc/igc_main.c | 78 ++++++++++++++++------- 1 file changed, 56 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 27872bdea9bd..6857f5f5b4b2 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1566,6 +1566,26 @@ static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *s return false; } +static void igc_insert_empty_packet(struct igc_ring *tx_ring) +{ + struct igc_tx_buffer *empty_info; + struct sk_buff *empty; + void *data; + + empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); + if (!empty) + return; + + data = skb_put(empty, IGC_EMPTY_FRAME_SIZE); + memset(data, 0, IGC_EMPTY_FRAME_SIZE); + + igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); + + if (igc_init_tx_empty_descriptor(tx_ring, empty, empty_info) < 0) + dev_kfree_skb_any(empty); +} + static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, struct igc_ring *tx_ring) { @@ -1603,26 +1623,8 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, skb->tstamp = ktime_set(0, 0); launch_time = igc_tx_launchtime(tx_ring, txtime, &first_flag, &insert_empty); - if (insert_empty) { - struct igc_tx_buffer *empty_info; - struct sk_buff *empty; - void *data; - - empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; - empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); - if (!empty) - goto done; - - data = skb_put(empty, IGC_EMPTY_FRAME_SIZE); - memset(data, 0, IGC_EMPTY_FRAME_SIZE); - - igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); - - if (igc_init_tx_empty_descriptor(tx_ring, - empty, - empty_info) < 0) - dev_kfree_skb_any(empty); - } + if (insert_empty) + igc_insert_empty_packet(tx_ring); done: /* record the location of the first descriptor for this packet */ @@ -2955,9 +2957,33 @@ static u64 igc_xsk_fill_timestamp(void *_priv) return *(u64 *)_priv; } +static void igc_xsk_request_launch_time(u64 launch_time, void *_priv) +{ + struct igc_metadata_request *meta_req = _priv; + struct igc_ring *tx_ring = meta_req->tx_ring; + __le32 launch_time_offset; + bool insert_empty = false; + bool first_flag = false; + + if (!tx_ring->launchtime_enable) + return; + + launch_time_offset = igc_tx_launchtime(tx_ring, + ns_to_ktime(launch_time), + &first_flag, &insert_empty); + if (insert_empty) { + igc_insert_empty_packet(tx_ring); + meta_req->tx_buffer = + &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + } + + igc_tx_ctxtdesc(tx_ring, launch_time_offset, first_flag, 0, 0, 0); +} + const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops = { .tmo_request_timestamp = igc_xsk_request_timestamp, .tmo_fill_timestamp = igc_xsk_fill_timestamp, + .tmo_request_launch_time = igc_xsk_request_launch_time, }; static void igc_xdp_xmit_zc(struct igc_ring *ring) @@ -2980,7 +3006,7 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) ntu = ring->next_to_use; budget = igc_desc_unused(ring); - while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) { + while (xsk_tx_peek_desc(pool, &xdp_desc) && budget >= 4) { struct igc_metadata_request meta_req; struct xsk_tx_metadata *meta = NULL; struct igc_tx_buffer *bi; @@ -3004,6 +3030,12 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops, &meta_req); + /* xsk_tx_metadata_request() may have updated next_to_use */ + ntu = ring->next_to_use; + + /* xsk_tx_metadata_request() may have updated Tx buffer info */ + bi = meta_req.tx_buffer; + tx_desc = IGC_TX_DESC(ring, ntu); tx_desc->read.cmd_type_len = cpu_to_le32(meta_req.cmd_type); tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); @@ -3021,9 +3053,11 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) ntu++; if (ntu == ring->count) ntu = 0; + + ring->next_to_use = ntu; + budget = igc_desc_unused(ring); } - ring->next_to_use = ntu; if (tx_desc) { igc_flush_tx_descriptors(ring); xsk_tx_release(pool); -- 2.34.1

6 months

1
0
0 0

[PATCH bpf-next v4 0/4] xsk: TX metadata Launch Time support

by Song Yoong Siang

This series expands the XDP TX metadata framework to allow user applications to pass per packet 64-bit launch time directly to the kernel driver, requesting launch time hardware offload support. The XDP TX metadata framework will not perform any clock conversion or packet reordering. Please note that the role of Tx metadata is just to pass the launch time, not to enable the offload feature. Users will need to enable the launch time hardware offload feature of the device by using the respective command, such as the tc-etf command. Although some devices use the tc-etf command to enable their launch time hardware offload feature, xsk packets will not go through the etf qdisc. Therefore, in my opinion, the launch time should always be based on the PTP Hardware Clock (PHC). Thus, i did not include a clock ID to indicate the clock source. To simplify the test steps, I modified the xdp_hw_metadata bpf self-test tool in such a way that it will set the launch time based on the offset provided by the user and the value of the Receive Hardware Timestamp, which is against the PHC. This will eliminate the need to discipline System Clock with the PHC and then use clock_gettime() to get the time. Please note that AF_XDP lacks a feedback mechanism to inform the application if the requested launch time is invalid. So, users are expected to familiar with the horizon of the launch time of the device they use and not request a launch time that is beyond the horizon. Otherwise, the driver might interpret the launch time incorrectly and react wrongly. For stmmac and igc, where modulo computation is used, a launch time larger than the horizon will cause the device to transmit the packet earlier that the requested launch time. Although there is no feedback mechanism for the launch time request for now, user still can check whether the requested launch time is working or not, by requesting the Transmit Completion Hardware Timestamp. Changes since v1: - renamed to use Earliest TxTime First (Willem) - renamed to use txtime (Willem) Changes since v2: - renamed to use launch time (Jesper & Willem) - changed the default launch time in xdp_hw_metadata apps from 1s to 0.1s because some NICs do not support such a large future time. Changes since v3: - added XDP launch time support to the igc driver (Jesper & Florian) - added per-driver launch time limitation on xsk-tx-metadata.rst (Jesper) - added explanation on FIFO behavior on xsk-tx-metadata.rst (Jakub) - added step to enable launch time in the commit message (Jesper & Willem) - explicitly documented the type of launch_time and which clock source it is against (Willem) v1: https://patchwork.kernel.org/project/netdevbpf/cover/20231130162028.852006-… v2: https://patchwork.kernel.org/project/netdevbpf/cover/20231201062421.1074768… v3: https://patchwork.kernel.org/project/netdevbpf/cover/20231203165129.1740512… Song Yoong Siang (4): xsk: Add launch time hardware offload support to XDP Tx metadata selftests/bpf: Add Launch Time request to xdp_hw_metadata net: stmmac: Add launch time support to XDP ZC igc: Add launch time support to XDP ZC Documentation/netlink/specs/netdev.yaml | 4 + Documentation/networking/xsk-tx-metadata.rst | 64 +++++++++++++++ drivers/net/ethernet/intel/igc/igc_main.c | 78 +++++++++++++------ drivers/net/ethernet/stmicro/stmmac/stmmac.h | 2 + .../net/ethernet/stmicro/stmmac/stmmac_main.c | 13 ++++ include/net/xdp_sock.h | 10 +++ include/net/xdp_sock_drv.h | 1 + include/uapi/linux/if_xdp.h | 10 +++ include/uapi/linux/netdev.h | 3 + net/core/netdev-genl.c | 2 + net/xdp/xsk.c | 3 + tools/include/uapi/linux/if_xdp.h | 10 +++ tools/include/uapi/linux/netdev.h | 3 + tools/testing/selftests/bpf/xdp_hw_metadata.c | 30 ++++++- 14 files changed, 208 insertions(+), 25 deletions(-) -- 2.34.1

6 months

1
0
0 0

rust/kernel/lib.rs:17:12 : warning: the feature `new_uninit` has been stable since 1.82.0 and no longer requires an attribute to enable

by Naresh Kamboju

The following kselftest rust builds failed on sashal/linus-next.git due to following build warnings / errors. Good: 829d8581c398a96deea1d6bc78578950347dcbec Bad: b2d472701a703596889c3fd067fd8929aeffc4be Build error: -------------- warning: the feature `new_uninit` has been stable since 1.82.0 and no longer requires an attribute to enable --> /rust/kernel/lib.rs:17:12 | 17 | #![feature(new_uninit)] | ^^^^^^^^^^ | = note: `#[warn(stable_features)]` on by default error[E0658]: use of unstable library feature 'box_uninit_write' --> /rust/kernel/alloc/box_ext.rs:41:12 | 41 | Ok(Box::write(b, x)) | ^^^^^^^^^^ | = note: see issue #129397 <https://github.com/rust-lang/rust/issues/129397> for more information = help: add `#![feature(box_uninit_write)]` to the crate attributes to enable = note: this compiler was built on 2024-11-26; consider upgrading it if it is out of date error: aborting due to 1 previous error; 1 warning emitted For more information about this error, try `rustc --explain E0658`. make[3]: *** [/rust/Makefile:425: rust/kernel.o] Error 1 Links: ------- - https://qa-reports.linaro.org/lkft/sashal-linus-next/build/v6.11-rc4-6237-g… - https://qa-reports.linaro.org/lkft/sashal-linus-next/build/v6.11-rc4-6237-g… - https://qa-reports.linaro.org/lkft/sashal-linus-next/build/v6.11-rc4-6237-g… metadata: ---- git repo: https://git.kernel.org/pub/scm/linux/kernel/git/sashal/linus-next.git kernel config: https://storage.tuxsuite.com/public/linaro/lkft/builds/2rByIOiC9ssqI7NjEPY7… build url: https://storage.tuxsuite.com/public/linaro/lkft/builds/2rByIOiC9ssqI7NjEPY7… toolchain: rustgcc compiler: 'name': 'gcc', 'version': '14', 'version_full': 'gcc (Debian 14.2.0-8) 14.2.0' config: rustgcc-lkftconfig-kselftest arch: arm64 -- Linaro LKFT https://lkft.linaro.org

6 months

3
4
0 0

[PATCH net] selftests: tc-testing: reduce rshift value

by Jakub Kicinski

After previous change rshift >= 32 is no longer allowed. Modify the test to use 31, the test doesn't seem to send any traffic so the exact value shouldn't matter. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: jhs(a)mojatatu.com CC: xiyou.wangcong(a)gmail.com CC: jiri(a)resnulli.us CC: shuah(a)kernel.org CC: karansanghvi98(a)gmail.com CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/tc-testing/tc-tests/filters/flow.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json index 996448afe31b..91d120548bf5 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json @@ -78,10 +78,10 @@ "setup": [ "$TC qdisc add dev $DEV1 ingress" ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0xff", + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0x1f", "expExitCode": "0", "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 1 flow", - "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 255 baseclass", + "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 31 baseclass", "matchCount": "1", "teardown": [ "$TC qdisc del dev $DEV1 ingress" -- 2.47.1

6 months

3
2
0 0

[PATCH v3 0/2] fix reading ESP during coredump

by Nam Cao

Hi, In /proc/PID/stat, there is the kstkesp field which is the stack pointer of a thread. While the thread is active, this field reads zero. But during a coredump, it should have a valid value. However, at the moment, kstkesp is zero even during coredump. The first commit fixes this problem, and the second commit adds a selftest to detect if this problem appears again in the future. v2..v3 https://lore.kernel.org/lkml/cover.1735550994.git.namcao@linutronix.de/ - Move stackdump file to local directory [Kees] - Always cleanup the stackdump file after the test [Kees] - Remove unused empty function v1..v2 https://lore.kernel.org/lkml/cover.1730883229.git.namcao@linutronix.de/ - Change the fix patch to use PF_POSTCOREDUMP [Oleg] Nam Cao (2): fs/proc: do_task_stat: Fix ESP not readable during coredump selftests: coredump: Add stackdump test fs/proc/array.c | 2 +- tools/testing/selftests/coredump/Makefile | 7 + tools/testing/selftests/coredump/README.rst | 50 ++++++ tools/testing/selftests/coredump/stackdump | 14 ++ .../selftests/coredump/stackdump_test.c | 151 ++++++++++++++++++ 5 files changed, 223 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/coredump/Makefile create mode 100644 tools/testing/selftests/coredump/README.rst create mode 100755 tools/testing/selftests/coredump/stackdump create mode 100644 tools/testing/selftests/coredump/stackdump_test.c -- 2.39.5

6 months

2
3
0 0

[PATCH AUTOSEL 6.6 3/3] selftests/alsa: Fix circular dependency involving global-timer

by Sasha Levin

From: Li Zhijian <lizhijian(a)fujitsu.com> [ Upstream commit 55853cb829dc707427c3519f6b8686682a204368 ] The pattern rule `$(OUTPUT)/%: %.c` inadvertently included a circular dependency on the global-timer target due to its inclusion in $(TEST_GEN_PROGS_EXTENDED). This resulted in a circular dependency warning during the build process. To resolve this, the dependency on $(TEST_GEN_PROGS_EXTENDED) has been replaced with an explicit dependency on $(OUTPUT)/libatest.so. This change ensures that libatest.so is built before any other targets that require it, without creating a circular dependency. This fix addresses the following warning: make[4]: Entering directory 'tools/testing/selftests/alsa' make[4]: Circular default_modconfig/kselftest/alsa/global-timer <- default_modconfig/kselftest/alsa/global-timer dependency dropped. make[4]: Nothing to be done for 'all'. make[4]: Leaving directory 'tools/testing/selftests/alsa' Cc: Mark Brown <broonie(a)kernel.org> Cc: Jaroslav Kysela <perex(a)perex.cz> Cc: Takashi Iwai <tiwai(a)suse.com> Cc: Shuah Khan <shuah(a)kernel.org> Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> Link: https://patch.msgid.link/20241218025931.914164-1-lizhijian@fujitsu.com Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/alsa/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index 5af9ba8a4645..140c7f821727 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -23,5 +23,5 @@ include ../lib.mk $(OUTPUT)/libatest.so: conf.c alsa-local.h $(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@ -$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) alsa-local.h +$(OUTPUT)/%: %.c $(OUTPUT)/libatest.so alsa-local.h $(CC) $(CFLAGS) $< $(LDLIBS) -latest -o $@ -- 2.39.5

6 months

1
0
0 0

[PATCH AUTOSEL 6.12 4/4] selftests/alsa: Fix circular dependency involving global-timer

by Sasha Levin

From: Li Zhijian <lizhijian(a)fujitsu.com> [ Upstream commit 55853cb829dc707427c3519f6b8686682a204368 ] The pattern rule `$(OUTPUT)/%: %.c` inadvertently included a circular dependency on the global-timer target due to its inclusion in $(TEST_GEN_PROGS_EXTENDED). This resulted in a circular dependency warning during the build process. To resolve this, the dependency on $(TEST_GEN_PROGS_EXTENDED) has been replaced with an explicit dependency on $(OUTPUT)/libatest.so. This change ensures that libatest.so is built before any other targets that require it, without creating a circular dependency. This fix addresses the following warning: make[4]: Entering directory 'tools/testing/selftests/alsa' make[4]: Circular default_modconfig/kselftest/alsa/global-timer <- default_modconfig/kselftest/alsa/global-timer dependency dropped. make[4]: Nothing to be done for 'all'. make[4]: Leaving directory 'tools/testing/selftests/alsa' Cc: Mark Brown <broonie(a)kernel.org> Cc: Jaroslav Kysela <perex(a)perex.cz> Cc: Takashi Iwai <tiwai(a)suse.com> Cc: Shuah Khan <shuah(a)kernel.org> Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> Link: https://patch.msgid.link/20241218025931.914164-1-lizhijian@fujitsu.com Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/alsa/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index 944279160fed..8dab90ad22bb 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -27,5 +27,5 @@ include ../lib.mk $(OUTPUT)/libatest.so: conf.c alsa-local.h $(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@ -$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) alsa-local.h +$(OUTPUT)/%: %.c $(OUTPUT)/libatest.so alsa-local.h $(CC) $(CFLAGS) $< $(LDLIBS) -latest -o $@ -- 2.39.5

6 months

1
0
0 0

[PATCH v7 0/2] selftests: tmpfs: Add kselftest support

by Shivam Chaudhary

This version 7 patch series replace direct error handling methods with ksft macros, which provide better reporting.Currently, when the tmpfs test runs, it does not display any output if it passes,and if it fails (particularly when not run as root),it simply exits without any warning or message. This series of patch adds: 1. Add 'ksft_print_header()' and 'ksft_set_plan()' to structure test outputs more effectively. 2. skip if not run as root. 3. Replace direct error handling with 'ksft_test_result_*', macros for better reporting. v6->v7: - Improve the handling of failure macros. v6 v1: https://lore.kernel.org/all/20241219152929.4005003-2-cvam0000@gmail.com/ v6 v2: https://lore.kernel.org/all/20241219152929.4005003-3-cvam0000@gmail.com/ v5->v6: - Skip if not run as root. v5 v1: https://lore.kernel.org/all/20241112143056.565122-2-cvam0000@gmail.com/ v5 v2: https://lore.kernel.org/all/20241112143056.565122-3-cvam0000@gmail.com/ v4->v5: - Remove unnecessary pass messages. - Remove unnecessary use of KSFT_SKIP. - Add appropriate use of ksft_exit_fail_msg. v4 v1: https://lore.kernel.org/all/8db9feab-0600-440b-b4b2-042695a100b5@linuxfound… v4 v2: https://lore.kernel.org/all/63d5e3bb-9817-4a34-98fe-823a9cac7c16@linuxfound… v3->v4: - Start a patchset - Split patch into smaller patches to make it easy to review. Patch1 Replace 'ksft_test_result_skip' with 'KSFT_SKIP' during root run check. Patch2 Replace 'ksft_test_result_fail' with 'KSFT_SKIP' where fail does not make sense, or failure could be due to not unsupported APIs with appropriate warnings. v3: https://lore.kernel.org/all/20241028185756.111832-1-cvam0000@gmail.com/ v2->v3: - Remove extra ksft_set_plan() - Remove function for unshare() - Fix the comment style v2: https://lore.kernel.org/all/20241026191621.2860376-1-cvam0000@gmail.com/ v1->v2: - Make the commit message more clear. v1: https://lore.kernel.org/all/20241024200228.1075840-1-cvam0000@gmail.com/T/#u thanks Shivam Shivam Chaudhary (2): selftests: tmpfs: Add Test-skip if not run as root selftests: tmpfs: Add kselftest support to tmpfs .../selftests/tmpfs/bug-link-o-tmpfile.c | 40 ++++++++++++------- 1 file changed, 26 insertions(+), 14 deletions(-) -- 2.34.1

6 months

2
6
0 0

[PATCH v5 0/3] rust: kunit: Support KUnit tests with a user-space like syntax

by David Gow

Hi all, v5 here is a small set of fixes and a rebase of the previous versions. If there are no major issues, I'd like to land this soon so it can be used and tested ready for 6.14. This series was originally written by José Expósito, and has been modified and updated by Matt Gilbride and myself. The original version can be found here: https://github.com/Rust-for-Linux/linux/pull/950 Add support for writing KUnit tests in Rust. While Rust doctests are already converted to KUnit tests and run, they're really better suited for examples, rather than as first-class unit tests. This series implements a series of direct Rust bindings for KUnit tests, as well as a new macro which allows KUnit tests to be written using a close variant of normal Rust unit test syntax. The only change required is replacing '#[cfg(test)]' with '#[kunit_tests(kunit_test_suite_name)]' An example test would look like: #[kunit_tests(rust_kernel_hid_driver)] mod tests { use super::*; use crate::{c_str, driver, hid, prelude::*}; use core::ptr; struct SimpleTestDriver; impl Driver for SimpleTestDriver { type Data = (); } #[test] fn rust_test_hid_driver_adapter() { let mut hid = bindings::hid_driver::default(); let name = c_str!("SimpleTestDriver"); static MODULE: ThisModule = unsafe { ThisModule::from_ptr(ptr::null_mut()) }; let res = unsafe { <hid::Adapter<SimpleTestDriver> as driver::DriverOps>::register(&mut hid, name, &MODULE) }; assert_eq!(res, Err(ENODEV)); // The mock returns -19 } } Please give this a go, and make sure I haven't broken it! There's almost certainly a lot of improvements which can be made -- and there's a fair case to be made for replacing some of this with generated C code which can use the C macros -- but this is hopefully an adequate implementation for now, and the interface can (with luck) remain the same even if the implementation changes. A few small notable missing features: - Attributes (like the speed of a test) are hardcoded to the default value. - Similarly, the module name attribute is hardcoded to NULL. In C, we use the KBUILD_MODNAME macro, but I couldn't find a way to use this from Rust which wasn't more ugly than just disabling it. - Assertions are not automatically rewritten to use KUnit assertions. --- Changes since v4: https://lore.kernel.org/linux-kselftest/20241101064505.3820737-1-davidgow@g… - Rebased against 6.13-rc1 - Allowed an unused_unsafe warning after the behaviour of addr_of_mut!() changed in Rust 1.82. (Thanks Boqun, Miguel) - "Expect" that the sample assert_eq!(1+1, 2) produces a clippy warning due to a redundant assertion. (Thanks Boqun, Miguel) - Fix some missing safety comments, and remove some unneeded 'unsafe' blocks. (Thanks Boqun) - Fix a couple of minor rustfmt issues which were triggering checkpatch warnings. Changes since v3: https://lore.kernel.org/linux-kselftest/20241030045719.3085147-2-davidgow@g… - The kunit_unsafe_test_suite!() macro now panic!s if the suite name is too long, triggering a compile error. (Thanks, Alice!) - The #[kunit_tests()] macro now preserves span information, so errors can be better reported. (Thanks, Boqun!) - The example tests have been updated to no longer use assert_eq!() with a constant bool argument (which triggered a clippy warning now we have the span info). Changes since v2: https://lore.kernel.org/linux-kselftest/20241029092422.2884505-1-davidgow@g… - Include missing rust/macros/kunit.rs file from v2. (Thanks Boqun!) - The kunit_unsafe_test_suite!() macro will truncate the name of the suite if it is too long. (Thanks Alice!) - The proc macro now emits an error if the suite name is too long. - We no longer needlessly use UnsafeCell<> in kunit_unsafe_test_suite!(). (Thanks Alice!) Changes since v1: https://lore.kernel.org/lkml/20230720-rustbind-v1-0-c80db349e3b5@google.com… - Rebase on top of the latest rust-next (commit 718c4069896c) - Make kunit_case a const fn, rather than a macro (Thanks Boqun) - As a result, the null terminator is now created with kernel::kunit::kunit_case_null() - Use the C kunit_get_current_test() function to implement in_kunit_test(), rather than re-implementing it (less efficiently) ourselves. Changes since the GitHub PR: - Rebased on top of kselftest/kunit - Add const_mut_refs feature This may conflict with https://lore.kernel.org/lkml/20230503090708.2524310-6-nmi@metaspace.dk/ - Add rust/macros/kunit.rs to the KUnit MAINTAINERS entry --- José Expósito (3): rust: kunit: add KUnit case and suite macros rust: macros: add macro to easily run KUnit tests rust: kunit: allow to know if we are in a test MAINTAINERS | 1 + rust/kernel/kunit.rs | 207 +++++++++++++++++++++++++++++++++++++++++++ rust/kernel/lib.rs | 1 + rust/macros/kunit.rs | 168 +++++++++++++++++++++++++++++++++++ rust/macros/lib.rs | 29 ++++++ 5 files changed, 406 insertions(+) create mode 100644 rust/macros/kunit.rs -- 2.47.1.613.gc27f4b7a9f-goog

6 months

2
7
0 0

Question about test_xsk.sh

by Alexis Lothoré

Hello all, I was looking at other test candidates for conversion to bpf test_progs framework (to increase automatic testing scope) and found test_xsk.sh, which does not seem to have coverage yet in test_progs. This test validates the AF_XDP socket behavior with different XDP modes (SKB, DRV, zero copy) and socket configuration (normal, busy polling). The testing program looks pretty big, considering all files involved (test_xsk.sh, xskxceiver.c, xsk.c, the different XDP programs) and the matrix of tests it runs. So before really diving into it, I would like to ask: - is it indeed a good/relevant target for integration in test_progs (all tests look like functional tests, so I guess it is) ? - if so, is there anyone already working on this ? - multiple commits on xskxceiver.c hint that the program is also used for testing on real hardware, could someone confirm that it is still the case (similar need has been seen with test_xdp_features.sh for example) ? If so, it means that the current form must be preserved, and it would be an additional integration into test_progs rather a conversion (then most of the code should be shared between the non-test_progs and the test_progs version) Thanks, Alexis -- Alexis Lothoré, Bootlin Embedded Linux and Kernel engineering https://bootlin.com

6 months

3
3
0 0

[PATCH net-next 0/4] netconsole: selftest for userdata overflow

by Breno Leitao

Implement comprehensive testing for netconsole userdata entry handling, demonstrating correct behavior when creating maximum entries and preventing unauthorized overflow. Refactor existing test infrastructure to support modular, reusable helper functions that validate strict entry limit enforcement. Also, add a warning if update_userdata() sees more than MAX_USERDATA_ITEMS entries. This shouldn't happen and it is a bug that shouldn't be silently ignored. Signed-off-by: Breno Leitao <leitao(a)debian.org> --- Breno Leitao (4): netconsole: Warn if MAX_USERDATA_ITEMS limit is exceeded netconsole: selftest: Split the helpers from the selftest netconsole: selftest: Delete all userdata keys netconsole: selftest: verify userdata entry limit MAINTAINERS | 3 +- drivers/net/netconsole.c | 2 +- .../selftests/drivers/net/lib/sh/lib_netcons.sh | 225 +++++++++++++++++++++ .../testing/selftests/drivers/net/netcons_basic.sh | 218 +------------------- .../selftests/drivers/net/netcons_overflow.sh | 67 ++++++ 5 files changed, 296 insertions(+), 219 deletions(-) --- base-commit: bb18265c3aba92b91a1355609769f3e967b65dee change-id: 20241204-netcons_overflow_test-eaf735d1f743 Best regards, -- Breno Leitao <leitao(a)debian.org>

6 months

2
9
0 0

[PATCH] selftests/ring-buffer: Add test for out-of-bound pgoff mapping

by Vincent Donnefort

Extend the ring-buffer mapping test coverage by checking an out-of-bound pgoff which has proven to be problematic in the past. Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Vincent Donnefort <vdonnefort(a)google.com> diff --git a/tools/testing/selftests/ring-buffer/map_test.c b/tools/testing/selftests/ring-buffer/map_test.c index d10a847130fb..a58f520f2f41 100644 --- a/tools/testing/selftests/ring-buffer/map_test.c +++ b/tools/testing/selftests/ring-buffer/map_test.c @@ -233,12 +233,18 @@ TEST_F(map, data_mmap) ASSERT_NE(data, MAP_FAILED); munmap(data, data_len); - /* Overflow the available subbufs by 1 */ + /* Offset within ring-buffer bounds, mapping size overflow */ meta_len += desc->meta->subbuf_size * 2; data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, desc->cpu_fd, meta_len); ASSERT_EQ(data, MAP_FAILED); + /* Offset outside ring-buffer bounds */ + data_len = desc->meta->subbuf_size * desc->meta->nr_subbufs; + data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, + desc->cpu_fd, data_len + (desc->meta->subbuf_size * 2)); + ASSERT_EQ(data, MAP_FAILED); + /* Verify meta-page padding */ if (desc->meta->meta_page_size > getpagesize()) { data_len = desc->meta->meta_page_size; base-commit: 61baee2dc5341c936e7fa7b1ca33c5607868de69 -- 2.47.1.613.gc27f4b7a9f-goog

6 months

3
2
0 0

[PATCH 0/1] selftests/memfd: skip hugetlbfs test if it's not supported

by Po-Hsu Lin

Handle the case that hugetlbfs is not supported. To make it easier for debugging. On a system that does not support hugetlbfs. There will be no such HugePages_Free entry in /proc/meminfo. And consequently freepgs will be empty. The huge pages availability check will fail and the test will be started anyway: ./run_hugetlbfs_test.sh: line 47: [: -lt: unary operator expected ./run_hugetlbfs_test.sh: line 60: 12577 Aborted (core dumped) ./memfd_test hugetlbfs Aborted (core dumped) Po-Hsu Lin (1): selftests/memfd: skip hugetlbfs test if it's not supported tools/testing/selftests/memfd/run_hugetlbfs_test.sh | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) -- 2.34.1

6 months

1
1
0 0

[PATCH 0/7] mm/damon: remove DAMON debugfs interface

by SeongJae Park

DAMON debugfs interface was the only user interface of DAMON at the beginning[1]. However, it turned out the interface would be not good enough for long-term flexibility and stability. In Feb 2022[2], we therefore introduced DAMON sysfs interface as an alternative user interface that aims long-term flexibility and stability. With its introduction, DAMON debugfs interface has announced to be deprecated in near future. In Feb 2023[3], we announced the official deprecation of DAMON debugfs interface. In Jan 2024[4], we further made the deprecation difficult to be ignored. In Oct 2024[5], we posted an RFC version of this patch series as the last notice. And as of this writing, no problem or concerns about the removal plan have reported. Apparently users are already moved to the alternative, or made good plans for the change. Remove the DAMON debugfs interface code from the tree. Given the past timeline and the absence of reported problems or concerns, it is safe enough to be done. [1] https://lore.kernel.org/20210716081449.22187-1-sj38.park@gmail.com [2] https://lore.kernel.org/20220228081314.5770-1-sj@kernel.org [3] https://lore.kernel.org/20230209192009.7885-1-sj@kernel.org [4] https://lore.kernel.org/20240130013549.89538-1-sj@kernel.org [5] https://lore.kernel.org/20241015175412.60563-1-sj@kernel.org Changes from RFC (https://lore.kernel.org/20241015175412.60563-1-sj@kernel.org) - Rebased on latest mm-unstable - Update and wordsmith commit messages SeongJae Park (7): Docs/admin-guide/mm/damon/usage: remove DAMON debugfs interface documentation Docs/mm/damon/design: update for removal of DAMON debugfs interface selftests/damon/config: remove configs for DAMON debugfs interface selftests selftests/damon: remove tests for DAMON debugfs interface kunit: configs: remove configs for DAMON debugfs interface tests mm/damon: remove DAMON debugfs interface kunit tests mm/damon: remove DAMON debugfs interface Documentation/admin-guide/mm/damon/usage.rst | 309 ----- Documentation/mm/damon/design.rst | 23 +- mm/damon/Kconfig | 30 - mm/damon/Makefile | 1 - mm/damon/dbgfs.c | 1148 ----------------- mm/damon/tests/.kunitconfig | 7 - mm/damon/tests/dbgfs-kunit.h | 173 --- tools/testing/kunit/configs/all_tests.config | 3 - tools/testing/selftests/damon/.gitignore | 3 - tools/testing/selftests/damon/Makefile | 11 +- tools/testing/selftests/damon/config | 1 - .../testing/selftests/damon/debugfs_attrs.sh | 17 - .../debugfs_duplicate_context_creation.sh | 27 - .../selftests/damon/debugfs_empty_targets.sh | 21 - .../damon/debugfs_huge_count_read_write.sh | 22 - .../damon/debugfs_rm_non_contexts.sh | 19 - .../selftests/damon/debugfs_schemes.sh | 19 - .../selftests/damon/debugfs_target_ids.sh | 19 - .../damon/debugfs_target_ids_pid_leak.c | 68 - .../damon/debugfs_target_ids_pid_leak.sh | 22 - ...fs_target_ids_read_before_terminate_race.c | 80 -- ...s_target_ids_read_before_terminate_race.sh | 14 - .../selftests/damon/huge_count_read_write.c | 46 - 23 files changed, 11 insertions(+), 2072 deletions(-) delete mode 100644 mm/damon/dbgfs.c delete mode 100644 mm/damon/tests/dbgfs-kunit.h delete mode 100755 tools/testing/selftests/damon/debugfs_attrs.sh delete mode 100755 tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh delete mode 100755 tools/testing/selftests/damon/debugfs_empty_targets.sh delete mode 100755 tools/testing/selftests/damon/debugfs_huge_count_read_write.sh delete mode 100755 tools/testing/selftests/damon/debugfs_rm_non_contexts.sh delete mode 100755 tools/testing/selftests/damon/debugfs_schemes.sh delete mode 100755 tools/testing/selftests/damon/debugfs_target_ids.sh delete mode 100644 tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c delete mode 100755 tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh delete mode 100644 tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c delete mode 100755 tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh delete mode 100644 tools/testing/selftests/damon/huge_count_read_write.c -- 2.39.5

6 months

1
4
0 0

[PATCH v2 1/3] selftest/powerpc/ptrace/core-pkey: Remove duplicate macros

by Madhavan Srinivasan

./powerpc/ptrace/Makefile includes flags.mk. In flags.mk, -I$(selfdir)/powerpc/include is always included as part of CFLAGS. So it will pick up the "pkeys.h" defined in powerpc/include. core-pkey.c test has couple of macros defined which are part of "pkeys.h" header file. Remove those duplicates and include "pkeys.h" Reviewed-by: Ritesh Harjani (IBM) <ritesh.list(a)gmail.com> Signed-off-by: Madhavan Srinivasan <maddy(a)linux.ibm.com> --- Changelog v1: - Added Reviewed-by tag - made changes to commit message .../selftests/powerpc/ptrace/core-pkey.c | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c index f6da4cb30cd6..31c9bf6d95db 100644 --- a/tools/testing/selftests/powerpc/ptrace/core-pkey.c +++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c @@ -16,14 +16,7 @@ #include <unistd.h> #include "ptrace.h" #include "child.h" - -#ifndef __NR_pkey_alloc -#define __NR_pkey_alloc 384 -#endif - -#ifndef __NR_pkey_free -#define __NR_pkey_free 385 -#endif +#include "pkeys.h" #ifndef NT_PPC_PKEY #define NT_PPC_PKEY 0x110 @@ -61,16 +54,6 @@ struct shared_info { time_t core_time; }; -static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights) -{ - return syscall(__NR_pkey_alloc, flags, init_access_rights); -} - -static int sys_pkey_free(int pkey) -{ - return syscall(__NR_pkey_free, pkey); -} - static int increase_core_file_limit(void) { struct rlimit rlim; -- 2.47.0

6 months

2
4
0 0

[PATCH bpf-next v4 0/2] bpf, verifier: Improve precision of BPF_MUL

by Matan Shachnai

Hi All, This patch-set aims to improve precision of BPF_MUL and add testcases to illustrate precision gains using signed and unsigned bounds. Thanks for taking the time to review and for all the feedback! Best, Matan Changes from v1: - Fixed typo made in patch. Changes from v2: - Added signed multiplication to BPF_MUL. - Added test cases to exercise BPF_MUL. - Reordered patches in the series. Changes from v3: - Coding style fixes. Matan Shachnai (2): bpf, verifier: Improve precision of BPF_MUL selftests/bpf: Add testcases for BPF_MUL kernel/bpf/verifier.c | 80 +++++------ .../selftests/bpf/progs/verifier_bounds.c | 134 ++++++++++++++++++ 2 files changed, 170 insertions(+), 44 deletions(-) -- 2.25.1

6 months

2
3
0 0

[PATCH v2 0/2] fix reading ESP during coredump

by Nam Cao

Hi, In /proc/PID/stat, there is the kstkesp field which is the stack pointer of a thread. While the thread is active, this field reads zero. But during a coredump, it should have a valid value. However, at the moment, kstkesp is zero even during coredump. The first commit fixes this problem, and the second commit adds a selftest to detect if this problem appears again in the future. v2: - Change the fix patch to use PF_POSTCOREDUMP [Oleg] Link to v1: https://lore.kernel.org/lkml/cover.1730883229.git.namcao@linutronix.de/ Nam Cao (2): fs/proc: do_task_stat: Fix ESP not readable during coredump selftests: coredump: Add stackdump test fs/proc/array.c | 2 +- tools/testing/selftests/coredump/Makefile | 7 + tools/testing/selftests/coredump/README.rst | 50 ++++++ tools/testing/selftests/coredump/stackdump | 14 ++ .../selftests/coredump/stackdump_test.c | 154 ++++++++++++++++++ 5 files changed, 226 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/coredump/Makefile create mode 100644 tools/testing/selftests/coredump/README.rst create mode 100755 tools/testing/selftests/coredump/stackdump create mode 100644 tools/testing/selftests/coredump/stackdump_test.c -- 2.39.5

6 months

2
4
0 0

[PATCH v4 0/4] Add support for the Idle HLT intercept feature

by Manali Shukla

The upcoming new Idle HLT Intercept feature allows for the HLT instruction execution by a vCPU to be intercepted by the hypervisor only if there are no pending V_INTR and V_NMI events for the vCPU. When the vCPU is expected to service the pending V_INTR and V_NMI events, the Idle HLT intercept won’t trigger. The feature allows the hypervisor to determine if the vCPU is actually idle and reduces wasteful VMEXITs. The idle HLT intercept feature is used for enlightened guests who wish to securely handle the events. When an enlightened guest does a HLT while an interrupt is pending, hypervisor will not have a way to figure out whether the guest needs to be re-entered or not. The Idle HLT intercept feature allows the HLT execution only if there are no pending V_INTR and V_NMI events. Presence of the Idle HLT Intercept feature is indicated via CPUID function Fn8000_000A_EDX[30]. Document for the Idle HLT intercept feature is available at [1]. This series is based on kvm-next/next (64dbb3a771a1) + [2]. Experiments done: ---------------- kvm_amd.avic is set to '0' for this experiment. The below numbers represent the average of 10 runs. Normal guest (L1) The below netperf command was run on the guest with smp = 1 (pinned). netperf -H <host ip> -t TCP_RR -l 60 ---------------------------------------------------------------- |with Idle HLT(transactions/Sec)|w/o Idle HLT(transactions/Sec)| ---------------------------------------------------------------- | 25645.7136 | 25773.2796 | ---------------------------------------------------------------- Number of transactions/sec with and without idle HLT intercept feature are almost same. Nested guest (L2) The below netperf command was run on L2 guest with smp = 1 (pinned). netperf -H <host ip> -t TCP_RR -l 60 ---------------------------------------------------------------- |with Idle HLT(transactions/Sec)|w/o Idle HLT(transactions/Sec)| ---------------------------------------------------------------- | 5655.4468 | 5755.2189 | ---------------------------------------------------------------- Number of transactions/sec with and without idle HLT intercept feature are almost same. Testing Done: - Tested the functionality for the Idle HLT intercept feature using selftest svm_idle_hlt_test. - Tested SEV and SEV-ES guest for the Idle HLT intercept functionality. - Tested the Idle HLT intercept functionality on nested guest. v3 -> v4 - Drop the patches to add vcpu_get_stat() into a new series [2]. - Added nested Idle HLT intercept support. v2 -> v3 - Incorporated Andrew's suggestion to structure vcpu_stat_types in a way that each architecture can share the generic types and also provide its own. v1 -> v2 - Done changes in svm_idle_hlt_test based on the review comments from Sean. - Added an enum based approach to get binary stats in vcpu_get_stat() which doesn't use string to get stat data based on the comments from Sean. - Added self_halt() and cli() helpers based on the comments from Sean. [1]: AMD64 Architecture Programmer's Manual Pub. 24593, April 2024, Vol 2, 15.9 Instruction Intercepts (Table 15-7: IDLE_HLT). https://bugzilla.kernel.org/attachment.cgi?id=306250 [2]: https://lore.kernel.org/kvm/20241021062226.108657-1-manali.shukla@amd.com/T… Manali Shukla (4): x86/cpufeatures: Add CPUID feature bit for Idle HLT intercept KVM: SVM: Add Idle HLT intercept support KVM: nSVM: implement the nested idle halt intercept KVM: selftests: KVM: SVM: Add Idle HLT intercept test arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/svm.h | 1 + arch/x86/include/uapi/asm/svm.h | 2 + arch/x86/kvm/governed_features.h | 1 + arch/x86/kvm/svm/nested.c | 7 ++ arch/x86/kvm/svm/svm.c | 15 +++- tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/include/x86_64/processor.h | 1 + .../selftests/kvm/x86_64/svm_idle_hlt_test.c | 89 +++++++++++++++++++ 9 files changed, 115 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/kvm/x86_64/svm_idle_hlt_test.c base-commit: c8d430db8eec7d4fd13a6bea27b7086a54eda6da prerequisite-patch-id: ca912571db5c004f77b70843b8dd35517ff1267f prerequisite-patch-id: 164ea3b4346f9e04bc69819278d20f5e1b5df5ed prerequisite-patch-id: 90d870f426ebc2cec43c0dd89b701ee998385455 prerequisite-patch-id: 45812b799c517a4521782a1fdbcda881237e1eda -- 2.34.1

6 months, 1 week

3
15
0 0

[PATCH v7 0/3] tracing: Support poll on event hist file

by Masami Hiramatsu (Google)

Hi, Here is the 7th version of the series to support polling on event 'hist' file. The previous version is here; https://lore.kernel.org/all/172907575534.470540.12941248697563459082.stgit@… This version updates descriptions, use guard() for mutex and fixes selftest problem. Background ---------- There has been interest in allowing user programs to monitor kernel events in real time. Ftrace provides `trace_pipe` interface to wait on events in the ring buffer, but it is needed to wait until filling up a page with events in the ring buffer. We can also peek the `trace` file periodically, but that is inefficient way to monitor a randomely happening event. Overview -------- This patch set allows user to `poll`(or `select`, `epoll`) on event histogram interface. As you know each event has its own `hist` file which shows histograms generated by trigger action. So user can set a new hist trigger on any event you want to monitor, and poll on the `hist` file until it is updated. There are 2 poll events are supported, POLLIN and POLLPRI. POLLIN means that there are any readable update on `hist` file and this event will be flashed only when you call read(). So, this is useful if you want to read the histogram periodically. The other POLLPRI event is for monitoring trace event. Like the POLLIN, this will be returned when the histogram is updated, but you don't need to read() the file and use poll() again. Note that this waits for histogram update (not event arrival), thus you must set a histogram on the event at first. Usage ----- Here is an example usage: ---- TRACEFS=/sys/kernel/tracing EVENT=$TRACEFS/events/sched/sched_process_free # setup histogram trigger and enable event echo "hist:key=comm" >> $EVENT/trigger echo 1 > $EVENT/enable # Wait for update poll pri $EVENT/hist # Event arrived. echo "process free event is comming" tail $TRACEFS/trace ---- The 'poll' command is in the selftest patch. You can take this series also from here; https://git.kernel.org/pub/scm/linux/kernel/git/mhiramat/linux.git/log/?h=t… Thank you, --- Masami Hiramatsu (Google) (3): tracing/hist: Add poll(POLLIN) support on hist file tracing/hist: Support POLLPRI event for poll on histogram selftests/tracing: Add hist poll() support test include/linux/trace_events.h | 14 +++ kernel/trace/trace_events.c | 14 +++ kernel/trace/trace_events_hist.c | 92 +++++++++++++++++++- tools/testing/selftests/ftrace/Makefile | 2 tools/testing/selftests/ftrace/poll.c | 74 ++++++++++++++++ .../ftrace/test.d/trigger/trigger-hist-poll.tc | 74 ++++++++++++++++ 6 files changed, 267 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/ftrace/poll.c create mode 100644 tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc -- Masami Hiramatsu (Google) <mhiramat(a)kernel.org>

6 months, 1 week

2
5
0 0

[PATCH net-next 0/4] selftests/net: packetdrill: import multiple tests

by Soham Chakradeo

From: Soham Chakradeo <sohamch(a)google.com> Import tests for the following features (folder names in brackets): ECN (ecn) : RFC 3168 Close (close) : RFC 9293 TCP_INFO (tcp_info) : RFC 9293 Fast recovery (fast_recovery) : RFC 5681 Timestamping (timestamping) : RFC 1323 Nagle (nagle) : RFC 896 Selective Acknowledgments (sack) : RFC 2018 Recent Timestamp (ts_recent) : RFC 1323 Send file (sendfile) Syscall bad arg (syscall_bad_arg) Validate (validate) Blocking (blocking) Splice (splice) End of record (eor) Limited transmit (limited_transmit) Procedure to import and test the packetdrill tests into upstream linux is explained in the first patch of this series These tests have many authors. We only import them here from github.com/google/packetdrill. Thanks to the following authors fo their contributions over the years to these tests: Neal Cardwell, Shuo Chen, Yuchung Cheng, Jerry Chu, Eric Dumazet, Luke Hsiao, Priyaranjan Jha, Chonggang Li, Tanner Love, John Sperbeck, Wei Wang and Maciej Żenczykowski. For more info see the original github commits, such as https://github.com/google/packetdrill/commit/8229c94928ac. Signed-off-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Soham Chakradeo <sohamch(a)google.com> Soham Chakradeo (4): selftests/net: packetdrill: import tcp/ecn , tcp/close , tcp/sack , tcp/tcp_info selftests/net: packetdrill: import tcp/fast_recovery , tcp/nagle , tcp/timestamping selftests/net: packetdrill: import tcp/eor , tcp/splice , tcp/ts_recent , tcp/blocking selftests/net: packetdrill: import tcp/user_timeout , tcp/validate , tcp/sendfile , tcp/limited-transmit , tcp/syscall_bad_arg .../tcp_blocking_blocking-accept.pkt | 18 +++ .../tcp_blocking_blocking-connect.pkt | 13 ++ .../tcp_blocking_blocking-read.pkt | 29 ++++ .../tcp_blocking_blocking-write.pkt | 35 +++++ ...lose_close-local-close-then-remote-fin.pkt | 23 +++ .../tcp_close_close-on-syn-sent.pkt | 21 +++ .../tcp_close_close-remote-fin-then-close.pkt | 36 +++++ .../net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt | 21 +++ .../packetdrill/tcp_eor_no-coalesce-large.pkt | 38 +++++ .../tcp_eor_no-coalesce-retrans.pkt | 72 +++++++++ .../packetdrill/tcp_eor_no-coalesce-small.pkt | 36 +++++ .../tcp_eor_no-coalesce-subsequent.pkt | 66 ++++++++ .../tcp_fast_recovery_prr-ss-10pkt-lost-1.pkt | 72 +++++++++ ...t_recovery_prr-ss-30pkt-lost-1_4-11_16.pkt | 50 ++++++ ...tcp_fast_recovery_prr-ss-30pkt-lost1_4.pkt | 43 ++++++ ...ecovery_prr-ss-ack-below-snd_una-cubic.pkt | 41 +++++ ...ited_transmit_limited-transmit-no-sack.pkt | 53 +++++++ ...limited_transmit_limited-transmit-sack.pkt | 50 ++++++ .../packetdrill/tcp_nagle_https_client.pkt | 40 +++++ .../tcp_nagle_sendmsg_msg_more.pkt | 66 ++++++++ .../tcp_nagle_sockopt_cork_nodelay.pkt | 43 ++++++ .../tcp_sack_sack-route-refresh-ip-tos.pkt | 37 +++++ ...ack_sack-shift-sacked-2-6-8-3-9-nofack.pkt | 64 ++++++++ ..._sack_sack-shift-sacked-7-3-4-8-9-fack.pkt | 66 ++++++++ ..._sack_sack-shift-sacked-7-5-6-8-9-fack.pkt | 62 ++++++++ .../tcp_sendfile_sendfile-simple.pkt | 26 ++++ .../tcp_splice_tcp_splice_loop_test.pkt | 20 +++ ...scall_bad_arg_fastopen-invalid-buf-ptr.pkt | 42 +++++ .../tcp_syscall_bad_arg_sendmsg-empty-iov.pkt | 31 ++++ ...yscall_bad_arg_syscall-invalid-buf-ptr.pkt | 25 +++ .../tcp_tcp_info_tcp-info-last_data_recv.pkt | 21 +++ .../tcp_tcp_info_tcp-info-rwnd-limited.pkt | 54 +++++++ .../tcp_tcp_info_tcp-info-sndbuf-limited.pkt | 39 +++++ ...tcp_timestamping_client-only-last-byte.pkt | 92 +++++++++++ .../packetdrill/tcp_timestamping_partial.pkt | 91 +++++++++++ .../packetdrill/tcp_timestamping_server.pkt | 145 ++++++++++++++++++ .../packetdrill/tcp_ts_recent_fin_tsval.pkt | 23 +++ .../packetdrill/tcp_ts_recent_invalid_ack.pkt | 25 +++ .../packetdrill/tcp_ts_recent_reset_tsval.pkt | 25 +++ .../tcp_user_timeout_user-timeout-probe.pkt | 37 +++++ .../tcp_user_timeout_user_timeout.pkt | 33 ++++ ...validate_validate-established-no-flags.pkt | 24 +++ 42 files changed, 1848 insertions(+) create mode 100644 tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-accept.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-connect.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-write.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_close_close-local-close-then-remote-fin.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_close_close-on-syn-sent.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_close_close-remote-fin-then-close.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-large.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-retrans.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-small.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-subsequent.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-10pkt-lost-1.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost-1_4-11_16.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost1_4.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-ack-below-snd_una-cubic.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-no-sack.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-sack.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_nagle_https_client.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_nagle_sendmsg_msg_more.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_nagle_sockopt_cork_nodelay.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_sack_sack-route-refresh-ip-tos.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-2-6-8-3-9-nofack.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-3-4-8-9-fack.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-5-6-8-9-fack.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_sendfile_sendfile-simple.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_splice_tcp_splice_loop_test.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_fastopen-invalid-buf-ptr.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_syscall-invalid-buf-ptr.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-last_data_recv.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-rwnd-limited.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-sndbuf-limited.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_timestamping_client-only-last-byte.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_timestamping_partial.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_timestamping_server.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_ts_recent_fin_tsval.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_ts_recent_reset_tsval.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_user_timeout_user_timeout.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_validate_validate-established-no-flags.pkt -- 2.47.0.338.g60cca15819-goog

6 months, 1 week

5
14
0 0

[PATCH v6 0/3] tracing: Support poll on event hist file

by Masami Hiramatsu (Google)

Hi, Here is the v6 patch to support polling on event 'hist' file. The previous version is here; https://lore.kernel.org/all/172398710447.295714.4489282566285719918.stgit@d… This version is rebased on the ftrace/for-next branch of the linux-trace tree, and use global irq_work and wq instead of per-event one. Background ---------- There has been interest in allowing user programs to monitor kernel events in real time. Ftrace provides `trace_pipe` interface to wait on events in the ring buffer, but it is needed to wait until filling up a page with events in the ring buffer. We can also peek the `trace` file periodically, but that is inefficient way to monitor a randomely happening event. Overview -------- This patch set allows user to `poll`(or `select`, `epoll`) on event histogram interface. As you know each event has its own `hist` file which shows histograms generated by trigger action. So user can set a new hist trigger on any event you want to monitor, and poll on the `hist` file until it is updated. There are 2 poll events are supported, POLLIN and POLLPRI. POLLIN means that there are any readable update on `hist` file and this event will be flashed only when you call read(). So, this is useful if you want to read the histogram periodically. The other POLLPRI event is for monitoring trace event. Like the POLLIN, this will be returned when the histogram is updated, but you don't need to read() the file and use poll() again. Note that this waits for histogram update (not event arrival), thus you must set a histogram on the event at first. Usage ----- Here is an example usage: ---- TRACEFS=/sys/kernel/tracing EVENT=$TRACEFS/events/sched/sched_process_free # setup histogram trigger and enable event echo "hist:key=comm" >> $EVENT/trigger echo 1 > $EVENT/enable # Wait for update poll pri $EVENT/hist # Event arrived. echo "process free event is comming" tail $TRACEFS/trace ---- The 'poll' command is in the selftest patch. You can take this series also from here; https://git.kernel.org/pub/scm/linux/kernel/git/mhiramat/linux.git/log/?h=t… Thank you, --- Masami Hiramatsu (Google) (3): tracing/hist: Add poll(POLLIN) support on hist file tracing/hist: Support POLLPRI event for poll on histogram selftests/tracing: Add hist poll() support test include/linux/trace_events.h | 14 +++ kernel/trace/trace_events.c | 14 +++ kernel/trace/trace_events_hist.c | 100 +++++++++++++++++++- tools/testing/selftests/ftrace/Makefile | 2 tools/testing/selftests/ftrace/poll.c | 74 +++++++++++++++ .../ftrace/test.d/trigger/trigger-hist-poll.tc | 74 +++++++++++++++ 6 files changed, 275 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/ftrace/poll.c create mode 100644 tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc -- Masami Hiramatsu (Google) <mhiramat(a)kernel.org>

6 months, 1 week

3
9
0 0

[PATCH v2 0/2] riscv/ptrace: add new regset to access original a0 register

by Celeste Liu

The orig_a0 is missing in struct user_regs_struct of riscv, and there is no way to add it without breaking UAPI. (See Link tag below) Like NT_ARM_SYSTEM_CALL do, we add a new regset name NT_RISCV_ORIG_A0 to access original a0 register from userspace via ptrace API. Link: https://lore.kernel.org/all/59505464-c84a-403d-972f-d4b2055eeaac@gmail.com/ Signed-off-by: Celeste Liu <uwu(a)coelacanthus.name> --- Changes in v2: - Fix integer width. - Add selftest. - Link to v1: https://lore.kernel.org/r/20241201-riscv-new-regset-v1-1-c83c58abcc7b@coela… --- Celeste Liu (1): riscv/ptrace: add new regset to access original a0 register Charlie Jenkins (1): riscv: selftests: Add a ptrace test to verify syscall parameter modification arch/riscv/kernel/ptrace.c | 32 +++++++ include/uapi/linux/elf.h | 1 + tools/testing/selftests/riscv/abi/.gitignore | 1 + tools/testing/selftests/riscv/abi/Makefile | 5 +- tools/testing/selftests/riscv/abi/ptrace.c | 134 +++++++++++++++++++++++++++ 5 files changed, 172 insertions(+), 1 deletion(-) --- base-commit: 0e287d31b62bb53ad81d5e59778384a40f8b6f56 change-id: 20241201-riscv-new-regset-d529b952ad0d Best regards, -- Celeste Liu <uwu(a)coelacanthus.name>

6 months, 1 week

5
10
0 0

[PATCH v3 0/2] riscv/ptrace: add new regset to access original a0 register

by Celeste Liu

The orig_a0 is missing in struct user_regs_struct of riscv, and there is no way to add it without breaking UAPI. (See Link tag below) Like NT_ARM_SYSTEM_CALL do, we add a new regset name NT_RISCV_ORIG_A0 to access original a0 register from userspace via ptrace API. Link: https://lore.kernel.org/all/59505464-c84a-403d-972f-d4b2055eeaac@gmail.com/ Signed-off-by: Celeste Liu <uwu(a)coelacanthus.name> --- Changes in v3: - Use return 0 directly for readability. - Fix test for modify a0. - Add Fixes: tag - Remove useless Cc: stable. - Selftest will check both a0 and orig_a0, but depends on the correctness of PTRACE_GET_SYSCALL_INFO. - Link to v2: https://lore.kernel.org/r/20241203-riscv-new-regset-v2-0-d37da8c0cba6@coela… Changes in v2: - Fix integer width. - Add selftest. - Link to v1: https://lore.kernel.org/r/20241201-riscv-new-regset-v1-1-c83c58abcc7b@coela… --- Celeste Liu (2): riscv/ptrace: add new regset to access original a0 register riscv: selftests: Add a ptrace test to verify syscall parameter modification arch/riscv/kernel/ptrace.c | 32 ++++++ include/uapi/linux/elf.h | 1 + tools/testing/selftests/riscv/abi/.gitignore | 1 + tools/testing/selftests/riscv/abi/Makefile | 5 +- tools/testing/selftests/riscv/abi/ptrace.c | 151 +++++++++++++++++++++++++++ 5 files changed, 189 insertions(+), 1 deletion(-) --- base-commit: 0e287d31b62bb53ad81d5e59778384a40f8b6f56 change-id: 20241201-riscv-new-regset-d529b952ad0d Best regards, -- Celeste Liu <uwu(a)coelacanthus.name>

6 months, 1 week

1
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror