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

[PATCH][next] selftests/mm: Fix spelling mistake "succedded" -> "succeeded"

by Colin Ian King

There is a spelling mistake in a ksft_exit_fail_msg message. Fix it. Signed-off-by: Colin Ian King <colin.i.king(a)gmail.com> --- tools/testing/selftests/mm/vm_util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 4aeb8d5299ff..05736c615734 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -75,7 +75,7 @@ static bool pagemap_scan_supported(int fd, char *start) /* Provide an invalid address in order to trigger EFAULT. */ ret = __pagemap_scan_get_categories(fd, start, (struct page_region *) ~0UL); if (ret == 0) - ksft_exit_fail_msg("PAGEMAP_SCAN succedded unexpectedly\n"); + ksft_exit_fail_msg("PAGEMAP_SCAN succeeded unexpectedly\n"); supported = errno == EFAULT; -- 2.39.2

1 year, 7 months

1
0
0 0

[PATCH net-next] selftests: net: verify fq per-band packet limit

by Willem de Bruijn

From: Willem de Bruijn <willemb(a)google.com> Commit 29f834aa326e ("net_sched: sch_fq: add 3 bands and WRR scheduling") introduces multiple traffic bands, and per-band maximum packet count. Per-band limits ensures that packets in one class cannot fill the entire qdisc and so cause DoS to the traffic in the other classes. Verify this behavior: 1. set the limit to 10 per band 2. send 20 pkts on band A: verify that 10 are queued, 10 dropped 3. send 20 pkts on band A: verify that 0 are queued, 20 dropped 4. send 20 pkts on band B: verify that 10 are queued, 10 dropped Packets must remain queued for a period to trigger this behavior. Use SO_TXTIME to store packets for 100 msec. The test reuses existing upstream test infra. The script is a fork of cmsg_time.sh. The scripts call cmsg_sender. The test extends cmsg_sender with two arguments: * '-P' SO_PRIORITY There is a subtle difference between IPv4 and IPv6 stack behavior: PF_INET/IP_TOS sets IP header bits and sk_priority PF_INET6/IPV6_TCLASS sets IP header bits BUT NOT sk_priority * '-n' num pkts Send multiple packets in quick succession. I first attempted a for loop in the script, but this is too slow in virtualized environments, causing flakiness as the 100ms timeout is reached and packets are dequeued. Also do not wait for timestamps to be queued unless timestamps are requested. Signed-off-by: Willem de Bruijn <willemb(a)google.com> --- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/cmsg_sender.c | 50 ++++++++++------ .../testing/selftests/net/fq_band_pktlimit.sh | 57 +++++++++++++++++++ 3 files changed, 91 insertions(+), 17 deletions(-) create mode 100755 tools/testing/selftests/net/fq_band_pktlimit.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 5b2aca4c5f10..9274edfb76ff 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -91,6 +91,7 @@ TEST_PROGS += test_bridge_neigh_suppress.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh TEST_PROGS += fdb_flush.sh +TEST_PROGS += fq_band_pktlimit.sh TEST_FILES := settings diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c index 24b21b15ed3f..8d7575389f58 100644 --- a/tools/testing/selftests/net/cmsg_sender.c +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -45,11 +45,13 @@ struct options { const char *host; const char *service; unsigned int size; + unsigned int num_pkt; struct { unsigned int mark; unsigned int dontfrag; unsigned int tclass; unsigned int hlimit; + unsigned int priority; } sockopt; struct { unsigned int family; @@ -72,6 +74,7 @@ struct options { } v6; } opt = { .size = 13, + .num_pkt = 1, .sock = { .family = AF_UNSPEC, .type = SOCK_DGRAM, @@ -112,7 +115,7 @@ static void cs_parse_args(int argc, char *argv[]) { int o; - while ((o = getopt(argc, argv, "46sS:p:m:M:d:tf:F:c:C:l:L:H:")) != -1) { + while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:")) != -1) { switch (o) { case 's': opt.silent_send = true; @@ -138,7 +141,9 @@ static void cs_parse_args(int argc, char *argv[]) cs_usage(argv[0]); } break; - + case 'P': + opt.sockopt.priority = atoi(optarg); + break; case 'm': opt.mark.ena = true; opt.mark.val = atoi(optarg); @@ -146,6 +151,9 @@ static void cs_parse_args(int argc, char *argv[]) case 'M': opt.sockopt.mark = atoi(optarg); break; + case 'n': + opt.num_pkt = atoi(optarg); + break; case 'd': opt.txtime.ena = true; opt.txtime.delay = atoi(optarg); @@ -410,6 +418,10 @@ static void ca_set_sockopts(int fd) setsockopt(fd, SOL_IPV6, IPV6_UNICAST_HOPS, &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit))) error(ERN_SOCKOPT, errno, "setsockopt IPV6_HOPLIMIT"); + if (opt.sockopt.priority && + setsockopt(fd, SOL_SOCKET, SO_PRIORITY, + &opt.sockopt.priority, sizeof(opt.sockopt.priority))) + error(ERN_SOCKOPT, errno, "setsockopt SO_PRIORITY"); } int main(int argc, char *argv[]) @@ -421,6 +433,7 @@ int main(int argc, char *argv[]) char *buf; int err; int fd; + int i; cs_parse_args(argc, argv); @@ -480,24 +493,27 @@ int main(int argc, char *argv[]) cs_write_cmsg(fd, &msg, cbuf, sizeof(cbuf)); - err = sendmsg(fd, &msg, 0); - if (err < 0) { - if (!opt.silent_send) - fprintf(stderr, "send failed: %s\n", strerror(errno)); - err = ERN_SEND; - goto err_out; - } else if (err != (int)opt.size) { - fprintf(stderr, "short send\n"); - err = ERN_SEND_SHORT; - goto err_out; - } else { - err = ERN_SUCCESS; + for (i = 0; i < opt.num_pkt; i++) { + err = sendmsg(fd, &msg, 0); + if (err < 0) { + if (!opt.silent_send) + fprintf(stderr, "send failed: %s\n", strerror(errno)); + err = ERN_SEND; + goto err_out; + } else if (err != (int)opt.size) { + fprintf(stderr, "short send\n"); + err = ERN_SEND_SHORT; + goto err_out; + } } + err = ERN_SUCCESS; - /* Make sure all timestamps have time to loop back */ - usleep(opt.txtime.delay); + if (opt.ts.ena) { + /* Make sure all timestamps have time to loop back */ + usleep(opt.txtime.delay); - cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + } err_out: close(fd); diff --git a/tools/testing/selftests/net/fq_band_pktlimit.sh b/tools/testing/selftests/net/fq_band_pktlimit.sh new file mode 100755 index 000000000000..24b77bdf41ff --- /dev/null +++ b/tools/testing/selftests/net/fq_band_pktlimit.sh @@ -0,0 +1,57 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Verify that FQ has a packet limit per band: +# +# 1. set the limit to 10 per band +# 2. send 20 pkts on band A: verify that 10 are queued, 10 dropped +# 3. send 20 pkts on band A: verify that 0 are queued, 20 dropped +# 4. send 20 pkts on band B: verify that 10 are queued, 10 dropped +# +# Send packets with a 100ms delay to ensure that previously sent +# packets are still queued when later ones are sent. +# Use SO_TXTIME for this. + +die() { + echo "$1" + exit 1 +} + +# run inside private netns +if [[ $# -eq 0 ]]; then + ./in_netns.sh "$0" __subprocess + exit +fi + +ip link add type dummy +ip link set dev dummy0 up +ip -6 addr add fdaa::1/128 dev dummy0 +ip -6 route add fdaa::/64 dev dummy0 +tc qdisc replace dev dummy0 root handle 1: fq quantum 1514 initial_quantum 1514 limit 10 + +./cmsg_sender -6 -p u -d 100000 -n 20 fdaa::2 8000 +OUT1="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" + +./cmsg_sender -6 -p u -d 100000 -n 20 fdaa::2 8000 +OUT2="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" + +./cmsg_sender -6 -p u -d 100000 -n 20 -P 7 fdaa::2 8000 +OUT3="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" + +# Initial stats will report zero sent, as all packets are still +# queued in FQ. Sleep for the delay period (100ms) and see that +# twenty are now sent. +sleep 0.1 +OUT4="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" + +# Log the output after the test +echo "${OUT1}" +echo "${OUT2}" +echo "${OUT3}" +echo "${OUT4}" + +# Test the output for expected values +echo "${OUT1}" | grep -q '0\ pkt\ (dropped\ 10' || die "unexpected drop count at 1" +echo "${OUT2}" | grep -q '0\ pkt\ (dropped\ 30' || die "unexpected drop count at 2" +echo "${OUT3}" | grep -q '0\ pkt\ (dropped\ 40' || die "unexpected drop count at 3" +echo "${OUT4}" | grep -q '20\ pkt\ (dropped\ 40' || die "unexpected accept count at 4" -- 2.43.0.rc1.413.gea7ed67945-goog

1 year, 7 months

4
3
0 0

Re: [PATCH v2 0/6] IOMMUFD: Deliver IO page faults to user space

by Jason Gunthorpe

On Wed, Nov 15, 2023 at 01:17:06PM +0800, Liu, Jing2 wrote: > This is the right way to approach it, > > I learned that there was discussion about using io_uring to get the > page fault without > > eventfd notification in [1], and I am new at io_uring and studying the > man page of > > liburing, but there're questions in my mind on how can QEMU get the > coming page fault > > with a good performance. > > Since both QEMU and Kernel don't know when comes faults, after QEMU > submits one > > read task to io_uring, we want kernel pending until fault comes. While > based on > > hwpt_fault_fops_read() in [patch v2 4/6], it just returns 0 since > there's now no fault, > > thus this round of read completes to CQ but it's not what we want. So > I'm wondering > > how kernel pending on the read until fault comes. Does fops callback > need special work to Implement a fops with poll support that triggers when a new event is pushed and everything will be fine. There are many examples in the kernel. The ones in the mlx5 vfio driver spring to mind as a scheme I recently looked at. Jason

1 year, 7 months

2
2
0 0

[PATCH bpf-next v2 0/4] selftests/bpf: Update multiple prog_tests to use ASSERT_ macros

by Yuran Pereira

Multiple files/programs in `tools/testing/selftests/bpf/prog_tests/` still heavily use the `CHECK` macro, even when better `ASSERT_` alternatives are available. As it was already pointed out by Yonghong Song [1] in the bpf selftests the use of the ASSERT_* series of macros is preferred over the CHECK macro. This patchset replaces the usage of `CHECK(` macros to the equivalent `ASSERT_` family of macros in the following prog_tests: - bind_perm.c - bpf_obj_id.c - bpf_tcp_ca.c - vmlinux.c [1] https://lore.kernel.org/lkml/0a142924-633c-44e6-9a92-2dc019656bf2@linux.dev Changes in v2: - Fixed pthread_join assertion that broke the previous test Previous version: v1 - https://lore.kernel.org/lkml/GV1PR10MB6563FCFF1C5DEBE84FEA985FE8B0A@GV1PR10… Yuran Pereira (4): Replaces the usage of CHECK calls for ASSERTs in bpf_tcp_ca Replaces the usage of CHECK calls for ASSERTs in bind_perm Replaces the usage of CHECK calls for ASSERTs in bpf_obj_id selftests/bpf: Replaces the usage of CHECK calls for ASSERTs in vmlinux .../selftests/bpf/prog_tests/bind_perm.c | 6 +- .../selftests/bpf/prog_tests/bpf_obj_id.c | 204 +++++++----------- .../selftests/bpf/prog_tests/bpf_tcp_ca.c | 50 ++--- .../selftests/bpf/prog_tests/vmlinux.c | 16 +- 4 files changed, 106 insertions(+), 170 deletions(-) -- 2.25.1

1 year, 7 months

2
10
0 0

[PATCH v4 0/5] cgroup/cpuset: Improve CPU isolation in isolated partitions

by Waiman Long

v4: - Update patch 1 to move apply_wqattrs_lock() and apply_wqattrs_unlock() down into CONFIG_SYSFS block to avoid compilation warnings. v3: - Break out a separate patch to make workqueue_set_unbound_cpumask() static and move it down to the CONFIG_SYSFS section. - Remove the "__DEBUG__." prefix and the CFTYPE_DEBUG flag from the new root only cpuset.cpus.isolated control files and update the test accordingly. v2: - Add 2 read-only workqueue sysfs files to expose the user requested cpumask as well as the isolated CPUs to be excluded from wq_unbound_cpumask. - Ensure that caller of the new workqueue_unbound_exclude_cpumask() hold cpus_read_lock. - Update the cpuset code to make sure the cpus_read_lock is held whenever workqueue_unbound_exclude_cpumask() may be called. Isolated cpuset partition can currently be created to contain an exclusive set of CPUs not used in other cgroups and with load balancing disabled to reduce interference from the scheduler. The main purpose of this isolated partition type is to dynamically emulate what can be done via the "isolcpus" boot command line option, specifically the default domain flag. One effect of the "isolcpus" option is to remove the isolated CPUs from the cpumasks of unbound workqueues since running work functions in an isolated CPU can be a major source of interference. Changing the unbound workqueue cpumasks can be done at run time by writing an appropriate cpumask without the isolated CPUs to /sys/devices/virtual/workqueue/cpumask. So one can set up an isolated cpuset partition and then write to the cpumask sysfs file to achieve similar level of CPU isolation. However, this manual process can be error prone. This patch series implements automatic exclusion of isolated CPUs from unbound workqueue cpumasks when an isolated cpuset partition is created and then adds those CPUs back when the isolated partition is destroyed. There are also other places in the kernel that look at the HK_FLAG_DOMAIN cpumask or other HK_FLAG_* cpumasks and exclude the isolated CPUs from certain actions to further reduce interference. CPUs in an isolated cpuset partition will not be able to avoid those interferences yet. That may change in the future as the need arises. Waiman Long (5): workqueue: Make workqueue_set_unbound_cpumask() static workqueue: Add workqueue_unbound_exclude_cpumask() to exclude CPUs from wq_unbound_cpumask selftests/cgroup: Minor code cleanup and reorganization of test_cpuset_prs.sh cgroup/cpuset: Keep track of CPUs in isolated partitions cgroup/cpuset: Take isolated CPUs out of workqueue unbound cpumask Documentation/admin-guide/cgroup-v2.rst | 10 +- include/linux/workqueue.h | 2 +- kernel/cgroup/cpuset.c | 286 +++++++++++++----- kernel/workqueue.c | 165 +++++++--- .../selftests/cgroup/test_cpuset_prs.sh | 216 ++++++++----- 5 files changed, 475 insertions(+), 204 deletions(-) -- 2.39.3

1 year, 7 months

2
7
0 0

[PATCH RFC RFT v2 0/5] fork: Support shadow stacks in clone3()

by Mark Brown

The kernel has recently added support for shadow stacks, currently x86 only using their CET feature but both arm64 and RISC-V have equivalent features (GCS and Zisslpcfi respectively), I am actively working on GCS[1]. With shadow stacks the hardware maintains an additional stack containing only the return addresses for branch instructions which is not generally writeable by userspace and ensures that any returns are to the recorded addresses. This provides some protection against ROP attacks and making it easier to collect call stacks. These shadow stacks are allocated in the address space of the userspace process. Our API for shadow stacks does not currently offer userspace any flexiblity for managing the allocation of shadow stacks for newly created threads, instead the kernel allocates a new shadow stack with the same size as the normal stack whenever a thread is created with the feature enabled. The stacks allocated in this way are freed by the kernel when the thread exits or shadow stacks are disabled for the thread. This lack of flexibility and control isn't ideal, in the vast majority of cases the shadow stack will be over allocated and the implicit allocation and deallocation is not consistent with other interfaces. As far as I can tell the interface is done in this manner mainly because the shadow stack patches were in development since before clone3() was implemented. Since clone3() is readily extensible let's add support for specifying a shadow stack when creating a new thread or process in a similar manner to how the normal stack is specified, keeping the current implicit allocation behaviour if one is not specified either with clone3() or through the use of clone(). Unlike normal stacks only the shadow stack size is specified, similar issues to those that lead to the creation of map_shadow_stack() apply. Please note that the x86 portions of this code are build tested only, I don't appear to have a system that can run CET avaible to me, I have done testing with an integration into my pending work for GCS. There is some possibility that the arm64 implementation may require the use of clone3() and explicit userspace allocation of shadow stacks, this is still under discussion. A new architecture feature Kconfig option for shadow stacks is added as here, this was suggested as part of the review comments for the arm64 GCS series and since we need to detect if shadow stacks are supported it seemed sensible to roll it in here. [1] https://lore.kernel.org/r/20231009-arm64-gcs-v6-0-78e55deaa4dd@kernel.org/ Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v2: - Rebase onto v6.7-rc1. - Remove ability to provide preallocated shadow stack, just specify the desired size. - Link to v1: https://lore.kernel.org/r/20231023-clone3-shadow-stack-v1-0-d867d0b5d4d0@ke… --- Mark Brown (5): mm: Introduce ARCH_HAS_USER_SHADOW_STACK fork: Add shadow stack support to clone3() selftests/clone3: Factor more of main loop into test_clone3() selftests/clone3: Allow tests to flag if -E2BIG is a valid error code kselftest/clone3: Test shadow stack support arch/x86/Kconfig | 1 + arch/x86/include/asm/shstk.h | 11 +- arch/x86/kernel/process.c | 2 +- arch/x86/kernel/shstk.c | 30 ++++- fs/proc/task_mmu.c | 2 +- include/linux/mm.h | 2 +- include/linux/sched/task.h | 2 + include/uapi/linux/sched.h | 4 + kernel/fork.c | 24 +++- mm/Kconfig | 6 + tools/testing/selftests/clone3/clone3.c | 151 ++++++++++++++++------ tools/testing/selftests/clone3/clone3_selftests.h | 7 + 12 files changed, 188 insertions(+), 54 deletions(-) --- base-commit: b85ea95d086471afb4ad062012a4d73cd328fa86 change-id: 20231019-clone3-shadow-stack-15d40d2bf536 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year, 7 months

5
31
0 0

[PATCH] selftests/resctrl: Add non-contiguous CBMs CAT test

by Maciej Wieczor-Retman

Non-contiguous CBM support for Intel CAT has been merged into the kernel with Commit 0e3cd31f6e90 ("x86/resctrl: Enable non-contiguous CBMs in Intel CAT") but there is no selftest that would validate if this feature works correctly. The selftest needs to verify if writing non-contiguous CBMs to the schemata file behaves as expected in comparison to the information about non-contiguous CBMs support. Add tests for both L2 and L3 CAT to verify if the return values generated by writing non-contiguous CBMs don't contradict the reported non-contiguous support information. Comparing the return value of write_schemata() with non-contiguous CBMs support information can be simplified as a logical XOR operation. In other words if non-contiguous CBMs are supported and if non-contiguous write succeeds the test should succeed and if the write fails the test should also fail. The opposite should happen if non-contiguous CBMs are not supported. Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman(a)intel.com> --- This patch is based on a rework of resctrl selftests that's currently in review [1]. The patch also implements a similiar functionality presented in the bash script included in the cover letter to the original non-contiguous CBMs in Intel CAT series [2]. [1] https://lore.kernel.org/all/20231024092634.7122-1-ilpo.jarvinen@linux.intel… [2] https://lore.kernel.org/all/cover.1696934091.git.maciej.wieczor-retman@inte… tools/testing/selftests/resctrl/cat_test.c | 97 +++++++++++++++++++ tools/testing/selftests/resctrl/resctrl.h | 2 + .../testing/selftests/resctrl/resctrl_tests.c | 2 + 3 files changed, 101 insertions(+) diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index bc88eb891f35..6a01a5da30b4 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -342,6 +342,87 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param return ret; } +static int noncont_cat_run_test(const struct resctrl_test *test, + const struct user_params *uparams) +{ + unsigned long full_cache_mask, cont_mask, noncont_mask; + unsigned int eax, ebx, ecx, edx, ret, sparse_masks; + char res_path[PATH_MAX]; + char schemata[64]; + int bit_center; + FILE *fp; + + /* Check to compare sparse_masks content to cpuid output. */ + snprintf(res_path, sizeof(res_path), "%s/%s/%s", INFO_PATH, + test->resource, "sparse_masks"); + + fp = fopen(res_path, "r"); + if (!fp) { + perror("# Error in opening file\n"); + return errno; + } + + if (fscanf(fp, "%u", &sparse_masks) <= 0) { + perror("Could not get sparse_masks contents\n"); + fclose(fp); + return -1; + } + + fclose(fp); + + if (!strcmp(test->resource, "L3")) + __cpuid_count(0x10, 1, eax, ebx, ecx, edx); + else if (!strcmp(test->resource, "L2")) + __cpuid_count(0x10, 2, eax, ebx, ecx, edx); + else + return -EINVAL; + + if (sparse_masks != ((ecx >> 3) & 1)) + return -1; + + /* Write checks initialization. */ + ret = get_cbm_mask(test->resource, &full_cache_mask); + if (ret < 0) + return ret; + bit_center = count_bits(full_cache_mask) / 2; + cont_mask = full_cache_mask >> bit_center; + + /* Contiguous mask write check. */ + snprintf(schemata, sizeof(schemata), "%lx", cont_mask); + ret = write_schemata("", schemata, uparams->cpu, test->resource); + if (ret) + return ret; + + /* + * Non-contiguous mask write check. CBM has a 0xf hole approximately in the middle. + * Output is compared with support information to catch any edge case errors. + */ + noncont_mask = ~(full_cache_mask & (0xf << bit_center)) & full_cache_mask; + snprintf(schemata, sizeof(schemata), "%lx", noncont_mask); + ret = write_schemata("", schemata, uparams->cpu, test->resource); + if (ret && sparse_masks) + ksft_print_msg("Non-contiguous CBMs supported but write failed\n"); + else if (ret && !sparse_masks) + ksft_print_msg("Non-contiguous CBMs not supported and write failed as expected\n"); + else if (!ret && !sparse_masks) + ksft_print_msg("Non-contiguous CBMs not supported but write succeeded\n"); + return !ret == !sparse_masks; +} + +static bool noncont_cat_feature_check(const struct resctrl_test *test) +{ + char res_path[PATH_MAX]; + struct stat statbuf; + + snprintf(res_path, sizeof(res_path), "%s/%s/%s", INFO_PATH, + test->resource, "sparse_masks"); + + if (stat(res_path, &statbuf)) + return false; + + return test_resource_feature_check(test); +} + struct resctrl_test l3_cat_test = { .name = "L3_CAT", .group = "CAT", @@ -357,3 +438,19 @@ struct resctrl_test l2_cat_test = { .feature_check = test_resource_feature_check, .run_test = cat_run_test, }; + +struct resctrl_test l3_noncont_cat_test = { + .name = "L3_NONCONT_CAT", + .group = "NONCONT_CAT", + .resource = "L3", + .feature_check = noncont_cat_feature_check, + .run_test = noncont_cat_run_test, +}; + +struct resctrl_test l2_noncont_cat_test = { + .name = "L2_NONCONT_CAT", + .group = "NONCONT_CAT", + .resource = "L2", + .feature_check = noncont_cat_feature_check, + .run_test = noncont_cat_run_test, +}; diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index fffeb442c173..51b8a6ff3a0d 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -184,5 +184,7 @@ extern struct resctrl_test mba_test; extern struct resctrl_test cmt_test; extern struct resctrl_test l3_cat_test; extern struct resctrl_test l2_cat_test; +extern struct resctrl_test l3_noncont_cat_test; +extern struct resctrl_test l2_noncont_cat_test; #endif /* RESCTRL_H */ diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index 9e254bca6c25..fdeef82feb4e 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -16,6 +16,8 @@ static struct resctrl_test *resctrl_tests[] = { &cmt_test, &l3_cat_test, &l2_cat_test, + &l3_noncont_cat_test, + &l2_noncont_cat_test, }; static int detect_vendor(void) -- 2.42.1

1 year, 7 months

3
3
0 0

[PATCH v2] Kunit to check the longest symbol length

by Sergio González Collado

The longest length of a symbol (KSYM_NAME_LEN) was increased to 512 in the reference [1]. This patch adds a kunit test to check the longest symbol length. [1] https://lore.kernel.org/lkml/20220802015052.10452-6-ojeda@kernel.org/ Tested-by: Martin Rodriguez Reboredo <yakoyoku(a)gmail.com> Signed-off-by: Sergio González Collado <sergio.collado(a)gmail.com> - - - V1 -> V2: corrected CI tests. Added fix proposed at [2] [2] https://lore.kernel.org/lkml/Y9ES4UKl%2F+DtvAVS@gmail.com/T/#m3ef0e12bb834d… --- arch/x86/tools/insn_decoder_test.c | 3 +- lib/Kconfig.debug | 9 +++ lib/Makefile | 2 + lib/longest_symbol_kunit.c | 122 +++++++++++++++++++++++++++++ 4 files changed, 135 insertions(+), 1 deletion(-) create mode 100644 lib/longest_symbol_kunit.c diff --git a/arch/x86/tools/insn_decoder_test.c b/arch/x86/tools/insn_decoder_test.c index 472540aeabc2..6c2986d2ad11 100644 --- a/arch/x86/tools/insn_decoder_test.c +++ b/arch/x86/tools/insn_decoder_test.c @@ -10,6 +10,7 @@ #include <assert.h> #include <unistd.h> #include <stdarg.h> +#include <linux/kallsyms.h> #define unlikely(cond) (cond) @@ -106,7 +107,7 @@ static void parse_args(int argc, char **argv) } } -#define BUFSIZE 256 +#define BUFSIZE (256 + KSYM_NAME_LEN) int main(int argc, char **argv) { diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index cc7d53d9dc01..a531abece0a7 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2769,6 +2769,15 @@ config FORTIFY_KUNIT_TEST by the str*() and mem*() family of functions. For testing runtime traps of FORTIFY_SOURCE, see LKDTM's "FORTIFY_*" tests. +config LONGEST_SYM_KUNIT_TEST + tristate "Test the longest symbol possible" if !KUNIT_ALL_TESTS + depends on KUNIT && KPROBES + default KUNIT_ALL_TESTS + help + Tests the longest symbol possible + + If unsure, say N. + config HW_BREAKPOINT_KUNIT_TEST bool "Test hw_breakpoint constraints accounting" if !KUNIT_ALL_TESTS depends on HAVE_HW_BREAKPOINT diff --git a/lib/Makefile b/lib/Makefile index 6b09731d8e61..f72003d5869b 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -406,6 +406,8 @@ obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o obj-$(CONFIG_STRCAT_KUNIT_TEST) += strcat_kunit.o obj-$(CONFIG_STRSCPY_KUNIT_TEST) += strscpy_kunit.o obj-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o +obj-$(CONFIG_LONGEST_SYM_KUNIT_TEST) += longest_symbol_kunit.o +CFLAGS_longest_symbol_kunit.o += $(call cc-disable-warning, missing-prototypes) obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o diff --git a/lib/longest_symbol_kunit.c b/lib/longest_symbol_kunit.c new file mode 100644 index 000000000000..998563018f7a --- /dev/null +++ b/lib/longest_symbol_kunit.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test the longest symbol length. Execute with: + * ./tools/testing/kunit/kunit.py run longest-symbol + * --arch=x86_64 --kconfig_add CONFIG_KPROBES=y --kconfig_add CONFIG_MODULES=y + * --kconfig_add CONFIG_RETPOLINE=n + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <kunit/test.h> +#include <linux/stringify.h> +#include <linux/kprobes.h> +#include <linux/kallsyms.h> + +#define DI(name) s##name##name +#define DDI(name) DI(n##name##name) +#define DDDI(name) DDI(n##name##name) +#define DDDDI(name) DDDI(n##name##name) +#define DDDDDI(name) DDDDI(n##name##name) + +#define PLUS1(name) __PASTE(name, e) + +/*Generate a symbol whose name length is 511 */ +#define LONGEST_SYM_NAME DDDDDI(g1h2i3j4k5l6m7n) + +/*Generate a symbol whose name length is 512 */ +#define LONGEST_SYM_NAME_PLUS1 PLUS1(LONGEST_SYM_NAME) + +#define RETURN_LONGEST_SYM 0xAAAAA +#define RETURN_LONGEST_SYM_PLUS1 0x55555 + +noinline int LONGEST_SYM_NAME(void); +noinline int LONGEST_SYM_NAME(void) +{ + return RETURN_LONGEST_SYM; +} + +noinline int LONGEST_SYM_NAME_PLUS1(void); +noinline int LONGEST_SYM_NAME_PLUS1(void) +{ + return RETURN_LONGEST_SYM_PLUS1; +} + +_Static_assert(sizeof(__stringify(LONGEST_SYM_NAME)) == KSYM_NAME_LEN, +"Incorrect symbol length found. Expected KSYM_NAME_LEN: " +__stringify(KSYM_NAME) ", but found: " +__stringify(sizeof(LONGEST_SYM_NAME))); + +static void test_longest_symbol(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM, LONGEST_SYM_NAME()); +}; + +static void test_longest_symbol_kallsyms(struct kunit *test) +{ + unsigned long (*kallsyms_lookup_name)(const char *name); + static int (*longest_sym)(void); + + struct kprobe kp = { + .symbol_name = "kallsyms_lookup_name", + }; + + if (register_kprobe(&kp) < 0) { + pr_info("%s: kprobe not registered\n", __func__); + KUNIT_FAIL(test, "test_longest_symbol kallsysms: kprobe not registered\n"); + return; + } + + kunit_warn(test, "test_longest_symbol kallsyms: kprobe registered\n"); + kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr; + unregister_kprobe(&kp); + + longest_sym = + (void *) kallsyms_lookup_name(__stringify(LONGEST_SYM_NAME)); + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM, longest_sym()); +}; + +static void test_longest_symbol_plus1(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM_PLUS1, LONGEST_SYM_NAME_PLUS1()); +}; + +static void test_longest_symbol_plus1_kallsyms(struct kunit *test) +{ + unsigned long (*kallsyms_lookup_name)(const char *name); + static int (*longest_sym_plus1)(void); + + struct kprobe kp = { + .symbol_name = "kallsyms_lookup_name", + }; + + if (register_kprobe(&kp) < 0) { + pr_info("%s: kprobe not registered\n", __func__); + KUNIT_FAIL(test, "test_longest_symbol kallsysms: kprobe not registered\n"); + return; + } + + kunit_warn(test, "test_longest_symbol_plus1 kallsyms: kprobe registered\n"); + kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr; + unregister_kprobe(&kp); + + longest_sym_plus1 = + (void *) kallsyms_lookup_name(__stringify(LONGEST_SYM_NAME_PLUS1)); + KUNIT_EXPECT_NULL(test, longest_sym_plus1); +}; + +static struct kunit_case longest_symbol_test_cases[] = { + KUNIT_CASE(test_longest_symbol), + KUNIT_CASE(test_longest_symbol_kallsyms), + KUNIT_CASE(test_longest_symbol_plus1), + KUNIT_CASE(test_longest_symbol_plus1_kallsyms), + {} +}; + +static struct kunit_suite longest_symbol_test_suite = { + .name = "longest-symbol", + .test_cases = longest_symbol_test_cases, +}; +kunit_test_suite(longest_symbol_test_suite); + +MODULE_LICENSE("GPL"); base-commit: 037266a5f7239ead1530266f7d7af153d2a867fa -- 2.39.2

1 year, 7 months

1
0
0 0

[PATCH 2/2] mm/damon/core-test: test damon_split_region_at()'s access rate copying

by SeongJae Park

damon_split_region_at() should set access rate related fields of the resulting regions same. It may forgotten, and actually there was the mistake before. Test it with the unit test case for the function. Signed-off-by: SeongJae Park <sj(a)kernel.org> --- mm/damon/core-test.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h index 649adf91ebc5..e6a01ea2ec54 100644 --- a/mm/damon/core-test.h +++ b/mm/damon/core-test.h @@ -122,18 +122,25 @@ static void damon_test_split_at(struct kunit *test) { struct damon_ctx *c = damon_new_ctx(); struct damon_target *t; - struct damon_region *r; + struct damon_region *r, *r_new; t = damon_new_target(); r = damon_new_region(0, 100); + r->nr_accesses_bp = 420000; + r->nr_accesses = 42; + r->last_nr_accesses = 15; damon_add_region(r, t); damon_split_region_at(t, r, 25); KUNIT_EXPECT_EQ(test, r->ar.start, 0ul); KUNIT_EXPECT_EQ(test, r->ar.end, 25ul); - r = damon_next_region(r); - KUNIT_EXPECT_EQ(test, r->ar.start, 25ul); - KUNIT_EXPECT_EQ(test, r->ar.end, 100ul); + r_new = damon_next_region(r); + KUNIT_EXPECT_EQ(test, r_new->ar.start, 25ul); + KUNIT_EXPECT_EQ(test, r_new->ar.end, 100ul); + + KUNIT_EXPECT_EQ(test, r->nr_accesses_bp, r_new->nr_accesses_bp); + KUNIT_EXPECT_EQ(test, r->nr_accesses, r_new->nr_accesses); + KUNIT_EXPECT_EQ(test, r->last_nr_accesses, r_new->last_nr_accesses); damon_free_target(t); damon_destroy_ctx(c); -- 2.34.1

1 year, 7 months

1
0
0 0

[PATCH v5 0/6] workload-specific and memory pressure-driven zswap writeback

by Nhat Pham

Changelog: v5: * Replace reference getting with an rcu_read_lock() section for zswap lru modifications (suggested by Yosry) * Add a new prep patch that allows mem_cgroup_iter() to return online cgroup. * Add a callback that updates pool->next_shrink when the cgroup is offlined (suggested by Yosry Ahmed, Johannes Weiner) v4: * Rename list_lru_add to list_lru_add_obj and __list_lru_add to list_lru_add (patch 1) (suggested by Johannes Weiner and Yosry Ahmed) * Some cleanups on the memcg aware LRU patch (patch 2) (suggested by Yosry Ahmed) * Use event interface for the new per-cgroup writeback counters. (patch 3) (suggested by Yosry Ahmed) * Abstract zswap's lruvec states and handling into zswap_lruvec_state (patch 5) (suggested by Yosry Ahmed) v3: * Add a patch to export per-cgroup zswap writeback counters * Add a patch to update zswap's kselftest * Separate the new list_lru functions into its own prep patch * Do not start from the top of the hierarchy when encounter a memcg that is not online for the global limit zswap writeback (patch 2) (suggested by Yosry Ahmed) * Do not remove the swap entry from list_lru in __read_swapcache_async() (patch 2) (suggested by Yosry Ahmed) * Removed a redundant zswap pool getting (patch 2) (reported by Ryan Roberts) * Use atomic for the nr_zswap_protected (instead of lruvec's lock) (patch 5) (suggested by Yosry Ahmed) * Remove the per-cgroup zswap shrinker knob (patch 5) (suggested by Yosry Ahmed) v2: * Fix loongarch compiler errors * Use pool stats instead of memcg stats when !CONFIG_MEMCG_KEM There are currently several issues with zswap writeback: 1. There is only a single global LRU for zswap, making it impossible to perform worload-specific shrinking - an memcg under memory pressure cannot determine which pages in the pool it owns, and often ends up writing pages from other memcgs. This issue has been previously observed in practice and mitigated by simply disabling memcg-initiated shrinking: https://lore.kernel.org/all/20230530232435.3097106-1-nphamcs@gmail.com/T/#u But this solution leaves a lot to be desired, as we still do not have an avenue for an memcg to free up its own memory locked up in the zswap pool. 2. We only shrink the zswap pool when the user-defined limit is hit. This means that if we set the limit too high, cold data that are unlikely to be used again will reside in the pool, wasting precious memory. It is hard to predict how much zswap space will be needed ahead of time, as this depends on the workload (specifically, on factors such as memory access patterns and compressibility of the memory pages). This patch series solves these issues by separating the global zswap LRU into per-memcg and per-NUMA LRUs, and performs workload-specific (i.e memcg- and NUMA-aware) zswap writeback under memory pressure. The new shrinker does not have any parameter that must be tuned by the user, and can be opted in or out on a per-memcg basis. As a proof of concept, we ran the following synthetic benchmark: build the linux kernel in a memory-limited cgroup, and allocate some cold data in tmpfs to see if the shrinker could write them out and improved the overall performance. Depending on the amount of cold data generated, we observe from 14% to 35% reduction in kernel CPU time used in the kernel builds. Domenico Cerasuolo (3): zswap: make shrinking memcg-aware mm: memcg: add per-memcg zswap writeback stat selftests: cgroup: update per-memcg zswap writeback selftest Nhat Pham (3): list_lru: allows explicit memcg and NUMA node selection memcontrol: allows mem_cgroup_iter() to check for onlineness zswap: shrinks zswap pool based on memory pressure Documentation/admin-guide/mm/zswap.rst | 7 + drivers/android/binder_alloc.c | 5 +- fs/dcache.c | 8 +- fs/gfs2/quota.c | 6 +- fs/inode.c | 4 +- fs/nfs/nfs42xattr.c | 8 +- fs/nfsd/filecache.c | 4 +- fs/xfs/xfs_buf.c | 6 +- fs/xfs/xfs_dquot.c | 2 +- fs/xfs/xfs_qm.c | 2 +- include/linux/list_lru.h | 46 ++- include/linux/memcontrol.h | 9 +- include/linux/mmzone.h | 2 + include/linux/vm_event_item.h | 1 + include/linux/zswap.h | 27 +- mm/list_lru.c | 48 ++- mm/memcontrol.c | 20 +- mm/mmzone.c | 1 + mm/shrinker.c | 4 +- mm/swap.h | 3 +- mm/swap_state.c | 26 +- mm/vmscan.c | 26 +- mm/vmstat.c | 1 + mm/workingset.c | 4 +- mm/zswap.c | 430 +++++++++++++++++--- tools/testing/selftests/cgroup/test_zswap.c | 74 ++-- 26 files changed, 625 insertions(+), 149 deletions(-) -- 2.34.1

1 year, 7 months

3
21
0 0

[PATCH] selftests:proc-empty-vm: Remove unused debug write callIn the function test_proc_pid_statm

by angquan yu

From: angquan yu <angquan21(a)gmail.com> In tools/testing/selftests/proc/proc-empty->because the return value of a write call was being ignored. This call was partof a conditional debugging block (if (0) { ... }), which meant it would neveractually execute. This patch removes the unused debug write call. This cleanup resolves the compi>warning about ignoring the result of write declared with the warn_unused_resultattribute. Removing this code also improves the clarity and maintainability ofthe function, as it eliminates a non-functional block of code. This is original warning: proc-empty-vm.c: In function ‘test_proc_pid_statm’:proc-empty-vm.c:385:17: warning: ignoring return value of ‘write’ declared with>385 | write(1, buf, rv);| Signed-off-by: angquan yu <angquan21(a)gmail.com> --- tools/testing/selftests/proc/proc-empty-vm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/proc/proc-empty-vm.c b/tools/testing/selftests/proc/proc-empty-vm.c index 56198d4ca..74ef8627f 100644 --- a/tools/testing/selftests/proc/proc-empty-vm.c +++ b/tools/testing/selftests/proc/proc-empty-vm.c @@ -382,7 +382,10 @@ static int test_proc_pid_statm(pid_t pid) assert(rv >= 0); assert(rv <= sizeof(buf)); if (0) { - write(1, buf, rv); + ssize_t written = write(1, buf, rv); + if (written == -1) { + perror("write failed /proc/${pid}"); + } } const char *p = buf; -- 2.39.2

1 year, 7 months

1
0
0 0

[PATCH] selftests:proc-empty-vm: Remove unused debug write callIn the function test_proc_pid_statm

by angquan yu

From: angquan yu <angquan21(a)gmail.com> In tools/testing/selftests/proc/proc-empty->because the return value of a write call was being ignored. This call was partof a conditional debugging block (if (0) { ... }), which meant it would neveractually execute. This patch removes the unused debug write call. This cleanup resolves the compi>warning about ignoring the result of write declared with the warn_unused_resultattribute. Removing this code also improves the clarity and maintainability ofthe function, as it eliminates a non-functional block of code. This is original warning: proc-empty-vm.c: In function ‘test_proc_pid_statm’:proc-empty-vm.c:385:17: warning: ignoring return value of ‘write’ declared with>385 | write(1, buf, rv);| Signed-off-by: angquan yu <angquan21(a)gmail.com> --- tools/testing/selftests/proc/proc-empty-vm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/proc/proc-empty-vm.c b/tools/testing/selftests/proc/proc-empty-vm.c index 56198d4ca..74ef8627f 100644 --- a/tools/testing/selftests/proc/proc-empty-vm.c +++ b/tools/testing/selftests/proc/proc-empty-vm.c @@ -382,7 +382,10 @@ static int test_proc_pid_statm(pid_t pid) assert(rv >= 0); assert(rv <= sizeof(buf)); if (0) { - write(1, buf, rv); + ssize_t written = write(1, buf, rv); + if (written == -1) { + perror("write failed /proc/${pid}"); + } } const char *p = buf; -- 2.39.2

1 year, 7 months

1
0
0 0

[PATCH 1/2] [PATCH,breakpoints] selftests/breakpoints: Fix format specifier in ksft_print_msg in step_after_suspend_test.c

by angquan yu

From: angquan yu <angquan21(a)gmail.com> In the function 'tools/testing/selftests/breakpoints/run_test' within step_after_suspend_test.c, the ksft_print_msg function call incorrectly used '$s' as a format specifier. This commit corrects this typo to use the proper '%s' format specifier, ensuring the error message from waitpid() is correctly displayed. The issue manifested as a compilation warning (too many arguments for format [-Wformat-extra-args]), potentially obscuring actual runtime errors and complicating debugging processes. This fix enhances the clarity of error messages during test failures and ensures compliance with standard C format string conventions. Signed-off-by: angquan yu <angquan21(a)gmail.com> --- tools/testing/selftests/breakpoints/step_after_suspend_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c index 2cf6f10ab..b8703c499 100644 --- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c +++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c @@ -89,7 +89,7 @@ int run_test(int cpu) wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { - ksft_print_msg("waitpid() failed: $s\n", strerror(errno)); + ksft_print_msg("waitpid() failed: %s\n", strerror(errno)); return KSFT_FAIL; } if (WIFEXITED(status)) { -- 2.39.2

1 year, 7 months

1
0
0 0

[PATCH] [PATCH,breakpoints] selftests/breakpoints: Fix format specifier in ksft_print_msg in step_after_suspend_test.c

by angquan yu

From: angquan yu <angquan21(a)gmail.com> In the function 'tools/testing/selftests/breakpoints/run_test' within step_after_suspend_test.c, the ksft_print_msg function call incorrectly used '$s' as a format specifier. This commit corrects this typo to use the proper '%s' format specifier, ensuring the error message from waitpid() is correctly displayed. The issue manifested as a compilation warning (too many arguments for format [-Wformat-extra-args]), potentially obscuring actual runtime errors and complicating debugging processes. This fix enhances the clarity of error messages during test failures and ensures compliance with standard C format string conventions. Signed-off-by: angquan yu <angquan21(a)gmail.com> --- tools/testing/selftests/breakpoints/step_after_suspend_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c index 2cf6f10ab..b8703c499 100644 --- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c +++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c @@ -89,7 +89,7 @@ int run_test(int cpu) wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { - ksft_print_msg("waitpid() failed: $s\n", strerror(errno)); + ksft_print_msg("waitpid() failed: %s\n", strerror(errno)); return KSFT_FAIL; } if (WIFEXITED(status)) { -- 2.39.2

1 year, 7 months

1
0
0 0

[PATCH bpf-next 0/4] selftests/bpf: Update multiple prog_tests to use ASSERT_ macros

by Yuran Pereira

Multiple files/programs in `tools/testing/selftests/bpf/prog_tests/` still heavily use the `CHECK` macro, even when better `ASSERT_` alternatives are available. As it was already pointed out by Yonghong Song [1] in the bpf selftests the use of the ASSERT_* series of macros is preferred over the CHECK macro. This patchset replaces the usage of `CHECK(` macros to the equivalent `ASSERT_` family of macros in the following prog_tests: - bind_perm.c - bpf_obj_id.c - bpf_tcp_ca.c - vmlinux.c [1] https://lore.kernel.org/lkml/0a142924-633c-44e6-9a92-2dc019656bf2@linux.dev Yuran Pereira (4): Replaces the usage of CHECK calls for ASSERTs in bpf_tcp_ca Replaces the usage of CHECK calls for ASSERTs in bind_perm Replaces the usage of CHECK calls for ASSERTs in bpf_obj_id selftests/bpf: Replaces the usage of CHECK calls for ASSERTs in vmlinux .../selftests/bpf/prog_tests/bind_perm.c | 6 +- .../selftests/bpf/prog_tests/bpf_obj_id.c | 204 +++++++----------- .../selftests/bpf/prog_tests/bpf_tcp_ca.c | 48 ++--- .../selftests/bpf/prog_tests/vmlinux.c | 16 +- 4 files changed, 105 insertions(+), 169 deletions(-) -- 2.25.1

1 year, 7 months

2
6
0 0

[PATCH net-next] net: ctnetlink: support filtering by zone

by Felix Huettner

conntrack zones are heavily used by tools like openvswitch to run multiple virtual "routers" on a single machine. In this context each conntrack zone matches to a single router, thereby preventing overlapping IPs from becoming issues. In these systems it is common to operate on all conntrack entries of a given zone, e.g. to delete them when a router is deleted. Previously this required these tools to dump the full conntrack table and filter out the relevant entries in userspace potentially causing performance issues. To do this we reuse the existing CTA_ZONE attribute. This was previous parsed but not used during dump and flush requests. Now if CTA_ZONE is set we filter these operations based on the provided zone. However this means that users that previously passed CTA_ZONE will experience a difference in functionality. Alternatively CTA_FILTER could have been used for the same functionality. However it is not yet supported during flush requests and is only available when using AF_INET or AF_INET6. Co-developed-by: Luca Czesla <luca.czesla(a)mail.schwarz> Signed-off-by: Luca Czesla <luca.czesla(a)mail.schwarz> Co-developed-by: Max Lamprecht <max.lamprecht(a)mail.schwarz> Signed-off-by: Max Lamprecht <max.lamprecht(a)mail.schwarz> Signed-off-by: Felix Huettner <felix.huettner(a)mail.schwarz> --- net/netfilter/nf_conntrack_netlink.c | 15 +- tools/testing/selftests/netfilter/.gitignore | 2 + tools/testing/selftests/netfilter/Makefile | 3 +- .../netfilter/conntrack_dump_flush.c | 430 ++++++++++++++++++ 4 files changed, 444 insertions(+), 6 deletions(-) create mode 100644 tools/testing/selftests/netfilter/conntrack_dump_flush.c diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index fb0ae15e96df..4e9133f61251 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -992,13 +992,13 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) if (err) goto err_filter; + err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); + if (err < 0) + goto err_filter; + if (!cda[CTA_FILTER]) return filter; - err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); - if (err < 0) - goto err_filter; - err = ctnetlink_parse_filter(cda[CTA_FILTER], filter); if (err < 0) goto err_filter; @@ -1043,7 +1043,8 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda) { - return family || cda[CTA_MARK] || cda[CTA_FILTER] || cda[CTA_STATUS]; + return family || cda[CTA_MARK] || cda[CTA_FILTER] || cda[CTA_STATUS] || + cda[CTA_ZONE]; } static int ctnetlink_start(struct netlink_callback *cb) @@ -1148,6 +1149,10 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) if (filter->family && nf_ct_l3num(ct) != filter->family) goto ignore_entry; + if (filter->zone.id != NF_CT_DEFAULT_ZONE_ID && + !nf_ct_zone_equal_any(ct, &filter->zone)) + goto ignore_entry; + if (filter->orig_flags) { tuple = nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL); if (!ctnetlink_filter_match_tuple(&filter->orig, tuple, diff --git a/tools/testing/selftests/netfilter/.gitignore b/tools/testing/selftests/netfilter/.gitignore index 4b2928e1c19d..c2229b3e40d4 100644 --- a/tools/testing/selftests/netfilter/.gitignore +++ b/tools/testing/selftests/netfilter/.gitignore @@ -2,3 +2,5 @@ nf-queue connect_close audit_logread +conntrack_dump_flush +sctp_collision diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index bced422b78f7..db27153eb4a0 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -14,6 +14,7 @@ HOSTPKG_CONFIG := pkg-config CFLAGS += $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null) LDLIBS += $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) -TEST_GEN_FILES = nf-queue connect_close audit_logread sctp_collision +TEST_GEN_FILES = nf-queue connect_close audit_logread sctp_collision \ + conntrack_dump_flush include ../lib.mk diff --git a/tools/testing/selftests/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/netfilter/conntrack_dump_flush.c new file mode 100644 index 000000000000..61bfb2be468a --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_dump_flush.c @@ -0,0 +1,430 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <time.h> +#include <libmnl/libmnl.h> +#include <netinet/ip.h> + +#include <linux/netlink.h> +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> +#include <linux/netfilter/nf_conntrack_tcp.h> +#include "../kselftest_harness.h" + +#define TEST_ZONE_ID 123 +#define CTA_FILTER_F_CTA_TUPLE_ZONE (1 << 2) + +static int reply_counter; + +static int build_cta_tuple_v4(struct nlmsghdr *nlh, int type, + uint32_t src_ip, uint32_t dst_ip, + uint16_t src_port, uint16_t dst_port) +{ + struct nlattr *nest, *nest_ip, *nest_proto; + + nest = mnl_attr_nest_start(nlh, type); + if (!nest) + return -1; + + nest_ip = mnl_attr_nest_start(nlh, CTA_TUPLE_IP); + if (!nest_ip) + return -1; + mnl_attr_put_u32(nlh, CTA_IP_V4_SRC, src_ip); + mnl_attr_put_u32(nlh, CTA_IP_V4_DST, dst_ip); + mnl_attr_nest_end(nlh, nest_ip); + + nest_proto = mnl_attr_nest_start(nlh, CTA_TUPLE_PROTO); + if (!nest_proto) + return -1; + mnl_attr_put_u8(nlh, CTA_PROTO_NUM, 6); + mnl_attr_put_u16(nlh, CTA_PROTO_SRC_PORT, htons(src_port)); + mnl_attr_put_u16(nlh, CTA_PROTO_DST_PORT, htons(dst_port)); + mnl_attr_nest_end(nlh, nest_proto); + + mnl_attr_nest_end(nlh, nest); +} + +static int build_cta_tuple_v6(struct nlmsghdr *nlh, int type, + struct in6_addr src_ip, struct in6_addr dst_ip, + uint16_t src_port, uint16_t dst_port) +{ + struct nlattr *nest, *nest_ip, *nest_proto; + + nest = mnl_attr_nest_start(nlh, type); + if (!nest) + return -1; + + nest_ip = mnl_attr_nest_start(nlh, CTA_TUPLE_IP); + if (!nest_ip) + return -1; + mnl_attr_put(nlh, CTA_IP_V6_SRC, sizeof(struct in6_addr), &src_ip); + mnl_attr_put(nlh, CTA_IP_V6_DST, sizeof(struct in6_addr), &dst_ip); + mnl_attr_nest_end(nlh, nest_ip); + + nest_proto = mnl_attr_nest_start(nlh, CTA_TUPLE_PROTO); + if (!nest_proto) + return -1; + mnl_attr_put_u8(nlh, CTA_PROTO_NUM, 6); + mnl_attr_put_u16(nlh, CTA_PROTO_SRC_PORT, htons(src_port)); + mnl_attr_put_u16(nlh, CTA_PROTO_DST_PORT, htons(dst_port)); + mnl_attr_nest_end(nlh, nest_proto); + + mnl_attr_nest_end(nlh, nest); +} + +static int build_cta_proto(struct nlmsghdr *nlh) +{ + struct nlattr *nest, *nest_proto; + + nest = mnl_attr_nest_start(nlh, CTA_PROTOINFO); + if (!nest) + return -1; + + nest_proto = mnl_attr_nest_start(nlh, CTA_PROTOINFO_TCP); + if (!nest_proto) + return -1; + mnl_attr_put_u8(nlh, CTA_PROTOINFO_TCP_STATE, TCP_CONNTRACK_ESTABLISHED); + mnl_attr_put_u16(nlh, CTA_PROTOINFO_TCP_FLAGS_ORIGINAL, 0x0a0a); + mnl_attr_put_u16(nlh, CTA_PROTOINFO_TCP_FLAGS_REPLY, 0x0a0a); + mnl_attr_nest_end(nlh, nest_proto); + + mnl_attr_nest_end(nlh, nest); +} + +static int conntrack_data_insert(struct mnl_socket *sock, struct nlmsghdr *nlh, + uint16_t zone) +{ + char buf[MNL_SOCKET_BUFFER_SIZE]; + struct nlmsghdr *rplnlh; + unsigned int portid; + int err, ret; + + portid = mnl_socket_get_portid(sock); + + ret = build_cta_proto(nlh); + if (ret < 0) { + perror("build_cta_proto"); + return -1; + } + mnl_attr_put_u32(nlh, CTA_TIMEOUT, htonl(20000)); + mnl_attr_put_u16(nlh, CTA_ZONE, htons(zone)); + + if (mnl_socket_sendto(sock, nlh, nlh->nlmsg_len) < 0) { + perror("mnl_socket_sendto"); + return -1; + } + + ret = mnl_socket_recvfrom(sock, buf, MNL_SOCKET_BUFFER_SIZE); + if (ret < 0) { + perror("mnl_socket_recvfrom"); + return ret; + } + + ret = mnl_cb_run(buf, ret, nlh->nlmsg_seq, portid, NULL, NULL); + if (ret < 0) { + if (errno == EEXIST) { + /* The entries are probably still there from a previous + * run. So we are good + */ + return 0; + } + perror("mnl_cb_run"); + return ret; + } + + return 0; +} + +static int conntracK_data_generate_v4(struct mnl_socket *sock, uint32_t src_ip, + uint32_t dst_ip, uint16_t zone) +{ + char buf[MNL_SOCKET_BUFFER_SIZE]; + struct nlmsghdr *nlh; + struct nfgenmsg *nfh; + int ret; + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = (NFNL_SUBSYS_CTNETLINK << 8) | IPCTNL_MSG_CT_NEW; + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | + NLM_F_ACK | NLM_F_EXCL; + nlh->nlmsg_seq = time(NULL); + + nfh = mnl_nlmsg_put_extra_header(nlh, sizeof(struct nfgenmsg)); + nfh->nfgen_family = AF_INET; + nfh->version = NFNETLINK_V0; + nfh->res_id = 0; + + ret = build_cta_tuple_v4(nlh, CTA_TUPLE_ORIG, src_ip, dst_ip, 12345, 443); + if (ret < 0) { + perror("build_cta_tuple_v4"); + return ret; + } + ret = build_cta_tuple_v4(nlh, CTA_TUPLE_REPLY, dst_ip, src_ip, 443, 12345); + if (ret < 0) { + perror("build_cta_tuple_v4"); + return ret; + } + return conntrack_data_insert(sock, nlh, zone); +} + +static int conntracK_data_generate_v6(struct mnl_socket *sock, + struct in6_addr src_ip, + struct in6_addr dst_ip, + uint16_t zone) +{ + char buf[MNL_SOCKET_BUFFER_SIZE]; + struct nlmsghdr *nlh; + struct nfgenmsg *nfh; + int ret; + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = (NFNL_SUBSYS_CTNETLINK << 8) | IPCTNL_MSG_CT_NEW; + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | + NLM_F_ACK | NLM_F_EXCL; + nlh->nlmsg_seq = time(NULL); + + nfh = mnl_nlmsg_put_extra_header(nlh, sizeof(struct nfgenmsg)); + nfh->nfgen_family = AF_INET6; + nfh->version = NFNETLINK_V0; + nfh->res_id = 0; + + ret = build_cta_tuple_v6(nlh, CTA_TUPLE_ORIG, src_ip, dst_ip, + 12345, 443); + if (ret < 0) { + perror("build_cta_tuple_v6"); + return ret; + } + ret = build_cta_tuple_v6(nlh, CTA_TUPLE_REPLY, dst_ip, src_ip, + 12345, 443); + if (ret < 0) { + perror("build_cta_tuple_v6"); + return ret; + } + return conntrack_data_insert(sock, nlh, zone); +} + +static int count_entries(const struct nlmsghdr *nlh, void *data) +{ + reply_counter++; +} + +static int conntracK_count_zone(struct mnl_socket *sock, uint16_t zone) +{ + char buf[MNL_SOCKET_BUFFER_SIZE]; + struct nlmsghdr *nlh, *rplnlh; + struct nfgenmsg *nfh; + struct nlattr *nest; + unsigned int portid; + int err, ret; + + portid = mnl_socket_get_portid(sock); + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = (NFNL_SUBSYS_CTNETLINK << 8) | IPCTNL_MSG_CT_GET; + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP; + nlh->nlmsg_seq = time(NULL); + + nfh = mnl_nlmsg_put_extra_header(nlh, sizeof(struct nfgenmsg)); + nfh->nfgen_family = AF_UNSPEC; + nfh->version = NFNETLINK_V0; + nfh->res_id = 0; + + mnl_attr_put_u16(nlh, CTA_ZONE, htons(zone)); + + ret = mnl_socket_sendto(sock, nlh, nlh->nlmsg_len); + if (ret < 0) { + perror("mnl_socket_sendto"); + return ret; + } + + reply_counter = 0; + ret = mnl_socket_recvfrom(sock, buf, MNL_SOCKET_BUFFER_SIZE); + while (ret > 0) { + ret = mnl_cb_run(buf, ret, nlh->nlmsg_seq, portid, + count_entries, NULL); + if (ret <= MNL_CB_STOP) + break; + + ret = mnl_socket_recvfrom(sock, buf, MNL_SOCKET_BUFFER_SIZE); + } + if (ret < 0) { + perror("mnl_socket_recvfrom"); + return ret; + } + + return reply_counter; +} + +static int conntrack_flush_zone(struct mnl_socket *sock, uint16_t zone) +{ + char buf[MNL_SOCKET_BUFFER_SIZE]; + struct nlmsghdr *nlh, *rplnlh; + struct nfgenmsg *nfh; + struct nlattr *nest; + unsigned int portid; + int err, ret; + + portid = mnl_socket_get_portid(sock); + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = (NFNL_SUBSYS_CTNETLINK << 8) | IPCTNL_MSG_CT_DELETE; + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + nlh->nlmsg_seq = time(NULL); + + nfh = mnl_nlmsg_put_extra_header(nlh, sizeof(struct nfgenmsg)); + nfh->nfgen_family = AF_UNSPEC; + nfh->version = NFNETLINK_V0; + nfh->res_id = 0; + + mnl_attr_put_u16(nlh, CTA_ZONE, htons(zone)); + + ret = mnl_socket_sendto(sock, nlh, nlh->nlmsg_len); + if (ret < 0) { + perror("mnl_socket_sendto"); + return ret; + } + + ret = mnl_socket_recvfrom(sock, buf, MNL_SOCKET_BUFFER_SIZE); + if (ret < 0) { + perror("mnl_socket_recvfrom"); + return ret; + } + + ret = mnl_cb_run(buf, ret, nlh->nlmsg_seq, portid, NULL, NULL); + if (ret < 0) { + perror("mnl_cb_run"); + return ret; + } + + return 0; +} + +FIXTURE(conntrack_dump_flush) +{ + struct mnl_socket *sock; +}; + +FIXTURE_SETUP(conntrack_dump_flush) +{ + struct in6_addr src, dst; + int ret; + + self->sock = mnl_socket_open(NETLINK_NETFILTER); + if (!self->sock) { + perror("mnl_socket_open"); + exit(EXIT_FAILURE); + } + + if (mnl_socket_bind(self->sock, 0, MNL_SOCKET_AUTOPID) < 0) { + perror("mnl_socket_bind"); + exit(EXIT_FAILURE); + } + + ret = conntracK_count_zone(self->sock, TEST_ZONE_ID); + if (ret < 0 && errno == EPERM) + SKIP(return, "Needs to be run as root"); + else if (ret < 0 && errno == EOPNOTSUPP) + SKIP(return, "Kernel does not seem to support conntrack zones"); + + ret = conntracK_data_generate_v4(self->sock, 0xf0f0f0f0, 0xf1f1f1f1, + TEST_ZONE_ID); + EXPECT_EQ(ret, 0); + ret = conntracK_data_generate_v4(self->sock, 0xf2f2f2f2, 0xf3f3f3f3, + TEST_ZONE_ID + 1); + EXPECT_EQ(ret, 0); + ret = conntracK_data_generate_v4(self->sock, 0xf4f4f4f4, 0xf5f5f5f5, + TEST_ZONE_ID + 2); + EXPECT_EQ(ret, 0); + + src = (struct in6_addr) {{ + .__u6_addr32 = { + 0xb80d0120, + 0x00000000, + 0x00000000, + 0x01000000 + } + }}; + dst = (struct in6_addr) {{ + .__u6_addr32 = { + 0xb80d0120, + 0x00000000, + 0x00000000, + 0x02000000 + } + }}; + ret = conntracK_data_generate_v6(self->sock, src, dst, + TEST_ZONE_ID); + EXPECT_EQ(ret, 0); + src = (struct in6_addr) {{ + .__u6_addr32 = { + 0xb80d0120, + 0x00000000, + 0x00000000, + 0x03000000 + } + }}; + dst = (struct in6_addr) {{ + .__u6_addr32 = { + 0xb80d0120, + 0x00000000, + 0x00000000, + 0x04000000 + } + }}; + ret = conntracK_data_generate_v6(self->sock, src, dst, + TEST_ZONE_ID + 1); + EXPECT_EQ(ret, 0); + src = (struct in6_addr) {{ + .__u6_addr32 = { + 0xb80d0120, + 0x00000000, + 0x00000000, + 0x05000000 + } + }}; + dst = (struct in6_addr) {{ + .__u6_addr32 = { + 0xb80d0120, + 0x00000000, + 0x00000000, + 0x06000000 + } + }}; + ret = conntracK_data_generate_v6(self->sock, src, dst, + TEST_ZONE_ID + 2); + EXPECT_EQ(ret, 0); + + ret = conntracK_count_zone(self->sock, TEST_ZONE_ID); + EXPECT_GE(ret, 2); + if (ret > 2) + SKIP(return, "kernel does not support filtering by zone"); +} + +FIXTURE_TEARDOWN(conntrack_dump_flush) +{ +} + +TEST_F(conntrack_dump_flush, test_dump_by_zone) +{ + int ret; + + ret = conntracK_count_zone(self->sock, TEST_ZONE_ID); + EXPECT_EQ(ret, 2); +} + +TEST_F(conntrack_dump_flush, test_flush_by_zone) +{ + int ret; + + ret = conntrack_flush_zone(self->sock, TEST_ZONE_ID); + EXPECT_EQ(ret, 0); + ret = conntracK_count_zone(self->sock, TEST_ZONE_ID); + EXPECT_EQ(ret, 0); + ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 1); + EXPECT_EQ(ret, 2); + ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 2); + EXPECT_EQ(ret, 2); +} + +TEST_HARNESS_MAIN base-commit: 18de1e517ed37ebaf33e771e46faf052e966e163 -- 2.42.0 Diese E Mail enthält möglicherweise vertrauliche Inhalte und ist nur für die Verwertung durch den vorgesehenen Empfänger bestimmt. Sollten Sie nicht der vorgesehene Empfänger sein, setzen Sie den Absender bitte unverzüglich in Kenntnis und löschen diese E Mail. Hinweise zum Datenschutz finden Sie hier<https://www.datenschutz.schwarz>. This e-mail may contain confidential content and is intended only for the specified recipient/s. If you are not the intended recipient, please inform the sender immediately and delete this e-mail. Information on data protection can be found here<https://www.datenschutz.schwarz>.

1 year, 7 months

1
0
0 0

Re: [PATCH net-next 14/14] selftests: mlxsw: Add PCI reset test

by Simon Horman

+ linux-kselftest ML, Shuah Khan On Wed, Nov 15, 2023 at 01:17:23PM +0100, Petr Machata wrote: > From: Ido Schimmel <idosch(a)nvidia.com> > > Test that PCI reset works correctly by verifying that only the expected > reset methods are supported and that after issuing the reset the ifindex > of the port changes. > > Signed-off-by: Ido Schimmel <idosch(a)nvidia.com> > Reviewed-by: Petr Machata <petrm(a)nvidia.com> > Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Simon Horman <horms(a)kernel.org> > --- > .../selftests/drivers/net/mlxsw/pci_reset.sh | 58 +++++++++++++++++++ > 1 file changed, 58 insertions(+) > create mode 100755 tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh > > diff --git a/tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh b/tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh > new file mode 100755 > index 000000000000..fe0343b95e6c > --- /dev/null > +++ b/tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh > @@ -0,0 +1,58 @@ > +#!/bin/bash > +# SPDX-License-Identifier: GPL-2.0 > +# > +# Test that PCI reset works correctly by verifying that only the expected reset > +# methods are supported and that after issuing the reset the ifindex of the > +# port changes. > + > +lib_dir=$(dirname $0)/../../../net/forwarding > + > +ALL_TESTS=" > + pci_reset_test > +" > +NUM_NETIFS=1 > +source $lib_dir/lib.sh > +source $lib_dir/devlink_lib.sh > + > +pci_reset_test() > +{ > + RET=0 > + > + local bus=$(echo $DEVLINK_DEV | cut -d '/' -f 1) > + local bdf=$(echo $DEVLINK_DEV | cut -d '/' -f 2) > + > + if [ $bus != "pci" ]; then > + check_err 1 "devlink device is not a PCI device" > + log_test "pci reset" > + return > + fi > + > + if [ ! -f /sys/bus/pci/devices/$bdf/reset_method ]; then > + check_err 1 "reset is not supported" > + log_test "pci reset" > + return > + fi > + > + [[ $(cat /sys/bus/pci/devices/$bdf/reset_method) == "bus" ]] > + check_err $? "only \"bus\" reset method should be supported" > + > + local ifindex_pre=$(ip -j link show dev $swp1 | jq '.[]["ifindex"]') > + > + echo 1 > /sys/bus/pci/devices/$bdf/reset > + check_err $? "reset failed" > + > + # Wait for udev to rename newly created netdev. > + udevadm settle > + > + local ifindex_post=$(ip -j link show dev $swp1 | jq '.[]["ifindex"]') > + > + [[ $ifindex_pre != $ifindex_post ]] > + check_err $? "reset not performed" > + > + log_test "pci reset" > +} > + > +swp1=${NETIFS[p1]} > +tests_run > + > +exit $EXIT_STATUS > -- > 2.41.0 >

1 year, 7 months

1
0
0 0

Re: [RFC 7/7] vfio: Add vfio_register_pasid_iommu_dev()

by Yi Liu

On 2023/11/16 13:12, Cao, Yahui wrote: > > On 10/9/2023 4:51 PM, Yi Liu wrote: >> From: Kevin Tian<kevin.tian(a)intel.com> >> >> This adds vfio_register_pasid_iommu_dev() for device driver to register >> virtual devices which are isolated per PASID in physical IOMMU. The major >> usage is for the SIOV devices which allows device driver to tag the DMAs >> out of virtual devices within it with different PASIDs. >> >> For a given vfio device, VFIO core creates both group user interface and >> device user interface (device cdev) if configured. However, for the virtual >> devices backed by PASID of the device, VFIO core shall only create device >> user interface as there is no plan to support such devices in the legacy >> vfio_iommu drivers which is a must if creating group user interface for >> such virtual devices. This introduces a VFIO_PASID_IOMMU group type for >> the device driver to register PASID virtual devices, and provides a wrapper >> API for it. In particular no iommu group (neither fake group or real group) >> exists per PASID, hence no group interface for this type. >> >> Signed-off-by: Kevin Tian<kevin.tian(a)intel.com> >> Signed-off-by: Yi Liu<yi.l.liu(a)intel.com> >> --- >> drivers/vfio/group.c | 18 ++++++++++++++++++ >> drivers/vfio/vfio.h | 8 ++++++++ >> drivers/vfio/vfio_main.c | 10 ++++++++++ >> include/linux/vfio.h | 1 + >> 4 files changed, 37 insertions(+) >> >> ... >> ... >> +/* >> + * Register a virtual device with IOMMU pasid protection. The user of >> + * this device can trigger DMA as long as all of its outgoing DMAs are >> + * always tagged with a pasid. >> + */ >> +int vfio_register_pasid_iommu_dev(struct vfio_device *device) >> +{ >> + return __vfio_register_dev(device, VFIO_PASID_IOMMU); >> +} >> + > > > Missing symbol export here. > fixed. -- Regards, Yi Liu

1 year, 7 months

1
0
0 0

[PATCH v1] KVM: selftests: Initalize sem_vcpu_[cont|stop] before each test in dirty_log_test

by Shaoqin Huang

When execute the dirty_log_test on some aarch64 machine, it sometimes trigger the ASSERT: ==== Test Assertion Failure ==== dirty_log_test.c:384: dirty_ring_vcpu_ring_full pid=14854 tid=14854 errno=22 - Invalid argument 1 0x00000000004033eb: dirty_ring_collect_dirty_pages at dirty_log_test.c:384 2 0x0000000000402d27: log_mode_collect_dirty_pages at dirty_log_test.c:505 3 (inlined by) run_test at dirty_log_test.c:802 4 0x0000000000403dc7: for_each_guest_mode at guest_modes.c:100 5 0x0000000000401dff: main at dirty_log_test.c:941 (discriminator 3) 6 0x0000ffff9be173c7: ?? ??:0 7 0x0000ffff9be1749f: ?? ??:0 8 0x000000000040206f: _start at ??:? Didn't continue vcpu even without ring full The dirty_log_test fails when execute the dirty-ring test, this is because the sem_vcpu_cont and the sem_vcpu_stop is non-zero value when execute the dirty_ring_collect_dirty_pages() function. When those two sem_t variables are non-zero, the dirty_ring_wait_vcpu() at the beginning of the dirty_ring_collect_dirty_pages() will not wait for the vcpu to stop, but continue to execute the following code. In this case, before vcpu stop, if the dirty_ring_vcpu_ring_full is true, and the dirty_ring_collect_dirty_pages() has passed the check for the dirty_ring_vcpu_ring_full but hasn't execute the check for the continued_vcpu, the vcpu stop, and set the dirty_ring_vcpu_ring_full to false. Then dirty_ring_collect_dirty_pages() will trigger the ASSERT. Why sem_vcpu_cont and sem_vcpu_stop can be non-zero value? It's because the dirty_ring_before_vcpu_join() execute the sem_post(&sem_vcpu_cont) at the end of each dirty-ring test. It can cause two cases: 1. sem_vcpu_cont be non-zero. When we set the host_quit to be true, the vcpu_worker directly see the host_quit to be true, it quit. So the log_mode_before_vcpu_join() function will set the sem_vcpu_cont to 1, since the vcpu_worker has quit, it won't consume it. 2. sem_vcpu_stop be non-zero. When we set the host_quit to be true, the vcpu_worker has entered the guest state, the next time it exit from guest state, it will set the sem_vcpu_stop to 1, and then see the host_quit, no one will consume the sem_vcpu_stop. When execute more and more dirty-ring tests, the sem_vcpu_cont and sem_vcpu_stop can be larger and larger, which makes many code paths don't wait for the sem_t. Thus finally cause the problem. Fix this problem is easy, simply initialize the sem_t before every test. Thus whatever the state previous test left, it won't interfere the next test. Signed-off-by: Shaoqin Huang <shahuang(a)redhat.com> --- tools/testing/selftests/kvm/dirty_log_test.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 936f3a8d1b83..23b179534c0b 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -726,6 +726,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) return; } + sem_init(&sem_vcpu_stop, 0, 0); + sem_init(&sem_vcpu_cont, 0, 0); + /* * We reserve page table for 2 times of extra dirty mem which * will definitely cover the original (1G+) test range. Here @@ -871,9 +874,6 @@ int main(int argc, char *argv[]) int opt, i; sigset_t sigset; - sem_init(&sem_vcpu_stop, 0, 0); - sem_init(&sem_vcpu_cont, 0, 0); - guest_modes_append_default(); while ((opt = getopt(argc, argv, "c:hi:I:p:m:M:")) != -1) { -- 2.40.1

1 year, 7 months

2
2
0 0

[PATCH net-next v3] selftests/net: synchronize udpgro tests' tx and rx connection

by Lucas Karpinski

The sockets used by udpgso_bench_tx aren't always ready when udpgso_bench_tx transmits packets. This issue is more prevalent in -rt kernels, but can occur in both. Replace the hacky sleep calls with a function that checks whether the ports in the namespace are ready for use. Suggested-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Lucas Karpinski <lkarpins(a)redhat.com> --- https://lore.kernel.org/all/6ceki76bcv7qz6de5rxc26ot6aezdmeoz2g4ubtve7qwozm… v3: - moved redundant code to net_helper.sh - replaced awk with grep - changed commit message to specify udpgro - added target tree v2: - applied synchronization method suggested by Paolo - changed commit message to code tools/testing/selftests/net/net_helper.sh | 22 +++++++++++++++++++ tools/testing/selftests/net/udpgro.sh | 13 +++++------ tools/testing/selftests/net/udpgro_bench.sh | 5 +++-- tools/testing/selftests/net/udpgro_frglist.sh | 5 +++-- 4 files changed, 34 insertions(+), 11 deletions(-) create mode 100755 tools/testing/selftests/net/net_helper.sh diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh new file mode 100755 index 000000000000..4fe0befa13fb --- /dev/null +++ b/tools/testing/selftests/net/net_helper.sh @@ -0,0 +1,22 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Helper functions + +wait_local_port_listen() +{ + local listener_ns="${1}" + local port="${2}" + local protocol="${3}" + local port_hex + local i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + if ip netns exec "${listener_ns}" cat /proc/net/"${protocol}"* | \ + grep -q "${port_hex}"; then + break + fi + sleep 0.1 + done +} diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index 0c743752669a..af5dc57c8ce9 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -3,6 +3,8 @@ # # Run a series of udpgro functional tests. +source net_helper.sh + readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" BPF_FILE="../bpf/xdp_dummy.bpf.o" @@ -51,8 +53,7 @@ run_one() { echo "ok" || \ echo "failed" & - # Hack: let bg programs complete the startup - sleep 0.2 + wait_local_port_listen ${PEER_NS} 8000 udp ./udpgso_bench_tx ${tx_args} ret=$? wait $(jobs -p) @@ -97,7 +98,7 @@ run_one_nat() { echo "ok" || \ echo "failed"& - sleep 0.1 + wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} ret=$? kill -INT $pid @@ -118,11 +119,9 @@ run_one_2sock() { echo "ok" || \ echo "failed" & - # Hack: let bg programs complete the startup - sleep 0.2 + wait_local_port_listen "${PEER_NS}" 12345 udp ./udpgso_bench_tx ${tx_args} -p 12345 - sleep 0.1 - # first UDP GSO socket should be closed at this point + wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} ret=$? wait $(jobs -p) diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh index 894972877e8b..cb664679b434 100755 --- a/tools/testing/selftests/net/udpgro_bench.sh +++ b/tools/testing/selftests/net/udpgro_bench.sh @@ -3,6 +3,8 @@ # # Run a series of udpgro benchmarks +source net_helper.sh + readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" BPF_FILE="../bpf/xdp_dummy.bpf.o" @@ -40,8 +42,7 @@ run_one() { ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r & - # Hack: let bg programs complete the startup - sleep 0.2 + wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} } diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index 0a6359bed0b9..dd47fa96f6b3 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -3,6 +3,8 @@ # # Run a series of udpgro benchmarks +source net_helper.sh + readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" BPF_FILE="../bpf/xdp_dummy.bpf.o" @@ -45,8 +47,7 @@ run_one() { echo ${rx_args} ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & - # Hack: let bg programs complete the startup - sleep 0.2 + wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} } -- 2.41.0

1 year, 7 months

3
2
0 0

[PATCH RFC 0/3] selftests/nolibc: introduce new test harness

by Thomas Weißschuh

This series introduces a new test harness for nolibc. It is similar to kselftest-harness and google test. More information in patch 1. This is an RFC to gather feedback, especially if it can be integrated with the original kselftest-harness somehow. Note: When run under qemu-loongarch64 8.1.2 the test "mmap_munmap_good" fails. This is a bug in qemu-user and already fixed there on master. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- Thomas Weißschuh (3): selftests/nolibc: add custom test harness selftests/nolibc: migrate startup tests to new harness selftests/nolibc: migrate vfprintf tests to new harness tools/testing/selftests/nolibc/nolibc-harness.h | 269 ++++++++++++++++++++++++ tools/testing/selftests/nolibc/nolibc-test.c | 180 ++++++++-------- 2 files changed, 353 insertions(+), 96 deletions(-) --- base-commit: d38d5366cb1c51f687b4720277adee97074b22e9 change-id: 20231105-nolibc-harness-28c59029d7a5 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

1 year, 7 months

2
9
0 0

[PATCH v2] KVM: arm64: selftests: Clean up the GIC[D,R]_BASE_GPA

by Shaoqin Huang

The GIC[D,R]_BASE_GPA has been defined in multiple files with the same value, define it in one place to make the code clean. Signed-off-by: Shaoqin Huang <shahuang(a)redhat.com> --- v1->v2: - Clean up the vpmu_counter_access.c. --- tools/testing/selftests/kvm/aarch64/arch_timer.c | 3 --- tools/testing/selftests/kvm/aarch64/vgic_irq.c | 3 --- tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c | 3 --- tools/testing/selftests/kvm/dirty_log_perf_test.c | 3 --- tools/testing/selftests/kvm/include/aarch64/vgic.h | 3 +++ 5 files changed, 3 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index 274b8465b42a..818854007bfd 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -59,9 +59,6 @@ static struct test_args test_args = { #define msecs_to_usecs(msec) ((msec) * 1000LL) -#define GICD_BASE_GPA 0x8000000ULL -#define GICR_BASE_GPA 0x80A0000ULL - enum guest_stage { GUEST_STAGE_VTIMER_CVAL = 1, GUEST_STAGE_VTIMER_TVAL, diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c index 2e64b4856e38..a48aff110fb6 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c @@ -19,9 +19,6 @@ #include "gic_v3.h" #include "vgic.h" -#define GICD_BASE_GPA 0x08000000ULL -#define GICR_BASE_GPA 0x080A0000ULL - /* * Stores the user specified args; it's passed to the guest and to every test * function. diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c index 5ea78986e665..325a8ead0660 100644 --- a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c +++ b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c @@ -421,9 +421,6 @@ static void guest_code(uint64_t expected_pmcr_n) GUEST_DONE(); } -#define GICD_BASE_GPA 0x8000000ULL -#define GICR_BASE_GPA 0x80A0000ULL - /* Create a VM that has one vCPU with PMUv3 configured. */ static void create_vpmu_vm(void *guest_code) { diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index d374dbcf9a53..4971e8f77a0a 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -22,9 +22,6 @@ #ifdef __aarch64__ #include "aarch64/vgic.h" -#define GICD_BASE_GPA 0x8000000ULL -#define GICR_BASE_GPA 0x80A0000ULL - static int gic_fd; static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus) diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/aarch64/vgic.h index 0ac6f05c63f9..9dbb342fd808 100644 --- a/tools/testing/selftests/kvm/include/aarch64/vgic.h +++ b/tools/testing/selftests/kvm/include/aarch64/vgic.h @@ -33,4 +33,7 @@ void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu); #define KVM_IRQCHIP_NUM_PINS (1020 - 32) +#define GICD_BASE_GPA 0x08000000ULL +#define GICR_BASE_GPA 0x080A0000ULL + #endif // SELFTEST_KVM_VGIC_H -- 2.40.1

1 year, 7 months

2
2
0 0

[PATCH v3 00/10] iov_iter: kunit: Cleanup, abstraction and more tests

by David Howells

Hi Christian, Can you take this through the filesystem tree? These patches make some changes to the kunit tests previously added for iov_iter testing, in particular adding testing of UBUF/IOVEC iterators and some benchmarking: (1) Clean up a couple of checkpatch style complaints. (2) Consolidate some repeated bits of code into helper functions and use the same struct to represent straight offset/address ranges and partial page lists. (3) Add a function to set up a userspace VM, attach the VM to the kunit testing thread, create an anonymous file, stuff some pages into the file and map the file into the VM to act as a buffer that can be used with UBUF/IOVEC iterators. I map an anonymous file with pages attached rather than using MAP_ANON so that I can check the pages obtained from iov_iter_extract_pages() without worrying about them changing due to swap, migrate, etc.. [?] Is this the best way to do things? Mirroring execve, it requires a number of extra core symbols to be exported. Should this be done in the core code? (4) Add tests for copying into and out of UBUF and IOVEC iterators. (5) Add tests for extracting pages from UBUF and IOVEC iterators. (6) Add tests to benchmark copying 256MiB to UBUF, IOVEC, KVEC, BVEC and XARRAY iterators. (7) Add a test to bencmark copying 256MiB from an xarray that gets decanted into 256-page BVEC iterators to model batching from the pagecache. (8) Add a test to benchmark copying 256MiB through dynamically allocated 256-page bvecs to simulate bio construction. Example benchmarks output: iov_kunit_benchmark_ubuf: avg 4474 uS, stddev 1340 uS iov_kunit_benchmark_iovec: avg 6619 uS, stddev 23 uS iov_kunit_benchmark_kvec: avg 2672 uS, stddev 14 uS iov_kunit_benchmark_bvec: avg 3189 uS, stddev 19 uS iov_kunit_benchmark_bvec_split: avg 3403 uS, stddev 8 uS iov_kunit_benchmark_xarray: avg 3709 uS, stddev 7 uS I've pushed the patches here also: https://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs.git/log/?… David Changes ======= ver #3) - #include <linux/personality.h> to get READ_IMPLIES_EXEC. - Add a test to benchmark decanting an xarray into bio_vecs. ver #2) - Use MAP_ANON to make the user buffer if we don't want a list of pages. - KUNIT_ASSERT_NOT_ERR_OR_NULL() doesn't like __user pointers as the condition, so cast. - Make the UBUF benchmark loop, doing an iterator per page so that the overhead from the iterator code is not negligible. - Make the KVEC benchmark use an iovec per page so that the iteration is not not negligible. - Switch the benchmarking to use copy_from_iter() so that only a single page is needed in the userspace buffer (as it can be shared R/O), not 256MiB's worth. Link: https://lore.kernel.org/r/20230914221526.3153402-1-dhowells@redhat.com/ # v1 Link: https://lore.kernel.org/r/20230920130400.203330-1-dhowells@redhat.com/ # v2 Link: https://lore.kernel.org/r/20230922113038.1135236-1-dhowells@redhat.com/ # v3 David Howells (10): iov_iter: Fix some checkpatch complaints in kunit tests iov_iter: Consolidate some of the repeated code into helpers iov_iter: Consolidate the test vector struct in the kunit tests iov_iter: Consolidate bvec pattern checking iov_iter: Create a function to prepare userspace VM for UBUF/IOVEC tests iov_iter: Add copy kunit tests for ITER_UBUF and ITER_IOVEC iov_iter: Add extract kunit tests for ITER_UBUF and ITER_IOVEC iov_iter: Add benchmarking kunit tests iov_iter: Add kunit to benchmark decanting of xarray to bvec iov_iter: Add benchmarking kunit tests for UBUF/IOVEC arch/s390/kernel/vdso.c | 1 + fs/anon_inodes.c | 1 + kernel/fork.c | 2 + lib/kunit_iov_iter.c | 1317 +++++++++++++++++++++++++++++++++------ mm/mmap.c | 1 + mm/util.c | 3 + 6 files changed, 1139 insertions(+), 186 deletions(-)

1 year, 7 months

3
16
0 0

[PATCH v3 0/5] cgroup/cpuset: Improve CPU isolation in isolated partitions

by Waiman Long

v3: - Break out a separate patch to make workqueue_set_unbound_cpumask() static and move it down to the CONFIG_SYSFS section. - Remove the "__DEBUG__." prefix and the CFTYPE_DEBUG flag from the new root only cpuset.cpus.isolated control files and update the test accordingly. v2: - Add 2 read-only workqueue sysfs files to expose the user requested cpumask as well as the isolated CPUs to be excluded from wq_unbound_cpumask. - Ensure that caller of the new workqueue_unbound_exclude_cpumask() hold cpus_read_lock. - Update the cpuset code to make sure the cpus_read_lock is held whenever workqueue_unbound_exclude_cpumask() may be called. Isolated cpuset partition can currently be created to contain an exclusive set of CPUs not used in other cgroups and with load balancing disabled to reduce interference from the scheduler. The main purpose of this isolated partition type is to dynamically emulate what can be done via the "isolcpus" boot command line option, specifically the default domain flag. One effect of the "isolcpus" option is to remove the isolated CPUs from the cpumasks of unbound workqueues since running work functions in an isolated CPU can be a major source of interference. Changing the unbound workqueue cpumasks can be done at run time by writing an appropriate cpumask without the isolated CPUs to /sys/devices/virtual/workqueue/cpumask. So one can set up an isolated cpuset partition and then write to the cpumask sysfs file to achieve similar level of CPU isolation. However, this manual process can be error prone. This patch series implements automatic exclusion of isolated CPUs from unbound workqueue cpumasks when an isolated cpuset partition is created and then adds those CPUs back when the isolated partition is destroyed. There are also other places in the kernel that look at the HK_FLAG_DOMAIN cpumask or other HK_FLAG_* cpumasks and exclude the isolated CPUs from certain actions to further reduce interference. CPUs in an isolated cpuset partition will not be able to avoid those interferences yet. That may change in the future as the need arises. Waiman Long (5): workqueue: Make workqueue_set_unbound_cpumask() static workqueue: Add workqueue_unbound_exclude_cpumask() to exclude CPUs from wq_unbound_cpumask selftests/cgroup: Minor code cleanup and reorganization of test_cpuset_prs.sh cgroup/cpuset: Keep track of CPUs in isolated partitions cgroup/cpuset: Take isolated CPUs out of workqueue unbound cpumask Documentation/admin-guide/cgroup-v2.rst | 10 +- include/linux/workqueue.h | 2 +- kernel/cgroup/cpuset.c | 286 +++++++++++++----- kernel/workqueue.c | 139 +++++++-- .../selftests/cgroup/test_cpuset_prs.sh | 216 ++++++++----- 5 files changed, 462 insertions(+), 191 deletions(-) -- 2.39.3

1 year, 7 months

2
7
0 0

[PATCH 1/3] kunit: Add a macro to wrap a deferred action function

by David Gow

KUnit's deferred action API accepts a void(*)(void *) function pointer which is called when the test is exited. However, we very frequently want to use existing functions which accept a single pointer, but which may not be of type void*. While this is probably dodgy enough to be on the wrong side of the C standard, it's been often used for similar callbacks, and gcc's -Wcast-function-type seems to ignore cases where the only difference is the type of the argument, assuming it's compatible (i.e., they're both pointers to data). However, clang 16 has introduced -Wcast-function-type-strict, which no longer permits any deviation in function pointer type. This seems to be because it'd break CFI, which validates the type of function calls. This rather ruins our attempts to cast functions to defer them, and leaves us with a few options. The one we've chosen is to implement a macro which will generate a wrapper function which accepts a void*, and casts the argument to the appropriate type. For example, if you were trying to wrap: void foo_close(struct foo *handle); you could use: KUNIT_DEFINE_ACTION_WRAPPER(kunit_action_foo_close, foo_close, struct foo *); This would create a new kunit_action_foo_close() function, of type kunit_action_t, which could be passed into kunit_add_action() and similar functions. In addition to defining this macro, update KUnit and its tests to use it. Link: https://github.com/ClangBuiltLinux/linux/issues/1750 Signed-off-by: David Gow <davidgow(a)google.com> --- This is a follow-up to the RFC here: https://lore.kernel.org/linux-kselftest/20230915050125.3609689-1-davidgow@g… There's no difference in the macro implementation, just an update to the KUnit tests to use it. This version is intended to complement: https://lore.kernel.org/all/20231106172557.2963-1-rf@opensource.cirrus.com/ There are also two follow-up patches in the series to use this macro in various DRM tests. Hopefully this will solve any CFI issues that show up with KUnit. Thanks, -- David --- include/kunit/resource.h | 9 +++++++++ lib/kunit/kunit-test.c | 5 +---- lib/kunit/test.c | 6 ++++-- 3 files changed, 14 insertions(+), 6 deletions(-) diff --git a/include/kunit/resource.h b/include/kunit/resource.h index c7383e90f5c9..4110e13970dc 100644 --- a/include/kunit/resource.h +++ b/include/kunit/resource.h @@ -390,6 +390,15 @@ void kunit_remove_resource(struct kunit *test, struct kunit_resource *res); /* A 'deferred action' function to be used with kunit_add_action. */ typedef void (kunit_action_t)(void *); +/* We can't cast function pointers to kunit_action_t if CFI is enabled. */ +#define KUNIT_DEFINE_ACTION_WRAPPER(wrapper, orig, arg_type) \ + static void wrapper(void *in) \ + { \ + arg_type arg = (arg_type)in; \ + orig(arg); \ + } + + /** * kunit_add_action() - Call a function when the test ends. * @test: Test case to associate the action with. diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index de2113a58fa0..ee6927c60979 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -538,10 +538,7 @@ static struct kunit_suite kunit_resource_test_suite = { #if IS_BUILTIN(CONFIG_KUNIT_TEST) /* This avoids a cast warning if kfree() is passed direct to kunit_add_action(). */ -static void kfree_wrapper(void *p) -{ - kfree(p); -} +KUNIT_DEFINE_ACTION_WRAPPER(kfree_wrapper, kfree, const void *); static void kunit_log_test(struct kunit *test) { diff --git a/lib/kunit/test.c b/lib/kunit/test.c index f2eb71f1a66c..0308865194bb 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -772,6 +772,8 @@ static struct notifier_block kunit_mod_nb = { }; #endif +KUNIT_DEFINE_ACTION_WRAPPER(kfree_action_wrapper, kfree, const void *) + void *kunit_kmalloc_array(struct kunit *test, size_t n, size_t size, gfp_t gfp) { void *data; @@ -781,7 +783,7 @@ void *kunit_kmalloc_array(struct kunit *test, size_t n, size_t size, gfp_t gfp) if (!data) return NULL; - if (kunit_add_action_or_reset(test, (kunit_action_t *)kfree, data) != 0) + if (kunit_add_action_or_reset(test, kfree_action_wrapper, data) != 0) return NULL; return data; @@ -793,7 +795,7 @@ void kunit_kfree(struct kunit *test, const void *ptr) if (!ptr) return; - kunit_release_action(test, (kunit_action_t *)kfree, (void *)ptr); + kunit_release_action(test, kfree_action_wrapper, (void *)ptr); } EXPORT_SYMBOL_GPL(kunit_kfree); -- 2.42.0.869.gea05f2083d-goog

1 year, 7 months

4
6
0 0

selftests: gpio: crash on arm64

by Naresh Kamboju

Following kernel warnings and crash notices on arm64 Rpi4 device while running selftests: gpio on Linux mainline 6.3.0-rc1 kernel and Linux next. Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> Please refer to test log links for detailed test plan and kernel crash logs. It is reproducible on arm64 juno-r2, Rpi4 and Qualcomm dragonboard 410c and qemu-arm64. Test log: ----------- kselftest: Running tests in gpio TAP version 13 1..2 # selftests: gpio: gpio-mockup.sh # 1. Module load tests [ 61.176149] ============================================================================= [ 61.176802] [ 61.176807] ====================================================== [ 61.176809] WARNING: possible circular locking dependency detected [ 61.176811] 6.3.0-rc1-next-20230307 #1 Not tainted [ 61.176814] ------------------------------------------------------ [ 61.176816] modprobe/510 is trying to acquire lock: [ 61.176818] ffff80000b2284e8 (console_owner){..-.}-{0:0}, at: console_flush_all (kernel/printk/printk.c:2879 kernel/printk/printk.c:2942) [ 61.176846] [ 61.176846] but task is already holding lock: [ 61.176848] ffff000040000698 (&n->list_lock){-.-.}-{2:2}, at: get_partial_node.part.0 (mm/slub.c:2271) [ 61.176861] [ 61.176861] which lock already depends on the new lock. [ 61.176861] [ 61.176863] [ 61.176863] the existing dependency chain (in reverse order) is: [ 61.176864] [ 61.176864] -> #2 (&n->list_lock){-.-.}-{2:2}: [ 61.176871] lock_acquire (kernel/locking/lockdep.c:5673) [ 61.176879] _raw_spin_lock_irqsave (include/linux/spinlock_api_smp.h:111 kernel/locking/spinlock.c:162) [ 61.176885] get_partial_node.part.0 (mm/slub.c:2271) [ 61.176890] ___slab_alloc (mm/slub.c:2268 mm/slub.c:2386 mm/slub.c:3188) [ 61.176894] __slab_alloc.constprop.0 (mm/slub.c:3292) [ 61.176899] __kmem_cache_alloc_node (mm/slub.c:3345 mm/slub.c:3442 mm/slub.c:3491) [ 61.176903] __kmalloc (mm/slab_common.c:968 mm/slab_common.c:980) [ 61.176908] tty_buffer_alloc (drivers/tty/tty_buffer.c:182) [ 61.176914] __tty_buffer_request_room (drivers/tty/tty_buffer.c:279) [ 61.176919] __tty_insert_flip_char (drivers/tty/tty_buffer.c:398) [ 61.176924] uart_insert_char (drivers/tty/serial/serial_core.c:3341) [ 61.176929] pl011_fifo_to_tty.isra.0 (drivers/tty/serial/amba-pl011.c:314) [ 61.176934] pl011_int (include/linux/spinlock.h:390 drivers/tty/serial/amba-pl011.c:1396 drivers/tty/serial/amba-pl011.c:1571) [ 61.176937] __handle_irq_event_percpu (kernel/irq/handle.c:158) [ 61.176941] handle_irq_event (kernel/irq/handle.c:193 kernel/irq/handle.c:210) [ 61.176944] handle_fasteoi_irq (kernel/irq/chip.c:716) [ 61.176950] generic_handle_domain_irq (kernel/irq/irqdesc.c:652 kernel/irq/irqdesc.c:707) [ 61.176953] gic_handle_irq (arch/arm64/include/asm/io.h:75 include/asm-generic/io.h:335 drivers/irqchip/irq-gic.c:344) [ 61.176958] call_on_irq_stack (arch/arm64/kernel/entry.S:905) [ 61.176962] do_interrupt_handler (arch/arm64/kernel/entry-common.c:274) [ 61.176968] el1_interrupt (arch/arm64/kernel/entry-common.c:472 arch/arm64/kernel/entry-common.c:486) [ 61.176971] el1h_64_irq_handler (arch/arm64/kernel/entry-common.c:492) [ 61.176975] el1h_64_irq (arch/arm64/kernel/entry.S:587) [ 61.176978] __kmem_cache_alloc_node (mm/slub.c:3490) [ 61.176983] kmalloc_trace (mm/slab_common.c:1064 (discriminator 4)) [ 61.176986] inet6_dump_fib (net/ipv6/ip6_fib.c:657) [ 61.176991] rtnl_dump_all (net/core/rtnetlink.c:3964) [ 61.176997] netlink_dump (net/netlink/af_netlink.c:2296) [ 61.177004] netlink_recvmsg (net/netlink/af_netlink.c:2024) [ 61.177009] ____sys_recvmsg (net/socket.c:1015 net/socket.c:1036 net/socket.c:2723) [ 61.177014] ___sys_recvmsg (net/socket.c:2765) [ 61.177019] __sys_recvmsg (include/linux/file.h:31 net/socket.c:2797) [ 61.177025] __arm64_sys_recvmsg (net/socket.c:2802) [ 61.177030] invoke_syscall (arch/arm64/include/asm/current.h:19 arch/arm64/kernel/syscall.c:57) [ 61.177037] el0_svc_common.constprop.0 (arch/arm64/kernel/syscall.c:149) [ 61.177043] do_el0_svc (arch/arm64/kernel/syscall.c:194) [ 61.177049] el0_svc (arch/arm64/include/asm/daifflags.h:28 arch/arm64/kernel/entry-common.c:133 arch/arm64/kernel/entry-common.c:142 arch/arm64/kernel/entry-common.c:638) [ 61.177052] el0t_64_sync_handler (arch/arm64/kernel/entry-common.c:656) [ 61.177055] el0t_64_sync (arch/arm64/kernel/entry.S:591) [ 61.177058] [ 61.177058] -> #1 (&port_lock_key){-.-.}-{2:2}: [ 61.177065] lock_acquire (kernel/locking/lockdep.c:5673) [ 61.177071] _raw_spin_lock_irqsave (include/linux/spinlock_api_smp.h:111 kernel/locking/spinlock.c:162) [ 61.177074] serial8250_console_write (drivers/tty/serial/8250/8250_port.c:3394) [ 61.177082] univ8250_console_write (drivers/tty/serial/8250/8250_core.c:585) [ 61.177087] console_flush_all (kernel/printk/printk.c:2888 kernel/printk/printk.c:2942) [ 61.177093] console_unlock.part.0 (kernel/printk/printk.c:3017) [ 61.177098] vprintk_emit (kernel/printk/printk.c:2317) [ 61.177104] vprintk_default (kernel/printk/printk.c:2328) [ 61.177110] vprintk (kernel/printk/printk_safe.c:50) [ 61.177116] _printk (kernel/printk/printk.c:2341) [ 61.177121] register_console (kernel/printk/printk.c:3468) [ 61.177126] uart_add_one_port (drivers/tty/serial/serial_core.c:2579 drivers/tty/serial/serial_core.c:3100) [ 61.177130] serial8250_register_8250_port (drivers/tty/serial/8250/8250_core.c:1093) [ 61.177135] bcm2835aux_serial_probe (drivers/tty/serial/8250/8250_bcm2835aux.c:184) [ 61.177141] platform_probe (drivers/base/platform.c:1405) [ 61.177148] really_probe (drivers/base/dd.c:552 drivers/base/dd.c:631) [ 61.177152] __driver_probe_device (drivers/base/dd.c:768) [ 61.177157] driver_probe_device (drivers/base/dd.c:798) [ 61.177161] __driver_attach (drivers/base/dd.c:1185) [ 61.177166] bus_for_each_dev (drivers/base/bus.c:368) [ 61.177170] driver_attach (drivers/base/dd.c:1202) [ 61.177173] bus_add_driver (drivers/base/bus.c:673) [ 61.177177] driver_register (drivers/base/driver.c:246) [ 61.177182] __platform_driver_register (drivers/base/platform.c:868) [ 61.177188] bcm2835aux_serial_driver_init (drivers/tty/serial/8250/8250_bcm2835aux.c:233) [ 61.177195] do_one_initcall (init/main.c:1306) [ 61.177199] kernel_init_freeable (init/main.c:1378 init/main.c:1395 init/main.c:1414 init/main.c:1634) [ 61.177207] kernel_init (init/main.c:1524) [ 61.177212] ret_from_fork (arch/arm64/kernel/entry.S:871) [ 61.177216] [ 61.177216] -> #0 (console_owner){..-.}-{0:0}: [ 61.177222] __lock_acquire (kernel/locking/lockdep.c:3099 kernel/locking/lockdep.c:3217 kernel/locking/lockdep.c:3832 kernel/locking/lockdep.c:5056) [ 61.177228] lock_acquire.part.0 (arch/arm64/include/asm/percpu.h:40 kernel/locking/lockdep.c:467 kernel/locking/lockdep.c:5671) [ 61.177233] lock_acquire (kernel/locking/lockdep.c:5673) [ 61.177238] console_flush_all (kernel/printk/printk.c:2883 kernel/printk/printk.c:2942) [ 61.177244] console_unlock.part.0 (kernel/printk/printk.c:3017) [ 61.177250] vprintk_emit (kernel/printk/printk.c:2317) [ 61.177255] vprintk_default (kernel/printk/printk.c:2328) [ 61.177261] vprintk (kernel/printk/printk_safe.c:50) [ 61.177267] _printk (kernel/printk/printk.c:2341) [ 61.177271] slab_bug (mm/slub.c:892) [ 61.177274] check_bytes_and_report (mm/slub.c:1054) [ 61.177279] check_object (mm/slub.c:1196 (discriminator 2)) [ 61.177283] alloc_debug_processing (mm/slub.c:1415 mm/slub.c:1425) [ 61.177287] get_partial_node.part.0 (mm/slub.c:2146 mm/slub.c:2279) [ 61.177291] ___slab_alloc (mm/slub.c:2268 mm/slub.c:2386 mm/slub.c:3188) [ 61.177295] __slab_alloc.constprop.0 (mm/slub.c:3292) [ 61.177300] __kmem_cache_alloc_node (mm/slub.c:3345 mm/slub.c:3442 mm/slub.c:3491) [ 61.177304] kmalloc_trace (mm/slab_common.c:1064 (discriminator 4)) [ 61.177308] device_add (drivers/base/core.c:3436 drivers/base/core.c:3486) [ 61.177311] platform_device_add (drivers/base/platform.c:717) [ 61.177317] platform_device_register_full (drivers/base/platform.c:844) [ 61.177323] gpio_mockup_register_chip+0x1ec/0x2b8 gpio_mockup [ 61.177342] gpio_mockup_init+0xf0/0xd40 gpio_mockup [ 61.177352] do_one_initcall (init/main.c:1306) [ 61.177356] do_init_module (kernel/module/main.c:2457) [ 61.177363] load_module (kernel/module/main.c:2859) [ 61.177369] __do_sys_finit_module (kernel/module/main.c:2961) [ 61.177375] __arm64_sys_finit_module (kernel/module/main.c:2928) [ 61.177381] invoke_syscall (arch/arm64/include/asm/current.h:19 arch/arm64/kernel/syscall.c:57) [ 61.177387] el0_svc_common.constprop.0 (arch/arm64/kernel/syscall.c:149) [ 61.177393] do_el0_svc (arch/arm64/kernel/syscall.c:194) [ 61.177398] el0_svc (arch/arm64/include/asm/daifflags.h:28 arch/arm64/kernel/entry-common.c:133 arch/arm64/kernel/entry-common.c:142 arch/arm64/kernel/entry-common.c:638) [ 61.177402] el0t_64_sync_handler (arch/arm64/kernel/entry-common.c:656) [ 61.177405] el0t_64_sync (arch/arm64/kernel/entry.S:591) [ 61.177408] [ 61.177408] other info that might help us debug this: [ 61.177408] [ 61.177410] Chain exists of: [ 61.177410] console_owner --> &port_lock_key --> &n->list_lock [ 61.177410] [ 61.177417] Possible unsafe locking scenario: [ 61.177417] [ 61.177418] CPU0 CPU1 [ 61.177419] ---- ---- [ 61.177420] lock(&n->list_lock); [ 61.177423] lock(&port_lock_key); [ 61.177426] lock(&n->list_lock); [ 61.177429] lock(console_owner); [ 61.177432] [ 61.177432] *** DEADLOCK *** [ 61.177432] [ 61.177434] 3 locks held by modprobe/510: [ 61.177436] #0: ffff000040000698 (&n->list_lock){-.-.}-{2:2}, at: get_partial_node.part.0 (mm/slub.c:2271) [ 61.177448] #1: ffff80000b227f18 (console_lock){+.+.}-{0:0}, at: vprintk_emit (kernel/printk/printk.c:1936 kernel/printk/printk.c:2315) [ 61.177460] #2: ffff80000b228388 (console_srcu){....}-{0:0}, at: console_flush_all (include/linux/srcu.h:200 kernel/printk/printk.c:290 kernel/printk/printk.c:2934) [ 61.177471] [ 61.177471] stack backtrace: [ 61.177474] CPU: 3 PID: 510 Comm: modprobe Not tainted 6.3.0-rc1-next-20230307 #1 [ 61.177479] Hardware name: Raspberry Pi 4 Model B (DT) [ 61.177482] Call trace: [ 61.177483] dump_backtrace (arch/arm64/kernel/stacktrace.c:160) [ 61.177487] show_stack (arch/arm64/kernel/stacktrace.c:167) [ 61.177490] dump_stack_lvl (lib/dump_stack.c:107) [ 61.177498] dump_stack (lib/dump_stack.c:114) [ 61.177504] print_circular_bug (kernel/locking/lockdep.c:2057) [ 61.177509] check_noncircular (kernel/locking/lockdep.c:2181) [ 61.177514] __lock_acquire (kernel/locking/lockdep.c:3099 kernel/locking/lockdep.c:3217 kernel/locking/lockdep.c:3832 kernel/locking/lockdep.c:5056) [ 61.177520] lock_acquire.part.0 (arch/arm64/include/asm/percpu.h:40 kernel/locking/lockdep.c:467 kernel/locking/lockdep.c:5671) [ 61.177525] lock_acquire (kernel/locking/lockdep.c:5673) [ 61.177530] console_flush_all (kernel/printk/printk.c:2883 kernel/printk/printk.c:2942) [ 61.177536] console_unlock.part.0 (kernel/printk/printk.c:3017) [ 61.177542] vprintk_emit (kernel/printk/printk.c:2317) [ 61.177547] vprintk_default (kernel/printk/printk.c:2328) [ 61.177553] vprintk (kernel/printk/printk_safe.c:50) [ 61.177559] _printk (kernel/printk/printk.c:2341) [ 61.177564] slab_bug (mm/slub.c:892) [ 61.177567] check_bytes_and_report (mm/slub.c:1054) [ 61.177571] check_object (mm/slub.c:1196 (discriminator 2)) [ 61.177575] alloc_debug_processing (mm/slub.c:1415 mm/slub.c:1425) [ 61.177579] get_partial_node.part.0 (mm/slub.c:2146 mm/slub.c:2279) [ 61.177583] ___slab_alloc (mm/slub.c:2268 mm/slub.c:2386 mm/slub.c:3188) [ 61.177587] __slab_alloc.constprop.0 (mm/slub.c:3292) [ 61.177592] __kmem_cache_alloc_node (mm/slub.c:3345 mm/slub.c:3442 mm/slub.c:3491) [ 61.177596] kmalloc_trace (mm/slab_common.c:1064 (discriminator 4)) [ 61.177600] device_add (drivers/base/core.c:3436 drivers/base/core.c:3486) [ 61.177603] platform_device_add (drivers/base/platform.c:717) [ 61.177609] platform_device_register_full (drivers/base/platform.c:844) [ 61.177615] gpio_mockup_register_chip+0x1ec/0x2b8 gpio_mockup [ 61.177625] gpio_mockup_init+0xf0/0xd40 gpio_mockup [ 61.177634] do_one_initcall (init/main.c:1306) [ 61.177638] do_init_module (kernel/module/main.c:2457) [ 61.177644] load_module (kernel/module/main.c:2859) [ 61.177650] __do_sys_finit_module (kernel/module/main.c:2961) [ 61.177656] __arm64_sys_finit_module (kernel/module/main.c:2928) [ 61.177662] invoke_syscall (arch/arm64/include/asm/current.h:19 arch/arm64/kernel/syscall.c:57) [ 61.177668] el0_svc_common.constprop.0 (arch/arm64/kernel/syscall.c:149) [ 61.177674] do_el0_svc (arch/arm64/kernel/syscall.c:194) [ 61.177680] el0_svc (arch/arm64/include/asm/daifflags.h:28 arch/arm64/kernel/entry-common.c:133 arch/arm64/kernel/entry-common.c:142 arch/arm64/kernel/entry-common.c:638) [ 61.177683] el0t_64_sync_handler (arch/arm64/kernel/entry-common.c:656) [ 61.177686] el0t_64_sync (arch/arm64/kernel/entry.S:591) [ 62.011685] BUG kmalloc-512 (Not tainted): Poison overwritten [ 62.017513] ----------------------------------------------------------------------------- [ 62.017513] [ 62.027300] 0xffff00004ecb7a38-0xffff00004ecb7a47 @offset=31288. First byte 0x6a instead of 0x6b [ 62.036210] Allocated in swnode_register+0x40/0x218 age=808 cpu=3 pid=386 [ 62.043101] __kmem_cache_alloc_node (mm/slub.c:3345 mm/slub.c:3442 mm/slub.c:3491) [ 62.047784] kmalloc_trace (mm/slab_common.c:1064 (discriminator 4)) [ 62.051406] swnode_register (drivers/base/swnode.c:776) [ 62.055293] fwnode_create_software_node (drivers/base/swnode.c:934 (discriminator 4)) [ 62.060238] gpio_mockup_register_chip+0x1c4/0x2b8 gpio_mockup [ 62.066337] gpio_mockup_init+0xf0/0xd40 gpio_mockup [ 62.071551] do_one_initcall (init/main.c:1306) [ 62.075437] do_init_module (kernel/module/main.c:2457) [ 62.079238] load_module (kernel/module/main.c:2859) [ 62.083037] __do_sys_finit_module (kernel/module/main.c:2961) [ 62.087455] __arm64_sys_finit_module (kernel/module/main.c:2928) [ 62.092048] invoke_syscall (arch/arm64/include/asm/current.h:19 arch/arm64/kernel/syscall.c:57) [ 62.095848] el0_svc_common.constprop.0 (arch/arm64/kernel/syscall.c:149) [ 62.100793] do_el0_svc (arch/arm64/kernel/syscall.c:194) [ 62.104151] el0_svc (arch/arm64/include/asm/daifflags.h:28 arch/arm64/kernel/entry-common.c:133 arch/arm64/kernel/entry-common.c:142 arch/arm64/kernel/entry-common.c:638) [ 62.107244] el0t_64_sync_handler (arch/arm64/kernel/entry-common.c:656) [ 62.111570] Freed in software_node_release+0xdc/0x108 age=632 cpu=0 pid=428 [ 62.118633] __kmem_cache_free (mm/slub.c:3732 mm/slub.c:3788 mm/slub.c:3800) [ 62.122784] kfree (mm/slab_common.c:1020) [ 62.125788] software_node_release (drivers/base/swnode.c:761) [ 62.130204] kobject_put (lib/kobject.c:685 lib/kobject.c:712 include/linux/kref.h:65 lib/kobject.c:729) [ 62.133739] software_node_notify_remove (drivers/base/swnode.c:1093) [ 62.138597] device_del (drivers/base/core.c:2265 drivers/base/core.c:3778) [ 62.142134] platform_device_del.part.0 (drivers/base/platform.c:753) [ 62.146903] platform_device_unregister (drivers/base/platform.c:551 drivers/base/platform.c:794) [ 62.151672] gpio_mockup_exit+0x54/0x280 gpio_mockup [ 62.156888] __arm64_sys_delete_module (kernel/module/main.c:756 kernel/module/main.c:698 kernel/module/main.c:698) [ 62.161745] invoke_syscall (arch/arm64/include/asm/current.h:19 arch/arm64/kernel/syscall.c:57) [ 62.165545] el0_svc_common.constprop.0 (arch/arm64/kernel/syscall.c:149) [ 62.170490] do_el0_svc (arch/arm64/kernel/syscall.c:194) [ 62.173850] el0_svc (arch/arm64/include/asm/daifflags.h:28 arch/arm64/kernel/entry-common.c:133 arch/arm64/kernel/entry-common.c:142 arch/arm64/kernel/entry-common.c:638) [ 62.176941] el0t_64_sync_handler (arch/arm64/kernel/entry-common.c:656) [ 62.181267] el0t_64_sync (arch/arm64/kernel/entry.S:591) [ 62.184975] Slab 0xfffffc00013b2c00 objects=21 used=7 fp=0xffff00004ecb7400 flags=0x7fffc0000010200(slab|head|node=0|zone=1|lastcpupid=0xffff) [ 62.197943] Object 0xffff00004ecb7a00 @offset=31232 fp=0xffff00004ecb7400 [ 62.197943] [ 62.206325] Redzone ffff00004ecb7800: ... [ 63.089597] CPU: 3 PID: 510 Comm: modprobe Not tainted 6.3.0-rc1-next-20230307 #1 [ 63.097186] Hardware name: Raspberry Pi 4 Model B (DT) [ 63.102392] Call trace: [ 63.104865] dump_backtrace (arch/arm64/kernel/stacktrace.c:160) [ 63.108665] show_stack (arch/arm64/kernel/stacktrace.c:167) [ 63.112021] dump_stack_lvl (lib/dump_stack.c:107) [ 63.115734] dump_stack (lib/dump_stack.c:114) [ 63.119093] print_trailer (mm/slub.c:953) [ 63.122892] check_bytes_and_report (mm/slub.c:1058) [ 63.127395] check_object (mm/slub.c:1196 (discriminator 2)) [ 63.131104] alloc_debug_processing (mm/slub.c:1415 mm/slub.c:1425) [ 63.135606] get_partial_node.part.0 (mm/slub.c:2146 mm/slub.c:2279) [ 63.140286] ___slab_alloc (mm/slub.c:2268 mm/slub.c:2386 mm/slub.c:3188) [ 63.144084] __slab_alloc.constprop.0 (mm/slub.c:3292) [ 63.148674] __kmem_cache_alloc_node (mm/slub.c:3345 mm/slub.c:3442 mm/slub.c:3491) [ 63.153354] kmalloc_trace (mm/slab_common.c:1064 (discriminator 4)) [ 63.156974] device_add (drivers/base/core.c:3436 drivers/base/core.c:3486) [ 63.160508] platform_device_add (drivers/base/platform.c:717) [ 63.164837] platform_device_register_full (drivers/base/platform.c:844) [ 63.169959] gpio_mockup_register_chip+0x1ec/0x2b8 gpio_mockup [ 63.176057] gpio_mockup_init+0xf0/0xd40 gpio_mockup [ 63.181269] do_one_initcall (init/main.c:1306) [ 63.185155] do_init_module (kernel/module/main.c:2457) [ 63.188956] load_module (kernel/module/main.c:2859) [ 63.192755] __do_sys_finit_module (kernel/module/main.c:2961) [ 63.197171] __arm64_sys_finit_module (kernel/module/main.c:2928) [ 63.201765] invoke_syscall (arch/arm64/include/asm/current.h:19 arch/arm64/kernel/syscall.c:57) [ 63.205565] el0_svc_common.constprop.0 (arch/arm64/kernel/syscall.c:149) [ 63.210510] do_el0_svc (arch/arm64/kernel/syscall.c:194) [ 63.213869] el0_svc (arch/arm64/include/asm/daifflags.h:28 arch/arm64/kernel/entry-common.c:133 arch/arm64/kernel/entry-common.c:142 arch/arm64/kernel/entry-common.c:638) [ 63.216961] el0t_64_sync_handler (arch/arm64/kernel/entry-common.c:656) [ 63.221287] el0t_64_sync (arch/arm64/kernel/entry.S:591) [ 63.224998] FIX kmalloc-512: Restoring Poison 0xffff00004ecb7a38-0xffff00004ecb7a47=0x6b [ 63.233202] FIX kmalloc-512: Marking all objects used [ 63.399213] ============================================================================= links to the crash: - https://lkft.validation.linaro.org/scheduler/job/6224830#L1291 - https://lkft.validation.linaro.org/scheduler/job/6224742#L1202 - https://lkft.validation.linaro.org/scheduler/job/6224784#L3415 - https://lkft.validation.linaro.org/scheduler/job/6224810#L2029 metadata: git_ref: master git_repo: https://gitlab.com/Linaro/lkft/mirrors/next/linux-next git_sha: 709c6adf19dc558e44ab5c01659b09a16a2d3c82 git_describe: next-20230307 kernel_version: 6.3.0-rc1 kernel-config: https://storage.tuxsuite.com/public/linaro/lkft/builds/2MfXESbRAbSUj9oic6d8… build-url: https://gitlab.com/Linaro/lkft/mirrors/next/linux-next/-/pipelines/798095907 artifact-location: https://storage.tuxsuite.com/public/linaro/lkft/builds/2MfXESbRAbSUj9oic6d8… toolchain: gcc-11 -- Linaro LKFT https://lkft.linaro.org

1 year, 7 months

5
8
0 0

[PATCH] KVM: arm64: selftests: Clean up the GIC[D,R]_BASE_GPA

by Shaoqin Huang

The GIC[D,R]_BASE_GPA has been defined in multiple files with the same value, define it in one place to make the code clean. Signed-off-by: Shaoqin Huang <shahuang(a)redhat.com> --- tools/testing/selftests/kvm/aarch64/arch_timer.c | 3 --- tools/testing/selftests/kvm/aarch64/vgic_irq.c | 3 --- tools/testing/selftests/kvm/dirty_log_perf_test.c | 3 --- tools/testing/selftests/kvm/include/aarch64/vgic.h | 3 +++ 4 files changed, 3 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index 274b8465b42a..818854007bfd 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -59,9 +59,6 @@ static struct test_args test_args = { #define msecs_to_usecs(msec) ((msec) * 1000LL) -#define GICD_BASE_GPA 0x8000000ULL -#define GICR_BASE_GPA 0x80A0000ULL - enum guest_stage { GUEST_STAGE_VTIMER_CVAL = 1, GUEST_STAGE_VTIMER_TVAL, diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c index 2e64b4856e38..a48aff110fb6 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c @@ -19,9 +19,6 @@ #include "gic_v3.h" #include "vgic.h" -#define GICD_BASE_GPA 0x08000000ULL -#define GICR_BASE_GPA 0x080A0000ULL - /* * Stores the user specified args; it's passed to the guest and to every test * function. diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index d374dbcf9a53..4971e8f77a0a 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -22,9 +22,6 @@ #ifdef __aarch64__ #include "aarch64/vgic.h" -#define GICD_BASE_GPA 0x8000000ULL -#define GICR_BASE_GPA 0x80A0000ULL - static int gic_fd; static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus) diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/aarch64/vgic.h index 0ac6f05c63f9..9dbb342fd808 100644 --- a/tools/testing/selftests/kvm/include/aarch64/vgic.h +++ b/tools/testing/selftests/kvm/include/aarch64/vgic.h @@ -33,4 +33,7 @@ void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu); #define KVM_IRQCHIP_NUM_PINS (1020 - 32) +#define GICD_BASE_GPA 0x08000000ULL +#define GICR_BASE_GPA 0x080A0000ULL + #endif // SELFTEST_KVM_VGIC_H -- 2.40.1

1 year, 7 months

1
1
0 0

[Discuss] Seeking advice on net selftests netns naming method

by Hangbin Liu

Hi, Good day! Following Guillaume's suggestion, I've been working on updating all net self-tests to run in their respective netns. This modification allows us to execute all tests in parallel, potentially saving a significant amount of test time. However, I've encountered a challenge while making these modifications. The net selftest folder contains around 80 tests (excluding the forwarding test), with some tests using common netns names and others using self-defined names. I've considered two methods to address this issue: One approach is to retain the original names but append a unique suffix using $(mktemp -u XXXXXX). While this is a straightforward solution, it may not prevent future tests from using common names. Another option is to establish a general netns lib. Similar to the NUM_NETIFS variable in the forwarding test, we could introduce a variable like NUM_NS. This variable would define the number of netns instances, and all tests would use the netns lib to set up and clean up netns accordingly. However, this approach might complicate test debugging, especially for tests like fib_nexthops.sh, which relies on clear and visually netns names (e.g., me/peer/remote). I'm reaching out to gather your insights on this matter. Do you have any suggestions or preferences regarding the two proposed methods, or do you have an alternative solution in mind? Your expertise in this area would be greatly appreciated. Best Regards Hangbin

1 year, 7 months

2
4
0 0

[PATCH net 0/5] mptcp: misc. fixes for v6.7

by Matthieu Baerts

Here are a few fixes related to MPTCP: - Patch 1 limits GSO max size to ~64K when MPTCP is being used due to a spec limit. 'gso_max_size' can exceed the max value supported by MPTCP since v5.19. - Patch 2 fixes a possible NULL pointer dereference on close that can happen since v6.7-rc1. - Patch 3 avoids sending a RM_ADDR when the corresponding address is no longer tracked locally. A regression for a fix backported to v5.19. - Patch 4 adds a missing lock when changing the IP TOS with setsockopt(). A fix for v5.17. - Patch 5 fixes an expectation when running MPTCP Join selftest with the checksum option (-C). An issue present since v6.1. Signed-off-by: Matthieu Baerts <matttbe(a)kernel.org> --- Geliang Tang (1): mptcp: add validity check for sending RM_ADDR Paolo Abeni (4): mptcp: deal with large GSO size mptcp: fix possible NULL pointer dereference on close mptcp: fix setsockopt(IP_TOS) subflow locking selftests: mptcp: fix fastclose with csum failure net/mptcp/pm_netlink.c | 5 +++-- net/mptcp/protocol.c | 11 ++++++++--- net/mptcp/sockopt.c | 3 +++ tools/testing/selftests/net/mptcp/mptcp_join.sh | 2 +- 4 files changed, 15 insertions(+), 6 deletions(-) --- base-commit: 2bd5b559a1f391f05927bbb0b31381fa71c61e26 change-id: 20231113-upstream-net-20231113-mptcp-misc-fixes-6-7-rc2-d15df60b0a3f Best regards, -- Matthieu Baerts <matttbe(a)kernel.org>

1 year, 7 months

2
6
0 0

[PATCH v2 00/21] arm64: Support for 2023 DPISA extensions

by Mark Brown

This series enables support for the data processing extensions in the newly released 2023 architecture, this is mainly support for 8 bit floating point formats. Most of the extensions only introduce new instructions and therefore only require hwcaps but there is a new EL0 visible control register FPMR used to control the 8 bit floating point formats, we need to manage traps for this and context switch it. The sharing of floating point save code between the host and guest kernels slightly complicates the introduction of KVM support, we first introduce host support with some placeholders for KVM then replace those with the actual KVM support. I've not added test coverage for ptrace, I've got a not quite finished test program which exercises all the FP ptrace interfaces and their interactions together, my plan is to cover it there rather than add another tiny test program that duplicates the boilerplace for tracing a target and doesn't actually run the traced program. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v2: - Rebase onto v6.7-rc1. - Link to v1: https://lore.kernel.org/r/20231026-arm64-2023-dpisa-v1-0-8470dd989bb2@kerne… --- Mark Brown (21): arm64/sysreg: Add definition for ID_AA64PFR2_EL1 arm64/sysreg: Update ID_AA64ISAR2_EL1 defintion for DDI0601 2023-09 arm64/sysreg: Add definition for ID_AA64ISAR3_EL1 arm64/sysreg: Add definition for ID_AA64FPFR0_EL1 arm64/sysreg: Update ID_AA64SMFR0_EL1 definition for DDI0601 2023-09 arm64/sysreg: Update SCTLR_EL1 for DDI0601 2023-09 arm64/sysreg: Update HCRX_EL2 definition for DDI0601 2023-09 arm64/sysreg: Add definition for FPMR arm64/cpufeature: Hook new identification registers up to cpufeature arm64/fpsimd: Enable host kernel access to FPMR arm64/fpsimd: Support FEAT_FPMR arm64/signal: Add FPMR signal handling arm64/ptrace: Expose FPMR via ptrace KVM: arm64: Add newly allocated ID registers to register descriptions KVM: arm64: Support FEAT_FPMR for guests arm64/hwcap: Define hwcaps for 2023 DPISA features kselftest/arm64: Handle FPMR context in generic signal frame parser kselftest/arm64: Add basic FPMR test kselftest/arm64: Add 2023 DPISA hwcap test coverage KVM: arm64: selftests: Document feature registers added in 2023 extensions KVM: arm64: selftests: Teach get-reg-list about FPMR Documentation/arch/arm64/elf_hwcaps.rst | 49 +++++ arch/arm64/include/asm/cpu.h | 3 + arch/arm64/include/asm/cpufeature.h | 5 + arch/arm64/include/asm/fpsimd.h | 2 + arch/arm64/include/asm/hwcap.h | 15 ++ arch/arm64/include/asm/kvm_arm.h | 4 +- arch/arm64/include/asm/kvm_host.h | 3 + arch/arm64/include/asm/processor.h | 2 + arch/arm64/include/uapi/asm/hwcap.h | 15 ++ arch/arm64/include/uapi/asm/sigcontext.h | 8 + arch/arm64/kernel/cpufeature.c | 72 +++++++ arch/arm64/kernel/cpuinfo.c | 18 ++ arch/arm64/kernel/fpsimd.c | 13 ++ arch/arm64/kernel/ptrace.c | 42 ++++ arch/arm64/kernel/signal.c | 59 ++++++ arch/arm64/kvm/fpsimd.c | 19 +- arch/arm64/kvm/hyp/include/hyp/switch.h | 7 +- arch/arm64/kvm/sys_regs.c | 17 +- arch/arm64/tools/cpucaps | 1 + arch/arm64/tools/sysreg | 153 ++++++++++++++- include/uapi/linux/elf.h | 1 + tools/testing/selftests/arm64/abi/hwcap.c | 217 +++++++++++++++++++++ tools/testing/selftests/arm64/signal/.gitignore | 1 + .../arm64/signal/testcases/fpmr_siginfo.c | 82 ++++++++ .../selftests/arm64/signal/testcases/testcases.c | 8 + .../selftests/arm64/signal/testcases/testcases.h | 1 + tools/testing/selftests/kvm/aarch64/get-reg-list.c | 11 +- 27 files changed, 810 insertions(+), 18 deletions(-) --- base-commit: b85ea95d086471afb4ad062012a4d73cd328fa86 change-id: 20231003-arm64-2023-dpisa-2f3d25746474 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year, 7 months

1
21
0 0

[PATCH bpf-next] selftests/bpf: add assert for user stacks in test_task_stack

by Jordan Rome

This is a follow up to: commit b8e3a87a627b ("bpf: Add crosstask check to __bpf_get_stack"). This test ensures that the task iterator only gets a single user stack (for the current task). Signed-off-by: Jordan Rome <linux(a)jordanrome.com> --- tools/testing/selftests/bpf/prog_tests/bpf_iter.c | 2 ++ tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c | 5 +++++ 2 files changed, 7 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 4e02093c2cbe..618af9dfae9b 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -332,6 +332,8 @@ static void test_task_stack(void) do_dummy_read(skel->progs.dump_task_stack); do_dummy_read(skel->progs.get_task_user_stacks); + ASSERT_EQ(skel->bss->num_user_stacks, 1, "num_user_stacks"); + bpf_iter_task_stack__destroy(skel); } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c index f2b8167b72a8..442f4ca39fd7 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c @@ -35,6 +35,8 @@ int dump_task_stack(struct bpf_iter__task *ctx) return 0; } +int num_user_stacks = 0; + SEC("iter/task") int get_task_user_stacks(struct bpf_iter__task *ctx) { @@ -51,6 +53,9 @@ int get_task_user_stacks(struct bpf_iter__task *ctx) if (res <= 0) return 0; + /* Only one task, the current one, should succeed */ + ++num_user_stacks; + buf_sz += res; /* If the verifier doesn't refine bpf_get_task_stack res, and instead -- 2.39.3

1 year, 8 months

3
2
0 0

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.7-rc1)

by kernelci.org bot

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.7-rc1) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------+------+---------------+----------+------------------------------+------------ imx6q-sabrelite | arm | lab-collabora | gcc-10 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.7-rc1/plan/ks… Test: kselftest-lkdtm Tree: kselftest Branch: next Describe: v6.7-rc1 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: b85ea95d086471afb4ad062012a4d73cd328fa86 Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------+------+---------------+----------+------------------------------+------------ imx6q-sabrelite | arm | lab-collabora | gcc-10 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/6552d8e2f99dd3968f7e4a6d Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-10 (arm-linux-gnueabihf-gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//kselftest/next/v6.7-rc1/arm/multi_v7_defconfi… HTML log: https://storage.kernelci.org//kselftest/next/v6.7-rc1/arm/multi_v7_defconfi… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bullseye-kselftest/2023062… * kselftest-lkdtm.login: https://kernelci.org/test/case/id/6552d8e2f99dd3968f7e4a6e failing since 348 days (last pass: v6.1-rc1-23-g00dd59519141, first fail: v6.1-rc1-23-g8008d88e6d16)

1 year, 8 months

1
0
0 0

kselftest/fixes kselftest-lkdtm: 1 runs, 1 regressions (v6.7-rc1)

by kernelci.org bot

kselftest/fixes kselftest-lkdtm: 1 runs, 1 regressions (v6.7-rc1) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------+------+---------------+----------+------------------------------+------------ imx6q-sabrelite | arm | lab-collabora | gcc-10 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/fixes/kernel/v6.7-rc1/plan/k… Test: kselftest-lkdtm Tree: kselftest Branch: fixes Describe: v6.7-rc1 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: b85ea95d086471afb4ad062012a4d73cd328fa86 Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------+------+---------------+----------+------------------------------+------------ imx6q-sabrelite | arm | lab-collabora | gcc-10 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/6552cfd1a643143fb07e4a6e Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-10 (arm-linux-gnueabihf-gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//kselftest/fixes/v6.7-rc1/arm/multi_v7_defconf… HTML log: https://storage.kernelci.org//kselftest/fixes/v6.7-rc1/arm/multi_v7_defconf… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bullseye-kselftest/2023062… * kselftest-lkdtm.login: https://kernelci.org/test/case/id/6552cfd1a643143fb07e4a6f failing since 392 days (last pass: v6.0-rc1, first fail: v6.1-rc1)

1 year, 8 months

1
0
0 0

kselftest/next build: 6 builds: 2 failed, 4 passed, 1 warning (v6.7-rc1)

by kernelci.org bot

kselftest/next build: 6 builds: 2 failed, 4 passed, 1 warning (v6.7-rc1) Full Build Summary: https://kernelci.org/build/kselftest/branch/next/kernel/v6.7-rc1/ Tree: kselftest Branch: next Git Describe: v6.7-rc1 Git Commit: b85ea95d086471afb4ad062012a4d73cd328fa86 Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git Built: 4 unique architectures Build Failures Detected: arm64: defconfig+kselftest+arm64-chromebook: (clang-16) FAIL defconfig+kselftest+arm64-chromebook: (gcc-10) FAIL Warnings Detected: arm64: arm: i386: x86_64: x86_64_defconfig+kselftest (clang-16): 1 warning Warnings summary: 1 vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x23: relocation to !ENDBR: .text+0x14bbfb ================================================================================ Detailed per-defconfig build reports: -------------------------------------------------------------------------------- defconfig+kselftest (arm64, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, gcc-10) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, clang-16) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- i386_defconfig+kselftest (i386, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- multi_v7_defconfig+kselftest (arm, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, clang-16) — PASS, 0 errors, 1 warning, 0 section mismatches Warnings: vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x23: relocation to !ENDBR: .text+0x14bbfb --- For more info write to <info(a)kernelci.org>

1 year, 8 months

1
0
0 0

kselftest/fixes build: 6 builds: 2 failed, 4 passed, 1 warning (v6.7-rc1)

by kernelci.org bot

kselftest/fixes build: 6 builds: 2 failed, 4 passed, 1 warning (v6.7-rc1) Full Build Summary: https://kernelci.org/build/kselftest/branch/fixes/kernel/v6.7-rc1/ Tree: kselftest Branch: fixes Git Describe: v6.7-rc1 Git Commit: b85ea95d086471afb4ad062012a4d73cd328fa86 Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git Built: 4 unique architectures Build Failures Detected: arm64: defconfig+kselftest+arm64-chromebook: (clang-16) FAIL defconfig+kselftest+arm64-chromebook: (gcc-10) FAIL Warnings Detected: arm64: arm: i386: x86_64: x86_64_defconfig+kselftest (clang-16): 1 warning Warnings summary: 1 vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x23: relocation to !ENDBR: .text+0x14bbfb ================================================================================ Detailed per-defconfig build reports: -------------------------------------------------------------------------------- defconfig+kselftest (arm64, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, gcc-10) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, clang-16) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- i386_defconfig+kselftest (i386, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- multi_v7_defconfig+kselftest (arm, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, clang-16) — PASS, 0 errors, 1 warning, 0 section mismatches Warnings: vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x23: relocation to !ENDBR: .text+0x14bbfb --- For more info write to <info(a)kernelci.org>

1 year, 8 months

1
0
0 0

[PATCH V10 0/7] amd-pstate preferred core

by Meng Li

Hi all: The core frequency is subjected to the process variation in semiconductors. Not all cores are able to reach the maximum frequency respecting the infrastructure limits. Consequently, AMD has redefined the concept of maximum frequency of a part. This means that a fraction of cores can reach maximum frequency. To find the best process scheduling policy for a given scenario, OS needs to know the core ordering informed by the platform through highest performance capability register of the CPPC interface. Earlier implementations of amd-pstate preferred core only support a static core ranking and targeted performance. Now it has the ability to dynamically change the preferred core based on the workload and platform conditions and accounting for thermals and aging. Amd-pstate driver utilizes the functions and data structures provided by the ITMT architecture to enable the scheduler to favor scheduling on cores which can be get a higher frequency with lower voltage. We call it amd-pstate preferred core. Here sched_set_itmt_core_prio() is called to set priorities and sched_set_itmt_support() is called to enable ITMT feature. Amd-pstate driver uses the highest performance value to indicate the priority of CPU. The higher value has a higher priority. Amd-pstate driver will provide an initial core ordering at boot time. It relies on the CPPC interface to communicate the core ranking to the operating system and scheduler to make sure that OS is choosing the cores with highest performance firstly for scheduling the process. When amd-pstate driver receives a message with the highest performance change, it will update the core ranking. Changes from V9->V10: - cpufreq: amd-pstate: - - add judgement for highest_perf. When it is less than 255, the preferred core feature is enabled. And it will set the priority. - - deleset "static u32 max_highest_perf" etc, because amd p-state perferred coe does not require specail process for hotpulg. Changes form V8->V9: - all: - - pick up Tested-By flag added by Oleksandr. - cpufreq: amd-pstate: - - pick up Review-By flag added by Wyes. - - ignore modification of bug. - - add a attribute of prefcore_ranking. - - modify data type conversion from u32 to int. - Documentation: amd-pstate: - - pick up Review-By flag added by Wyes. Changes form V7->V8: - all: - - pick up Review-By flag added by Mario and Ray. - cpufreq: amd-pstate: - - use hw_prefcore embeds into cpudata structure. - - delete preferred core init from cpu online/off. Changes form V6->V7: - x86: - - Modify kconfig about X86_AMD_PSTATE. - cpufreq: amd-pstate: - - modify incorrect comments about scheduler_work(). - - convert highest_perf data type. - - modify preferred core init when cpu init and online. - acpi: cppc: - - modify link of CPPC highest performance. - cpufreq: - - modify link of CPPC highest performance changed. Changes form V5->V6: - cpufreq: amd-pstate: - - modify the wrong tag order. - - modify warning about hw_prefcore sysfs attribute. - - delete duplicate comments. - - modify the variable name cppc_highest_perf to prefcore_ranking. - - modify judgment conditions for setting highest_perf. - - modify sysfs attribute for CPPC highest perf to pr_debug message. - Documentation: amd-pstate: - - modify warning: title underline too short. Changes form V4->V5: - cpufreq: amd-pstate: - - modify sysfs attribute for CPPC highest perf. - - modify warning about comments - - rebase linux-next - cpufreq: - - Moidfy warning about function declarations. - Documentation: amd-pstate: - - align with ``amd-pstat`` Changes form V3->V4: - Documentation: amd-pstate: - - Modify inappropriate descriptions. Changes form V2->V3: - x86: - - Modify kconfig and description. - cpufreq: amd-pstate: - - Add Co-developed-by tag in commit message. - cpufreq: - - Modify commit message. - Documentation: amd-pstate: - - Modify inappropriate descriptions. Changes form V1->V2: - acpi: cppc: - - Add reference link. - cpufreq: - - Moidfy link error. - cpufreq: amd-pstate: - - Init the priorities of all online CPUs - - Use a single variable to represent the status of preferred core. - Documentation: - - Default enabled preferred core. - Documentation: amd-pstate: - - Modify inappropriate descriptions. - - Default enabled preferred core. - - Use a single variable to represent the status of preferred core. Meng Li (7): x86: Drop CPU_SUP_INTEL from SCHED_MC_PRIO for the expansion. acpi: cppc: Add get the highest performance cppc control cpufreq: amd-pstate: Enable amd-pstate preferred core supporting. cpufreq: Add a notification message that the highest perf has changed cpufreq: amd-pstate: Update amd-pstate preferred core ranking dynamically Documentation: amd-pstate: introduce amd-pstate preferred core Documentation: introduce amd-pstate preferrd core mode kernel command line options .../admin-guide/kernel-parameters.txt | 5 + Documentation/admin-guide/pm/amd-pstate.rst | 59 +++++- arch/x86/Kconfig | 5 +- drivers/acpi/cppc_acpi.c | 13 ++ drivers/acpi/processor_driver.c | 6 + drivers/cpufreq/amd-pstate.c | 187 ++++++++++++++++-- drivers/cpufreq/cpufreq.c | 13 ++ include/acpi/cppc_acpi.h | 5 + include/linux/amd-pstate.h | 10 + include/linux/cpufreq.h | 5 + 10 files changed, 288 insertions(+), 20 deletions(-) -- 2.34.1

1 year, 8 months

3
10
0 0

[PATCH v3] KVM: selftests: Initialise dynamically allocated configuration names

by Mark Brown

When we dynamically generate a name for a configuration in get-reg-list we use strcat() to append to a buffer allocated using malloc() but we never initialise that buffer. Since malloc() offers no guarantees regarding the contents of the memory it returns this can lead to us corrupting, and likely overflowing, the buffer: vregs: PASS vregs+pmu: PASS sve: PASS sve+pmu: PASS vregs+pauth_address+pauth_generic: PASS X�vr+gspauth_addre+spauth_generi+pmu: PASS Initialise the buffer to an empty string to avoid this. Fixes: 2f9ace5d4557 ("KVM: arm64: selftests: get-reg-list: Introduce vcpu configs") Reviewed-by: Andrew Jones <ajones(a)ventanamicro.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v3: - Rebase this bugfix onto v6.7-rc1 - Link to v2: https://lore.kernel.org/r/20231017-kvm-get-reg-list-str-init-v2-1-ee30b1df3… Changes in v2: - Update Fixes: tag. - Link to v1: https://lore.kernel.org/r/20231013-kvm-get-reg-list-str-init-v1-1-034f370ff… --- tools/testing/selftests/kvm/get-reg-list.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c index be7bf5224434..dd62a6976c0d 100644 --- a/tools/testing/selftests/kvm/get-reg-list.c +++ b/tools/testing/selftests/kvm/get-reg-list.c @@ -67,6 +67,7 @@ static const char *config_name(struct vcpu_reg_list *c) c->name = malloc(len); + c->name[0] = '\0'; len = 0; for_each_sublist(c, s) { if (!strcmp(s->name, "base")) --- base-commit: b85ea95d086471afb4ad062012a4d73cd328fa86 change-id: 20231012-kvm-get-reg-list-str-init-76c8ed4e19d6 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year, 8 months

1
0
0 0

[PATCH v2 0/4] cgroup/cpuset: Improve CPU isolation in isolated partitions

by Waiman Long

v2: - Add 2 read-only workqueue sysfs files to expose the user requested cpumask as well as the isolated CPUs to be excluded from wq_unbound_cpumask. - Ensure that caller of the new workqueue_unbound_exclude_cpumask() hold cpus_read_lock. - Update the cpuset code to make sure the cpus_read_lock is held whenever workqueue_unbound_exclude_cpumask() may be called. Isolated cpuset partition can currently be created to contain an exclusive set of CPUs not used in other cgroups and with load balancing disabled to reduce interference from the scheduler. The main purpose of this isolated partition type is to dynamically emulate what can be done via the "isolcpus" boot command line option, specifically the default domain flag. One effect of the "isolcpus" option is to remove the isolated CPUs from the cpumasks of unbound workqueues since running work functions in an isolated CPU can be a major source of interference. Changing the unbound workqueue cpumasks can be done at run time by writing an appropriate cpumask without the isolated CPUs to /sys/devices/virtual/workqueue/cpumask. So one can set up an isolated cpuset partition and then write to the cpumask sysfs file to achieve similar level of CPU isolation. However, this manual process can be error prone. This patch series implements automatic exclusion of isolated CPUs from unbound workqueue cpumasks when an isolated cpuset partition is created and then adds those CPUs back when the isolated partition is destroyed. There are also other places in the kernel that look at the HK_FLAG_DOMAIN cpumask or other HK_FLAG_* cpumasks and exclude the isolated CPUs from certain actions to further reduce interference. CPUs in an isolated cpuset partition will not be able to avoid those interferences yet. That may change in the future as the need arises. Waiman Long (4): workqueue: Add workqueue_unbound_exclude_cpumask() to exclude CPUs from wq_unbound_cpumask selftests/cgroup: Minor code cleanup and reorganization of test_cpuset_prs.sh cgroup/cpuset: Keep track of CPUs in isolated partitions cgroup/cpuset: Take isolated CPUs out of workqueue unbound cpumask Documentation/admin-guide/cgroup-v2.rst | 10 +- include/linux/workqueue.h | 2 +- kernel/cgroup/cpuset.c | 286 +++++++++++++----- kernel/workqueue.c | 91 +++++- .../selftests/cgroup/test_cpuset_prs.sh | 216 ++++++++----- 5 files changed, 438 insertions(+), 167 deletions(-) -- 2.39.3

1 year, 8 months

3
7
0 0

[RFC PATCH 0/8] DAMOS: Introduce Aim-oriented Feedback-driven Aggressiveness Auto Tuning

by SeongJae Park

Another candidate of the subject was "Let users feed and tame DAMOS". DAMOS Control Difficulty ======================== DAMOS helps users easily implementing effective access pattern aware system operations. However, controlling DAMOS in wild is not that easy. The basic way to control DAMON is specifying the target access pattern. Hence, the user is assumed to know the access pattern of the system and the workloads well. Though some good tools including DAMON can help that, it requires time and resource, and the cost depends on the complexity and the dynamicity of the system and workloads. After all, the access pattern consist of three ranges, namely ranges of access rate, age, and size of the regions. Tuning six parameters is already complex. It is not doable for everyone. To ease the control, DAMOS allows users to set the upper-limit of the schemes's aggressiveness, namely DAMOS quota. Then DAMOS prioritizes regions to apply the action under the limit based on the action and the access pattern of the regions. For example, use can ask DAMOS to page out up to 100 MiB of memory regions per second. Then DAMOS pages out regions that not accessed for longer time first under the limit. This allows users to set access pattern bit more naively, and focus on only the one parameter, the quota. That is, the number of parameters to tune with special care can be reduced from six to one. Still, however, the optimal value for the quota depends on the system and the workloads' characteristics, so not that simple. The number of parameters to tune can also increase again if the user needs to run multiple schemes, e.g., collapsing hot pages into THP while splitting cold pages into regular pages. In short, the existing approach asks users to find the perfect or adapted tuning and instruct DAMOS how to work. It requires users to be deligent. That's not a virtue of human, but the machine. Aim-oriented Feedback-driven DAMOS Quota Auto Tuning ==================================================== Most users would start using DAMOS since there is something they want to achieve with DAMOS. Having such goal metrics like SLO is common. Hence, a better approach would be letting users inform DAMOS what they aim to achieve, and how well DAMOS is doing that. Then DAMOS can somehow make it. In detail, users provide feedback for each DAMOS scheme. DAMOS then tune the quota of each scheme based on the users' feedback and the current quota values. This patchset implements the idea. Implementation -------------- The core logic implementation is in the first patch. In short, it uses below simple feedback loop algorithm to get next aggressiveness from the current aggressiveness and the feedback (target_core and current_score) for the current aggressiveness. f(n, target_score, current_score) = max(f(n - 1) * ((target_score - current_score) / target_score + 1), 1) Note that this algorithm assumes the aggressiveness and the score are positively proportional. Making it true is the feedback provider's responsibility. Test Results ------------ To show if this provides the expected benefit, we extend the performance tests of damon-tests suite to support virtual address space-based proactive reclamation scheme that aims 0.5% last 10 seconds some memory PSI. The test suite runs PARSEC3 and SPLASH-2X workloads with the scheme and measure the runtime, the RSS, and the PSI for memory (some). We do same with the same scheme but not having the goal, and yet another variant of it that the target access patterns of the scheme is tuned for each workload, in a offline-tuning approach named DAMOOS[1]. The results that normalized to the output that made without any scheme are as below. The PSI for original run (without any scheme) was zero. To avoid divide-by-zero, we normalize the value to that of Not-tuned scheme's result. xx Not-tuned Offline-tuned Online-tuned RSS 0.622688178226118 0.787950678944904 0.740093483278979 runtime 1.11767826657912 1.0564674983585 1.0910833880499 PSI 1 0.727521443794069 0.308498846350299 The not-tuned scheme acheives about 38.7% memory saving but incur about 11.7% runtime slowdown. The offline-tuned scheme achieves about 22.2% memory saving with about 5.5% runtiem slowdown. It also achieves about 28.2% PSI saving. The online-tuned scheme achieves about 26% memory saving with about 9.1% runtime slowdown. It also achieves about 69.1% PSI saving. Given the online-tuned version is using this RFC level implementation and the goal (0.5% last-10 secs memory PSI) was made after only a few experiments within a day, I think this results show some potential of this feedback-driven auto tuning approach. The test code is available[2], so you can reproduce on your system. [1] https://www.amazon.science/publications/daos-data-access-aware-operating-sy… [2] https://github.com/damonitor/damon-tests/commit/3f884e61193f0166b8724554b6d… Patches Sequence ================ The first four patches implement the core logic and user interfaces for the auto tuning. The first patch implements the core logic for the auto tuning, and the API for DAMOS users in the kernel space. The second patch implements basic file operations of DAMON sysfs directories and files that will be used for setting the goals and providing the feedback. The third patch connects the quota goals files inputs to the DAMOS core logic. Finally the fourth patch implements a dedicated DAMOS sysfs command for efficiently committing the quota goals feedback. Two patches for simple test of the logic and interfaces follow. The fifth patch implements the core logic unit test. The sixth patch implements a selftest for the DAMON Sysfs interface for the goals. Finally, two patches for documentation follows. The seventh patch documents the design of the feature. The final eighth patch updates the usage document for the features. SeongJae Park (8): mm/damon/core: implement goal-oriented feedback-driven quota auto-tuning mm/damon/sysfs-schemes: implement scheme quota goals directory mm/damon/sysfs-schemes: commit damos quota goals user input to DAMOS quota auto-tuning mm/damon/sysfs-schemes: implement a command for scheme quota goals only commit mm/damon/core-test: add a unit test for the feedback loop algorithm selftests/damon: test quota goals directory Docs/mm/damon/design: Document DAMOS quota auto tuning Docs/admin-guide/mm/damon/usage: update for quota goals Documentation/admin-guide/mm/damon/usage.rst | 25 +- Documentation/mm/damon/design.rst | 11 + include/linux/damon.h | 19 ++ mm/damon/core-test.h | 32 +++ mm/damon/core.c | 65 ++++- mm/damon/sysfs-common.h | 3 + mm/damon/sysfs-schemes.c | 272 ++++++++++++++++++- mm/damon/sysfs.c | 27 ++ tools/testing/selftests/damon/sysfs.sh | 27 ++ 9 files changed, 463 insertions(+), 18 deletions(-) base-commit: 4f26b84c39fbc6b03208674681bfde06e0bce25a -- 2.34.1

1 year, 8 months

1
2
0 0

[PATCH v1] selftests: cgroup: Fixes a typo in a comment

by Atul Kumar Pant

Signed-off-by: Atul Kumar Pant <atulpant.linux(a)gmail.com> --- tools/testing/selftests/cgroup/test_freezer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c index ff519029f6f4..8845353aca53 100644 --- a/tools/testing/selftests/cgroup/test_freezer.c +++ b/tools/testing/selftests/cgroup/test_freezer.c @@ -740,7 +740,7 @@ static int test_cgfreezer_ptraced(const char *root) /* * cg_check_frozen(cgroup, true) will fail here, - * because the task in in the TRACEd state. + * because the task is in the TRACEd state. */ if (cg_freeze_wait(cgroup, false)) goto cleanup; -- 2.25.1

1 year, 8 months

2
1
0 0

[PATCH v6] selftests: rtc: Fixes rtctest error handling.

by Atul Kumar Pant

Adds a check to verify if the rtc device file is valid or not and prints a useful error message if the file is not accessible. Signed-off-by: Atul Kumar Pant <atulpant.linux(a)gmail.com> --- changes since v5: Updated error message to use strerror(). If the rtc file is invalid, the skip the test. changes since v4: Updated the commit message. changes since v3: Added Linux-kselftest and Linux-kernel mailing lists. changes since v2: Changed error message when rtc file does not exist. changes since v1: Removed check for uid=0 If rtc file is invalid, then exit the test. tools/testing/selftests/rtc/rtctest.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/rtc/rtctest.c b/tools/testing/selftests/rtc/rtctest.c index 630fef735c7e..27b466111885 100644 --- a/tools/testing/selftests/rtc/rtctest.c +++ b/tools/testing/selftests/rtc/rtctest.c @@ -15,6 +15,7 @@ #include <sys/types.h> #include <time.h> #include <unistd.h> +#include <error.h> #include "../kselftest_harness.h" #include "../kselftest.h" @@ -437,7 +438,7 @@ int main(int argc, char **argv) if (access(rtc_file, F_OK) == 0) ret = test_harness_run(argc, argv); else - ksft_exit_fail_msg("[ERROR]: Cannot access rtc file %s - Exiting\n", rtc_file); + ksft_exit_skip("%s: %s\n", rtc_file, strerror(errno)); return ret; } -- 2.25.1

1 year, 8 months

2
4
0 0

[PATCH v3 0/6] KVM RISC-V Conditional Operations

by Anup Patel

This series extends KVM RISC-V to allow Guest/VM discover and use conditional operations related ISA extensions (namely XVentanaCondOps and Zicond). To try these patches, use KVMTOOL from riscv_zbx_zicntr_smstateen_condops_v1 branch at: https://github.com/avpatel/kvmtool.git These patches are based upon the latest riscv_kvm_queue and can also be found in the riscv_kvm_condops_v3 branch at: https://github.com/avpatel/linux.git Changes since v2: - Dropped patch1, patch2, and patch5 since these patches don't meet the requirements of patch acceptance policy. Changes since v1: - Rebased the series on riscv_kvm_queue - Split PATCH1 and PATCH2 of v1 series into two patches - Added separate test configs for XVentanaCondOps and Zicond in PATCH7 of v1 series. Anup Patel (6): dt-bindings: riscv: Add Zicond extension entry RISC-V: Detect Zicond from ISA string RISC-V: KVM: Allow Zicond extension for Guest/VM KVM: riscv: selftests: Add senvcfg register to get-reg-list test KVM: riscv: selftests: Add smstateen registers to get-reg-list test KVM: riscv: selftests: Add condops extensions to get-reg-list test .../devicetree/bindings/riscv/extensions.yaml | 6 +++ arch/riscv/include/asm/hwcap.h | 1 + arch/riscv/include/uapi/asm/kvm.h | 1 + arch/riscv/kernel/cpufeature.c | 1 + arch/riscv/kvm/vcpu_onereg.c | 2 + .../selftests/kvm/riscv/get-reg-list.c | 54 +++++++++++++++++++ 6 files changed, 65 insertions(+) -- 2.34.1

1 year, 8 months

4
11
0 0

[RESEND PATCH 0/2] add loongarch and riscv support for kprobe args test

by Yu Liao

Yu Liao (2): selftests/ftrace: add loongarch support for kprobe args char tests selftests/ftrace: Add riscv support for kprobe arg tests .../selftests/ftrace/test.d/kprobe/kprobe_args_char.tc | 6 ++++++ .../selftests/ftrace/test.d/kprobe/kprobe_args_string.tc | 3 +++ .../selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc | 4 ++++ 3 files changed, 13 insertions(+) -- 2.25.1

1 year, 8 months

3
4
0 0

PSA: This list is being migrated (no action required)

by Konstantin Ryabitsev

Hello, all: This list is being migrated to new vger infrastructure. No action is required on your part and there will be no change in how you interact with this list after the migration is completed. There will be a short 30-minute delay to the list archives on lore.kernel.org. Once the backend work is done, I will follow up with another message. -K

1 year, 8 months

1
1
0 0

[PATCH] Kunit to check the longest symbol length

by Sergio González Collado

The longest length of a symbol (KSYM_NAME_LEN) was increased to 512 in the reference [1]. This patch adds a kunit test to check the longest symbol length. [1] https://lore.kernel.org/lkml/20220802015052.10452-6-ojeda@kernel.org/ Signed-off-by: Sergio González Collado <sergio.collado(a)gmail.com> --- lib/Kconfig.debug | 9 +++ lib/Makefile | 1 + lib/longest_symbol_kunit.c | 120 +++++++++++++++++++++++++++++++++++++ 3 files changed, 130 insertions(+) create mode 100644 lib/longest_symbol_kunit.c diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index fa307f93fa2e..7c0ae4373aa6 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2760,6 +2760,15 @@ config FORTIFY_KUNIT_TEST by the str*() and mem*() family of functions. For testing runtime traps of FORTIFY_SOURCE, see LKDTM's "FORTIFY_*" tests. +config LONGEST_SYM_KUNIT_TEST + tristate "Test the longest symbol possible" if !KUNIT_ALL_TESTS + depends on KUNIT && KPROBES + default KUNIT_ALL_TESTS + help + Tests the longest symbol possible + + If unsure, say N. + config HW_BREAKPOINT_KUNIT_TEST bool "Test hw_breakpoint constraints accounting" if !KUNIT_ALL_TESTS depends on HAVE_HW_BREAKPOINT diff --git a/lib/Makefile b/lib/Makefile index 740109b6e2c8..82ac084b6bc6 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -402,6 +402,7 @@ obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o obj-$(CONFIG_STRCAT_KUNIT_TEST) += strcat_kunit.o obj-$(CONFIG_STRSCPY_KUNIT_TEST) += strscpy_kunit.o obj-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o +obj-$(CONFIG_LONGEST_SYM_KUNIT_TEST) += longest_symbol_kunit.o obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o diff --git a/lib/longest_symbol_kunit.c b/lib/longest_symbol_kunit.c new file mode 100644 index 000000000000..6282fbb7e991 --- /dev/null +++ b/lib/longest_symbol_kunit.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test the longest symbol length. Execute with: + * ./tools/testing/kunit/kunit.py run longest-symbol + * --arch=x86_64 --kconfig_add CONFIG_KPROBES=y --kconfig_add CONFIG_MODULES=y + * --kconfig_add CONFIG_RETPOLINE=n + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <kunit/test.h> +#include <linux/stringify.h> +#include <linux/kprobes.h> +#include <linux/kallsyms.h> + +#define DI(name) s##name##name +#define DDI(name) DI(n##name##name) +#define DDDI(name) DDI(n##name##name) +#define DDDDI(name) DDDI(n##name##name) +#define DDDDDI(name) DDDDI(n##name##name) + +#define PLUS1(name) __PASTE(name, e) + +/*Generate a symbol whose name length is 511 */ +#define LONGEST_SYM_NAME DDDDDI(g1h2i3j4k5l6m7n) + +/*Generate a symbol whose name length is 512 */ +#define LONGEST_SYM_NAME_PLUS1 PLUS1(LONGEST_SYM_NAME) + +#define RETURN_LONGEST_SYM 0xAAAAA +#define RETURN_LONGEST_SYM_PLUS1 0x55555 + +noinline int LONGEST_SYM_NAME(void) +{ + return RETURN_LONGEST_SYM; +} + +noinline int LONGEST_SYM_NAME_PLUS1(void) +{ + return RETURN_LONGEST_SYM_PLUS1; +} + +_Static_assert(sizeof(__stringify(LONGEST_SYM_NAME)) == KSYM_NAME_LEN, +"Incorrect symbol length found. Expected KSYM_NAME_LEN: " +__stringify(KSYM_NAME) ", but found: " +__stringify(sizeof(LONGEST_SYM_NAME))); + +static void test_longest_symbol(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM, LONGEST_SYM_NAME()); +}; + +static void test_longest_symbol_kallsyms(struct kunit *test) +{ + unsigned long (*kallsyms_lookup_name)(const char *name); + static int (*longest_sym)(void); + + struct kprobe kp = { + .symbol_name = "kallsyms_lookup_name", + }; + + if (register_kprobe(&kp) < 0) { + pr_info("%s: kprobe not registered\n", __func__); + KUNIT_FAIL(test, "test_longest_symbol kallsysms: kprobe not registered\n"); + return; + } + + kunit_warn(test, "test_longest_symbol kallsyms: kprobe registered\n"); + kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr; + unregister_kprobe(&kp); + + longest_sym = + (void *) kallsyms_lookup_name(__stringify(LONGEST_SYM_NAME)); + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM, longest_sym()); +}; + +static void test_longest_symbol_plus1(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM_PLUS1, LONGEST_SYM_NAME_PLUS1()); +}; + +static void test_longest_symbol_plus1_kallsyms(struct kunit *test) +{ + unsigned long (*kallsyms_lookup_name)(const char *name); + static int (*longest_sym_plus1)(void); + + struct kprobe kp = { + .symbol_name = "kallsyms_lookup_name", + }; + + if (register_kprobe(&kp) < 0) { + pr_info("%s: kprobe not registered\n", __func__); + KUNIT_FAIL(test, "test_longest_symbol kallsysms: kprobe not registered\n"); + return; + } + + kunit_warn(test, "test_longest_symbol_plus1 kallsyms: kprobe registered\n"); + kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr; + unregister_kprobe(&kp); + + longest_sym_plus1 = + (void *) kallsyms_lookup_name(__stringify(LONGEST_SYM_NAME_PLUS1)); + KUNIT_EXPECT_NULL(test, longest_sym_plus1); +}; + +static struct kunit_case longest_symbol_test_cases[] = { + KUNIT_CASE(test_longest_symbol), + KUNIT_CASE(test_longest_symbol_kallsyms), + KUNIT_CASE(test_longest_symbol_plus1), + KUNIT_CASE(test_longest_symbol_plus1_kallsyms), + {} +}; + +static struct kunit_suite longest_symbol_test_suite = { + .name = "longest-symbol", + .test_cases = longest_symbol_test_cases, +}; +kunit_test_suite(longest_symbol_test_suite); + +MODULE_LICENSE("GPL"); -- 2.39.2

1 year, 8 months

4
6
0 0

[PATCH 0/2] Fuse submount_lookup needs to be initialized

by Krister Johansen

Hi Miklos, I got a couple of bug reports[1][2] this morning from teams that are tracking regresssions in linux-next. My patch 513dfacefd71 ("fuse: share lookup state between submount and its parent") is causing panics in the fuse unmount path. The reports came from users with SLUB_DEBUG enabled, and the additional debug sanitization catches the fact that the submount_lookup field isn't getting initialized which could lead to a subsequently bogus attempt to access the submount_lookup structure and adjust its refcount. I've added SLUB_DEBUG to my testing kconfig, and have reproduced the problem using the memfd self-test that was triggering the problem for both reporters. With the fix that follows this e-mail, I see no more erroneous accesses of poisoned slub memory. I'm a bit unsure of the desired approach for fixing these kinds of problems. I'm also away from the office on Nov 10th and Nov 13th, but expect to be back on the console on the Nov 14th. Given the gap, I've prepared a pair of patches, but we only need one. The first is simply a followup fix that addresses the problem in a subsequent one-line commit. If you'd rather revert the entire bad patch and go again, the second patch in the series is a v5 of the original with the submount_lookup initialization added. Either should do, but I wasn't sure which approach was preferable. Thanks, and my apologies for the inconvenience. -K [1] https://lore.kernel.org/linux-fsdevel/CA+G9fYue-dV7t-NrOhWwGshvyboXjb2B6HpC… [2] https://lore.kernel.org/intel-gfx/SJ1PR11MB6129508509896AD7D0E03114B9AFA@SJ…

1 year, 8 months

2
3
0 0

selftests: memfd: run_fuse_test.sh - fuse_evict_inode - fs/fuse/inode.c:162 - panic

by Naresh Kamboju

Following kernel panic noticed while running selftests: memfd: run_fuse_test.sh on arm64 Juno-r2 and x86 devices running Linux next-20231109. Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> log: --- # timeout set to 45 # selftests: memfd: run_fuse_test.sh # opening: ./mnt/memfd # fuse: DONE [ 1931.860330] Unable to handle kernel paging request at virtual address 005a5a5a5a5a5a5a [ 1931.868645] Mem abort info: [ 1931.871505] ESR = 0x0000000096000021 [ 1931.875311] EC = 0x25: DABT (current EL), IL = 32 bits [ 1931.880805] SET = 0, FnV = 0 [ 1931.883924] EA = 0, S1PTW = 0 [ 1931.887563] FSC = 0x21: alignment fault [ 1931.891618] Data abort info: [ 1931.894542] ISV = 0, ISS = 0x00000021, ISS2 = 0x00000000 [ 1931.900219] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 1931.905305] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 1931.910692] [005a5a5a5a5a5a5a] address between user and kernel address ranges [ 1931.918091] Internal error: Oops: 0000000096000021 [#1] PREEMPT SMP [ 1931.924375] Modules linked in: gpio_sim onboard_usb_hub tda998x hdlcd crct10dif_ce cec drm_dma_helper dm_mod [last unloaded: gpio_mockup] [ 1931.936789] CPU: 1 PID: 20739 Comm: fusermount Not tainted 6.6.0-next-20231109 #1 [ 1931.944295] Hardware name: ARM Juno development board (r2) (DT) [ 1931.950224] pstate: 40000005 (nZcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 1931.957205] pc : fuse_evict_inode (arch/arm64/include/asm/atomic_ll_sc.h:96 (discriminator 3) arch/arm64/include/asm/atomic.h:51 (discriminator 3) include/linux/atomic/atomic-arch-fallback.h:944 (discriminator 3) include/linux/atomic/atomic-instrumented.h:401 (discriminator 3) include/linux/refcount.h:272 (discriminator 3) include/linux/refcount.h:315 (discriminator 3) include/linux/refcount.h:333 (discriminator 3) fs/fuse/inode.c:137 (discriminator 3) fs/fuse/inode.c:166 (discriminator 3)) [ 1931.961586] lr : fuse_evict_inode (fs/fuse/inode.c:162) [ 1931.965868] sp : ffff80008792ba90 [ 1931.969189] x29: ffff80008792ba90 x28: ffff000800b58040 x27: 0000000000000000 [ 1931.976358] x26: 0000000000000000 x25: ffff800080508f98 x24: ffff80008316a008 [ 1931.983519] x23: ffff80008316a008 x22: ffff80008424a020 x21: ffff00082a514c00 [ 1931.990679] x20: 5a5a5a5a5a5a5a5a x19: ffff000838828780 x18: 0000000000000000 [ 1931.997840] x17: ffff80008050e610 x16: ffff80008050e5bc x15: ffff80008050e3e8 [ 1932.005003] x14: ffff80008050df10 x13: ffff800080769c60 x12: ffff8000851f6388 [ 1932.012165] x11: 0000000000000645 x10: 0000000000000645 x9 : ffff800081c0e0b4 [ 1932.019332] x8 : ffff80008792b988 x7 : 0000000000000000 x6 : ffff800084a75fe8 [ 1932.026495] x5 : 0000000000000000 x4 : 0000000000000001 x3 : ffff80008424a968 [ 1932.033659] x2 : 0000000000000002 x1 : ffff000800b58040 x0 : 0000000000000001 [ 1932.040820] Call trace: [ 1932.043272] fuse_evict_inode (arch/arm64/include/asm/atomic_ll_sc.h:96 (discriminator 3) arch/arm64/include/asm/atomic.h:51 (discriminator 3) include/linux/atomic/atomic-arch-fallback.h:944 (discriminator 3) include/linux/atomic/atomic-instrumented.h:401 (discriminator 3) include/linux/refcount.h:272 (discriminator 3) include/linux/refcount.h:315 (discriminator 3) include/linux/refcount.h:333 (discriminator 3) fs/fuse/inode.c:137 (discriminator 3) fs/fuse/inode.c:166 (discriminator 3)) [ 1932.047296] evict (fs/inode.c:669) [ 1932.050279] iput_final (fs/inode.c:1776) [ 1932.053694] iput.part.0 (fs/inode.c:1803) [ 1932.057280] iput (fs/inode.c:1803) [ 1932.060085] dentry_unlink_inode (fs/dcache.c:402) [ 1932.064281] __dentry_kill (arch/arm64/include/asm/current.h:19 arch/arm64/include/asm/preempt.h:47 fs/dcache.c:610) [ 1932.067956] shrink_dentry_list (include/linux/list.h:373 (discriminator 2) fs/dcache.c:1179 (discriminator 2)) [ 1932.072067] shrink_dcache_parent (fs/dcache.c:1652) [ 1932.076433] shrink_dcache_for_umount (fs/dcache.c:1682 fs/dcache.c:1698) [ 1932.081062] generic_shutdown_super (fs/super.c:647) [ 1932.085518] kill_anon_super (fs/super.c:1254) [ 1932.089277] fuse_kill_sb_anon (fs/fuse/fuse_i.h:895 fs/fuse/inode.c:1912) [ 1932.093298] deactivate_locked_super (fs/super.c:489) [ 1932.097753] deactivate_super (fs/super.c:522) [ 1932.101599] cleanup_mnt (fs/namespace.c:139 fs/namespace.c:1257) [ 1932.105097] __cleanup_mnt (fs/namespace.c:1264) [ 1932.108680] task_work_run (kernel/task_work.c:182) [ 1932.112266] do_notify_resume (include/linux/resume_user_mode.h:49 arch/arm64/kernel/signal.c:1305) [ 1932.116283] el0_svc (arch/arm64/kernel/entry-common.c:137 arch/arm64/kernel/entry-common.c:144 arch/arm64/kernel/entry-common.c:679) [ 1932.119345] el0t_64_sync_handler (arch/arm64/kernel/entry-common.c:697) [ 1932.123710] el0t_64_sync (arch/arm64/kernel/entry.S:595) [ 1932.127383] Code: f9026a7f 17ffffd9 52800020 f9800291 (885f7e81) All code ======== 0: f9026a7f str xzr, [x19, #1232] 4: 17ffffd9 b 0xffffffffffffff68 8: 52800020 mov w0, #0x1 // #1 c: f9800291 prfm pstl1strm, [x20] 10:* 885f7e81 ldxr w1, [x20] <-- trapping instruction Code starting with the faulting instruction =========================================== 0: 885f7e81 ldxr w1, [x20] [ 1932.133486] ---[ end trace 0000000000000000 ]--- [ 1932.138111] Kernel panic - not syncing: Oops: Fatal exception [ 1932.143867] SMP: stopping secondary CPUs [ 1932.148008] Kernel Offset: disabled [ 1932.151498] CPU features: 0x1,0000020c,3c020000,0100421b [ 1932.156820] Memory Limit: none [ 1932.159880] ---[ end Kernel panic - not syncing: Oops: Fatal exception ]--- Links: - https://lkft.validation.linaro.org/scheduler/job/7006578#L6164 - https://lkft.validation.linaro.org/scheduler/job/7006482#L9235 metadata: git_ref: master git_repo: https://gitlab.com/Linaro/lkft/mirrors/next/linux-next git_sha: b622d91ca201bf97582e9b09ebbaab005ecee86f git_describe: next-20231109 kernel_version: 6.6.0 kernel-config: https://storage.tuxsuite.com/public/linaro/lkft/builds/2Xv92VPrzXNNmQil9l8b… artifact-location: https://storage.tuxsuite.com/public/linaro/lkft/builds/2Xv92VPrzXNNmQil9l8b… toolchain: gcc-13 -- Linaro LKFT https://lkft.linaro.org

1 year, 8 months

2
1
0 0

[PATCH] selftests: sud_test: return correct emulated syscall value on RISC-V

by Clément Léger

Currently, the sud_test expects the emulated syscall to return the emulated syscall number. This assumption only works on architectures were the syscall calling convention use the same register for syscall number/syscall return value. This is not the case for RISC-V and thus the return value must be also emulated using the provided ucontext. Signed-off-by: Clément Léger <cleger(a)rivosinc.com> --- tools/testing/selftests/syscall_user_dispatch/sud_test.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c index b5d592d4099e..1b5553c19700 100644 --- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c +++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c @@ -158,6 +158,14 @@ static void handle_sigsys(int sig, siginfo_t *info, void *ucontext) /* In preparation for sigreturn. */ SYSCALL_DISPATCH_OFF(glob_sel); + + /* + * Modify interrupted context returned value according to syscall + * calling convention + */ +#if defined(__riscv) + ((ucontext_t*)ucontext)->uc_mcontext.__gregs[REG_A0] = MAGIC_SYSCALL_1; +#endif } TEST(dispatch_and_return) -- 2.40.1

1 year, 8 months

2
3
0 0

[PATCH v2] tools/nolibc: mips: add support for PIC

by Thomas Weißschuh

MIPS requires some extra instructions to set up the $gp register for the with a pointer to the global data area. This isn't needed for non-PIC builds, but this patch enables the code unconditionally to prevent bitrot. Also enable PIC in one of the test configurations for ongoing validation. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- Changes in v2: - Preserver 8-byte alignment of stack pointer - Link to v1: https://lore.kernel.org/r/20231108-nolibc-pic-v1-1-9b7a429d5a6d@weissschuh.… --- tools/include/nolibc/arch-mips.h | 7 ++++++- tools/testing/selftests/nolibc/Makefile | 2 +- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h index 3a2c76716b83..62cc50ef3288 100644 --- a/tools/include/nolibc/arch-mips.h +++ b/tools/include/nolibc/arch-mips.h @@ -184,8 +184,13 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_ __asm__ volatile ( ".set push\n" ".set noreorder\n" - ".option pic0\n" + "bal 1f\n" /* prime $ra for .cpload */ + "nop\n" + "1:\n" + ".cpload $ra\n" "move $a0, $sp\n" /* save stack pointer to $a0, as arg1 of _start_c */ + "addiu $sp, $sp, -4\n" /* space for .cprestore to store $gp */ + ".cprestore 0\n" "li $t0, -8\n" "and $sp, $sp, $t0\n" /* $sp must be 8-byte aligned */ "addiu $sp, $sp, -16\n" /* the callee expects to save a0..a3 there */ diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 508435b8ac2a..484bb02d8e6c 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -144,7 +144,7 @@ CFLAGS_ppc = -m32 -mbig-endian -mno-vsx $(call cc-option,-mmultiple) CFLAGS_ppc64 = -m64 -mbig-endian -mno-vsx $(call cc-option,-mmultiple) CFLAGS_ppc64le = -m64 -mlittle-endian -mno-vsx $(call cc-option,-mabi=elfv2) CFLAGS_s390 = -m64 -CFLAGS_mips32le = -EL -mabi=32 +CFLAGS_mips32le = -EL -mabi=32 -fPIC CFLAGS_mips32be = -EB -mabi=32 CFLAGS_STACKPROTECTOR ?= $(call cc-option,-mstack-protector-guard=global $(call cc-option,-fstack-protector-all)) CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 -W -Wall -Wextra \ --- base-commit: ba335752620565c25c3028fff9496bb8ef373602 change-id: 20770914-nolibc-pic-30043ffb0403 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

1 year, 8 months

1
0
0 0

[PATCH] tools/nolibc: mips: add support for PIC

by Thomas Weißschuh

MIPS requires some extra instructions to set up the $gp register for the with a pointer to the global data area. This isn't needed for non-PIC builds, but this patch enables the code unconditionally to prevent bitrot. Also enable PIC in one of the test configurations for ongoing validation. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- tools/include/nolibc/arch-mips.h | 7 ++++++- tools/testing/selftests/nolibc/Makefile | 2 +- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h index 3a2c76716b83..e9a01847c2b8 100644 --- a/tools/include/nolibc/arch-mips.h +++ b/tools/include/nolibc/arch-mips.h @@ -184,10 +184,15 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_ __asm__ volatile ( ".set push\n" ".set noreorder\n" - ".option pic0\n" + "bal 1f\n" /* prime $ra for .cpload */ + "nop\n" + "1:\n" + ".cpload $ra\n" "move $a0, $sp\n" /* save stack pointer to $a0, as arg1 of _start_c */ "li $t0, -8\n" "and $sp, $sp, $t0\n" /* $sp must be 8-byte aligned */ + "addiu $sp, $sp, -4\n" /* space for .cprestore to store $gp */ + ".cprestore 0\n" "addiu $sp, $sp, -16\n" /* the callee expects to save a0..a3 there */ "jal _start_c\n" /* transfer to c runtime */ " nop\n" /* delayed slot */ diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 508435b8ac2a..484bb02d8e6c 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -144,7 +144,7 @@ CFLAGS_ppc = -m32 -mbig-endian -mno-vsx $(call cc-option,-mmultiple) CFLAGS_ppc64 = -m64 -mbig-endian -mno-vsx $(call cc-option,-mmultiple) CFLAGS_ppc64le = -m64 -mlittle-endian -mno-vsx $(call cc-option,-mabi=elfv2) CFLAGS_s390 = -m64 -CFLAGS_mips32le = -EL -mabi=32 +CFLAGS_mips32le = -EL -mabi=32 -fPIC CFLAGS_mips32be = -EB -mabi=32 CFLAGS_STACKPROTECTOR ?= $(call cc-option,-mstack-protector-guard=global $(call cc-option,-fstack-protector-all)) CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 -W -Wall -Wextra \ --- base-commit: ba335752620565c25c3028fff9496bb8ef373602 change-id: 20770914-nolibc-pic-30043ffb0403 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

1 year, 8 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror