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

[PATCH bpf-next v1 1/2] bpf: Restrict usage scope of bpf_get_cgroup_classid

by Jiayuan Chen

A previous commit expanded the usage scope of bpf_get_cgroup_classid() to all contexts (see Fixes tag), but this was inappropriate. First, syzkaller reported a bug [1]. Second, it uses skb as an argument, but its implementation varies across different bpf prog types. For example, in sock_filter and sock_addr, it retrieves the classid from the current context (bpf_get_cgroup_classid_curr_proto) instead of from skb. In tc egress and lwt, it fetches the classid from skb->sk, but in tc ingress, it returns 0. In summary, the definition of bpf_get_cgroup_classid() is ambiguous and its usage scenarios are limited. It should not be treated as a general-purpose helper. This patch reverts part of the previous commit. [1] https://syzkaller.appspot.com/bug?extid=9767c7ed68b95cfa69e6 Fixes: ee971630f20f ("bpf: Allow some trace helpers for all prog types") Reported-by: syzbot+9767c7ed68b95cfa69e6(a)syzkaller.appspotmail.com Signed-off-by: Jiayuan Chen <jiayuan.chen(a)linux.dev> --- include/linux/bpf-cgroup.h | 8 ++++++++ kernel/bpf/cgroup.c | 25 +++++++++++++++++++++++++ kernel/bpf/helpers.c | 4 ---- 3 files changed, 33 insertions(+), 4 deletions(-) diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 4847dcade917..9de7adb68294 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -427,6 +427,8 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, const struct bpf_func_proto * cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); +const struct bpf_func_proto * +cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); #else static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } @@ -463,6 +465,12 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } +static inline const struct bpf_func_proto * +cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return NULL; +} + static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 62a1d8deb3dc..a99b72e6f1c9 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1653,6 +1653,10 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) if (func_proto) return func_proto; + func_proto = cgroup_current_func_proto(func_id, prog); + if (func_proto) + return func_proto; + switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; @@ -2200,6 +2204,10 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) if (func_proto) return func_proto; + func_proto = cgroup_current_func_proto(func_id, prog); + if (func_proto) + return func_proto; + switch (func_id) { case BPF_FUNC_sysctl_get_name: return &bpf_sysctl_get_name_proto; @@ -2343,6 +2351,10 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) if (func_proto) return func_proto; + func_proto = cgroup_current_func_proto(func_id, prog); + if (func_proto) + return func_proto; + switch (func_id) { #ifdef CONFIG_NET case BPF_FUNC_get_netns_cookie: @@ -2589,3 +2601,16 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } } + +const struct bpf_func_proto * +cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { +#ifdef CONFIG_CGROUP_NET_CLASSID + case BPF_FUNC_get_cgroup_classid: + return &bpf_get_cgroup_classid_curr_proto; +#endif + default: + return NULL; + } +} diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index b71e428ad936..9d0d54f4f0de 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2024,10 +2024,6 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_ancestor_cgroup_id_proto; case BPF_FUNC_current_task_under_cgroup: return &bpf_current_task_under_cgroup_proto; -#endif -#ifdef CONFIG_CGROUP_NET_CLASSID - case BPF_FUNC_get_cgroup_classid: - return &bpf_get_cgroup_classid_curr_proto; #endif case BPF_FUNC_task_storage_get: if (bpf_prog_check_recur(prog)) -- 2.47.1

5 months, 3 weeks

2
2
0 0

[PATCH v7 0/8] ublk: decouple server threads from ublk_queues/hctxs

by Uday Shankar

This patch set aims to allow ublk server threads to better balance load amongst themselves by decoupling server threads from ublk_queues/hctxs, so that multiple threads can service I/Os that are issued from a single CPU. This can improve performance for workloads in which ublk server CPU is a bottleneck, and for which load is issued from CPUs which are not balanced across ublk_queues/hctxs. Performance ----------- First create two ublk devices with: ublkb0: ./kublk add -t null -q 2 --nthreads 2 ublkb1: ./kublk add -t null -q 2 --nthreads 2 --per_io_tasks Then run load with: taskset -c 1 fio/t/io_uring -r5 -p0 /dev/ublkb0: 1.90M IOPS taskset -c 1 fio/t/io_uring -r5 -p0 /dev/ublkb1: 2.18M IOPS Since ublkb1 has per-io-tasks, the second command is able to make use of both ublk server worker threads and therefore has increased max throughput. Caveats: - This testing was done on a system with 2 numa nodes, but the penalty of having I/O cross a numa (or LLC) boundary in the per_io_tasks case is quite high. So these numbers were obtained after moving all ublk server threads and the application threads to CPUs on the same numa node/LLC. - One might expect the scaling to be linear - because ublkb1 can make use of twice as many ublk server threads, it should be able to drive twice the throughput. However this is not true (the improvement is ~15%), and needs further investigation. Signed-off-by: Uday Shankar <ushankar(a)purestorage.com> --- Changes in v7: - Fix queue_rqs batch dispatch for per-io daemons - Kick round-robin tag allocation changes to a followup - Add explicit feature flag for per-task daemons (Ming Lei, Caleb Sander Mateos) - Move some variable assignments to avoid redundant computation (Caleb Sander Mateos) - Switch from storing pointers in ublk_io to computing based on address with container_of in a couple places (Ming Lei) - Link to v6: https://lore.kernel.org/r/20250507-ublk_task_per_io-v6-0-a2a298783c01@pures… Changes in v6: - Add a feature flag for this feature, called UBLK_F_RR_TAGS (Ming Lei) - Add test for this feature (Ming Lei) - Add documentation for this feature (Ming Lei) - Link to v5: https://lore.kernel.org/r/20250416-ublk_task_per_io-v5-0-9261ad7bff20@pures… Changes in v5: - Set io->task before ublk_mark_io_ready (Caleb Sander Mateos) - Set io->task atomically, read it atomically when needed - Return 0 on success from command-specific helpers in __ublk_ch_uring_cmd (Caleb Sander Mateos) - Rename ublk_handle_need_get_data to ublk_get_data (Caleb Sander Mateos) - Link to v4: https://lore.kernel.org/r/20250415-ublk_task_per_io-v4-0-54210b91a46f@pures… Changes in v4: - Drop "ublk: properly serialize all FETCH_REQs" since Ming is taking it in another set - Prevent data races by marking data structures which should be read-only in the I/O path as const (Ming Lei) - Link to v3: https://lore.kernel.org/r/20250410-ublk_task_per_io-v3-0-b811e8f4554a@pures… Changes in v3: - Check for UBLK_IO_FLAG_ACTIVE on I/O again after taking lock to ensure that two concurrent FETCH_REQs on the same I/O can't succeed (Caleb Sander Mateos) - Link to v2: https://lore.kernel.org/r/20250408-ublk_task_per_io-v2-0-b97877e6fd50@pures… Changes in v2: - Remove changes split into other patches - To ease error handling/synchronization, associate each I/O (instead of each queue) to the last task that issues a FETCH_REQ against it. Only that task is allowed to operate on the I/O. - Link to v1: https://lore.kernel.org/r/20241002224437.3088981-1-ushankar@purestorage.com --- Uday Shankar (8): ublk: have a per-io daemon instead of a per-queue daemon selftests: ublk: kublk: plumb q_id in io_uring user_data selftests: ublk: kublk: tie sqe allocation to io instead of queue selftests: ublk: kublk: lift queue initialization out of thread selftests: ublk: kublk: move per-thread data out of ublk_queue selftests: ublk: kublk: decouple ublk_queues from ublk server threads selftests: ublk: add test for per io daemons Documentation: ublk: document UBLK_F_PER_IO_DAEMON Documentation/block/ublk.rst | 35 ++- drivers/block/ublk_drv.c | 108 +++---- include/uapi/linux/ublk_cmd.h | 9 + tools/testing/selftests/ublk/Makefile | 1 + tools/testing/selftests/ublk/fault_inject.c | 4 +- tools/testing/selftests/ublk/file_backed.c | 20 +- tools/testing/selftests/ublk/kublk.c | 345 ++++++++++++++------- tools/testing/selftests/ublk/kublk.h | 73 +++-- tools/testing/selftests/ublk/null.c | 22 +- tools/testing/selftests/ublk/stripe.c | 17 +- tools/testing/selftests/ublk/test_generic_12.sh | 55 ++++ .../selftests/ublk/trace/count_ios_per_tid.bt | 11 + 12 files changed, 470 insertions(+), 230 deletions(-) --- base-commit: 533c87e2ed742454957f14d7bef9f48d5a72e72d change-id: 20250408-ublk_task_per_io-c693cf608d7a Best regards, -- Uday Shankar <ushankar(a)purestorage.com>

5 months, 3 weeks

3
17
0 0

[PATCH bpf-next 2/2] selftests/bpf: Add selftests for bpf_task_cwd_from_pid()

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Add some selftest testcases that validate the expected behavior of the bpf_task_cwd_from_pid() kfunc that was added in the prior patch. Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- .../selftests/bpf/prog_tests/task_kfunc.c | 3 ++ .../selftests/bpf/progs/task_kfunc_common.h | 1 + .../selftests/bpf/progs/task_kfunc_success.c | 47 +++++++++++++++++++ 3 files changed, 51 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c index 83b90335967a..c18a0cb67164 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c +++ b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c @@ -149,6 +149,9 @@ static const char * const success_tests[] = { "task_kfunc_acquire_trusted_walked", "test_task_kfunc_flavor_relo", "test_task_kfunc_flavor_relo_not_found", + "test_task_cwd_from_pid_arg", + "test_task_cwd_from_pid", + "test_task_cwd_from_pid_current", }; static const char * const vpid_success_tests[] = { diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_common.h b/tools/testing/selftests/bpf/progs/task_kfunc_common.h index e9c4fea7a4bb..b762054a1825 100644 --- a/tools/testing/selftests/bpf/progs/task_kfunc_common.h +++ b/tools/testing/selftests/bpf/progs/task_kfunc_common.h @@ -24,6 +24,7 @@ struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym; void bpf_task_release(struct task_struct *p) __ksym; struct task_struct *bpf_task_from_pid(s32 pid) __ksym; struct task_struct *bpf_task_from_vpid(s32 vpid) __ksym; +int bpf_task_cwd_from_pid(s32 pid, char *buf, u32 buf_len) __ksym; void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_success.c b/tools/testing/selftests/bpf/progs/task_kfunc_success.c index 5fb4fc19d26a..6424cf5c151e 100644 --- a/tools/testing/selftests/bpf/progs/task_kfunc_success.c +++ b/tools/testing/selftests/bpf/progs/task_kfunc_success.c @@ -351,6 +351,53 @@ int BPF_PROG(test_task_from_pid_invalid, struct task_struct *task, u64 clone_fla return 0; } +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_cwd_from_pid_arg, struct task_struct *task, u64 clone_flags) +{ + char cwd[256]; + + if (!is_test_kfunc_task()) + return 0; + + err = 0; + err += bpf_task_cwd_from_pid(task->pid, NULL, sizeof(cwd)) != -EINVAL; + err += bpf_task_cwd_from_pid(task->pid, cwd, 0) != -EINVAL; + err += bpf_task_cwd_from_pid(-1, cwd, sizeof(cwd)) != -ESRCH; + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_cwd_from_pid, struct task_struct *task, u64 clone_flags) +{ + char cwd[256]; + + if (!is_test_kfunc_task()) + return 0; + + err = bpf_task_cwd_from_pid(task->pid, cwd, sizeof(cwd)); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_cwd_from_pid_current, struct task_struct *task, u64 clone_flags) +{ + char cwd[128], cwd2[128]; + struct task_struct *current; + + if (!is_test_kfunc_task()) + return 0; + + current = bpf_get_current_task_btf(); + + err = 0; + err += bpf_task_cwd_from_pid(task->pid, cwd, sizeof(cwd)); + err += bpf_task_cwd_from_pid(current->pid, cwd2, sizeof(cwd2)); + + err += bpf_strncmp(cwd, sizeof(cwd), cwd2) != 0; + + return 0; +} + SEC("tp_btf/task_newtask") int BPF_PROG(task_kfunc_acquire_trusted_walked, struct task_struct *task, u64 clone_flags) { -- 2.49.0

5 months, 3 weeks

1
0
0 0

[PATCH bpf-next 0/2] Add kfunc for doing pid -> task cwd

by Rong Tao

In some application like bpftrace [1], need to get the cwd from the pid. This patch provides a new kfunc that can get the cwd of the process from the pid. [1] https://github.com/bpftrace/bpftrace/issues/3314 Rong Tao (2): bpf: Add bpf_task_cwd_from_pid() kfunc selftests/bpf: Add selftests for bpf_task_cwd_from_pid() kernel/bpf/helpers.c | 45 ++++++++++++++++++ .../selftests/bpf/prog_tests/task_kfunc.c | 3 ++ .../selftests/bpf/progs/task_kfunc_common.h | 1 + .../selftests/bpf/progs/task_kfunc_success.c | 47 +++++++++++++++++++ 4 files changed, 96 insertions(+) -- 2.49.0

5 months, 3 weeks

1
0
0 0

[PATCH net-next] selftest: Add selftest for multicast address notifications

by Yuyang Huang

This commit adds a new kernel selftest to verify RTNLGRP_IPV4_MCADDR and RTNLGRP_IPV6_MCADDR notifications. The test works by adding and removing a dummy interface and then confirming that the system correctly receives join and removal notifications for the 224.0.0.1 and ff02::1 multicast addresses. The test relies on the iproute2 version to be 6.13+. Tested by the following command: $ vng -v --user root --cpus 16 -- \ make -C tools/testing/selftests TARGETS=net TEST_PROGS=rtnetlink.sh \ TEST_GEN_PROGS="" run_tests Cc: Maciej Żenczykowski <maze(a)google.com> Cc: Lorenzo Colitti <lorenzo(a)google.com> Signed-off-by: Yuyang Huang <yuyanghuang(a)google.com> --- tools/testing/selftests/net/rtnetlink.sh | 34 ++++++++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 2e8243a65b50..9dbcaaeaf8cd 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -21,6 +21,7 @@ ALL_TESTS=" kci_test_vrf kci_test_encap kci_test_macsec + kci_test_mcast_addr_notification kci_test_ipsec kci_test_ipsec_offload kci_test_fdb_get @@ -1334,6 +1335,39 @@ kci_test_mngtmpaddr() return $ret } +kci_test_mcast_addr_notification() +{ + local tmpfile + local monitor_pid + local match_result + + tmpfile=$(mktemp) + + ip monitor maddr > $tmpfile & + monitor_pid=$! + sleep 1 + + run_cmd ip link add name test-dummy1 type dummy + run_cmd ip link set test-dummy1 up + run_cmd ip link del dev test-dummy1 + sleep 1 + + match_result=$(grep -cE "test-dummy1.*(224.0.0.1|ff02::1)" $tmpfile) + + kill $monitor_pid + rm $tmpfile + # There should be 4 line matches as follows. + # 13: test-dummy1 inet6 mcast ff02::1 scope global + # 13: test-dummy1 inet mcast 224.0.0.1 scope global + # Deleted 13: test-dummy1 inet mcast 224.0.0.1 scope global + # Deleted 13: test-dummy1 inet6 mcast ff02::1 scope global + if [ $match_result -ne 4 ];then + end_test "FAIL: mcast addr notification" + return 1 + fi + end_test "PASS: mcast addr notification" +} + kci_test_rtnl() { local current_test -- 2.49.0.1204.g71687c7c1d-goog

5 months, 3 weeks

2
2
0 0

[PATCH v1] selftests/mm: two fixes for the pfnmap test

by David Hildenbrand

When unregistering the signal handler, we have to pass SIG_DFL, and blindly reading from PFN 0 and PFN 1 seems to be problematic on !x86 systems. In particularly, on arm64 tx2 machines where noting resides at these physical memory locations, we can generate RAS errors. Let's fix it by scanning /proc/iomem for actual "System RAM". Reported-by: Ryan Roberts <ryan.roberts(a)arm.com> Closes: https://lore.kernel.org/all/232960c2-81db-47ca-a337-38c4bce5f997@arm.com/T/… Fixes: 2616b370323a ("selftests/mm: add simple VM_PFNMAP tests based on mmap'ing /dev/mem") Reviewed-by: Ryan Roberts <ryan.roberts(a)arm.com> Tested-by: Aishwarya TCV <aishwarya.tcv(a)arm.com> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Signed-off-by: David Hildenbrand <david(a)redhat.com> --- tools/testing/selftests/mm/pfnmap.c | 61 +++++++++++++++++++++++++++-- 1 file changed, 57 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/mm/pfnmap.c b/tools/testing/selftests/mm/pfnmap.c index 8a9d19b6020c7..866ac023baf5c 100644 --- a/tools/testing/selftests/mm/pfnmap.c +++ b/tools/testing/selftests/mm/pfnmap.c @@ -12,6 +12,8 @@ #include <stdint.h> #include <unistd.h> #include <errno.h> +#include <stdio.h> +#include <ctype.h> #include <fcntl.h> #include <signal.h> #include <setjmp.h> @@ -43,14 +45,62 @@ static int test_read_access(char *addr, size_t size, size_t pagesize) /* Force a read that the compiler cannot optimize out. */ *((volatile char *)(addr + offs)); } - if (signal(SIGSEGV, signal_handler) == SIG_ERR) + if (signal(SIGSEGV, SIG_DFL) == SIG_ERR) return -EINVAL; return ret; } +static int find_ram_target(off_t *phys_addr, + unsigned long long pagesize) +{ + unsigned long long start, end; + char line[80], *end_ptr; + FILE *file; + + /* Search /proc/iomem for the first suitable "System RAM" range. */ + file = fopen("/proc/iomem", "r"); + if (!file) + return -errno; + + while (fgets(line, sizeof(line), file)) { + /* Ignore any child nodes. */ + if (!isalnum(line[0])) + continue; + + if (!strstr(line, "System RAM\n")) + continue; + + start = strtoull(line, &end_ptr, 16); + /* Skip over the "-" */ + end_ptr++; + /* Make end "exclusive". */ + end = strtoull(end_ptr, NULL, 16) + 1; + + /* Actual addresses are not exported */ + if (!start && !end) + break; + + /* We need full pages. */ + start = (start + pagesize - 1) & ~(pagesize - 1); + end &= ~(pagesize - 1); + + if (start != (off_t)start) + break; + + /* We need two pages. */ + if (end > start + 2 * pagesize) { + fclose(file); + *phys_addr = start; + return 0; + } + } + return -ENOENT; +} + FIXTURE(pfnmap) { + off_t phys_addr; size_t pagesize; int dev_mem_fd; char *addr1; @@ -63,14 +113,17 @@ FIXTURE_SETUP(pfnmap) { self->pagesize = getpagesize(); + /* We'll require two physical pages throughout our tests ... */ + if (find_ram_target(&self->phys_addr, self->pagesize)) + SKIP(return, "Cannot find ram target in '/proc/iomem'\n"); + self->dev_mem_fd = open("/dev/mem", O_RDONLY); if (self->dev_mem_fd < 0) SKIP(return, "Cannot open '/dev/mem'\n"); - /* We'll require the first two pages throughout our tests ... */ self->size1 = self->pagesize * 2; self->addr1 = mmap(NULL, self->size1, PROT_READ, MAP_SHARED, - self->dev_mem_fd, 0); + self->dev_mem_fd, self->phys_addr); if (self->addr1 == MAP_FAILED) SKIP(return, "Cannot mmap '/dev/mem'\n"); @@ -129,7 +182,7 @@ TEST_F(pfnmap, munmap_split) */ self->size2 = self->pagesize; self->addr2 = mmap(NULL, self->pagesize, PROT_READ, MAP_SHARED, - self->dev_mem_fd, 0); + self->dev_mem_fd, self->phys_addr); ASSERT_NE(self->addr2, MAP_FAILED); } -- 2.49.0

5 months, 3 weeks

1
0
0 0

[PATCH v2] selftests/mm: add simple VM_PFNMAP tests based on mmap'ing /dev/mem

by David Hildenbrand

Let's test some basic functionality using /dev/mem. These tests will implicitly cover some PAT (Page Attribute Handling) handling on x86. These tests will only run when /dev/mem access to the first two pages in physical address space is possible and allowed; otherwise, the tests are skipped. On current x86-64 with PAT inside a VM, all tests pass: TAP version 13 1..6 # Starting 6 tests from 1 test cases. # RUN pfnmap.madvise_disallowed ... # OK pfnmap.madvise_disallowed ok 1 pfnmap.madvise_disallowed # RUN pfnmap.munmap_split ... # OK pfnmap.munmap_split ok 2 pfnmap.munmap_split # RUN pfnmap.mremap_fixed ... # OK pfnmap.mremap_fixed ok 3 pfnmap.mremap_fixed # RUN pfnmap.mremap_shrink ... # OK pfnmap.mremap_shrink ok 4 pfnmap.mremap_shrink # RUN pfnmap.mremap_expand ... # OK pfnmap.mremap_expand ok 5 pfnmap.mremap_expand # RUN pfnmap.fork ... # OK pfnmap.fork ok 6 pfnmap.fork # PASSED: 6 / 6 tests passed. # Totals: pass:6 fail:0 xfail:0 xpass:0 skip:0 error:0 However, we are able to trigger: [ 27.888251] x86/PAT: pfnmap:1790 freeing invalid memtype [mem 0x00000000-0x00000fff] There are probably more things worth testing in the future, such as MAP_PRIVATE handling. But this set of tests is sufficient to cover most of the things we will rework regarding PAT handling. Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: Dev Jain <dev.jain(a)arm.com> Signed-off-by: David Hildenbrand <david(a)redhat.com> --- Hopefully I didn't miss any review feedback. v1 -> v2: * Rewrite using kselftest_harness, which simplifies a lot of things * Add to .gitignore and run_vmtests.sh * Register signal handler on demand * Use volatile trick to force a read (not factoring out FORCE_READ just yet) * Drop mprotect() test case * Add some more comments why we test certain things * Use NULL for mmap() first parameter instead of 0 * Smaller fixes --- tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/pfnmap.c | 196 ++++++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 4 + 4 files changed, 202 insertions(+) create mode 100644 tools/testing/selftests/mm/pfnmap.c diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 91db34941a143..824266982aa36 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -20,6 +20,7 @@ mremap_test on-fault-limit transhuge-stress pagemap_ioctl +pfnmap *.tmp* protection_keys protection_keys_32 diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index ad4d6043a60f0..ae6f994d3add7 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -84,6 +84,7 @@ TEST_GEN_FILES += mremap_test TEST_GEN_FILES += mseal_test TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl +TEST_GEN_FILES += pfnmap TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += uffd-stress diff --git a/tools/testing/selftests/mm/pfnmap.c b/tools/testing/selftests/mm/pfnmap.c new file mode 100644 index 0000000000000..8a9d19b6020c7 --- /dev/null +++ b/tools/testing/selftests/mm/pfnmap.c @@ -0,0 +1,196 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Basic VM_PFNMAP tests relying on mmap() of '/dev/mem' + * + * Copyright 2025, Red Hat, Inc. + * + * Author(s): David Hildenbrand <david(a)redhat.com> + */ +#define _GNU_SOURCE +#include <stdlib.h> +#include <string.h> +#include <stdint.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <signal.h> +#include <setjmp.h> +#include <linux/mman.h> +#include <sys/mman.h> +#include <sys/wait.h> + +#include "../kselftest_harness.h" +#include "vm_util.h" + +static sigjmp_buf sigjmp_buf_env; + +static void signal_handler(int sig) +{ + siglongjmp(sigjmp_buf_env, -EFAULT); +} + +static int test_read_access(char *addr, size_t size, size_t pagesize) +{ + size_t offs; + int ret; + + if (signal(SIGSEGV, signal_handler) == SIG_ERR) + return -EINVAL; + + ret = sigsetjmp(sigjmp_buf_env, 1); + if (!ret) { + for (offs = 0; offs < size; offs += pagesize) + /* Force a read that the compiler cannot optimize out. */ + *((volatile char *)(addr + offs)); + } + if (signal(SIGSEGV, signal_handler) == SIG_ERR) + return -EINVAL; + + return ret; +} + +FIXTURE(pfnmap) +{ + size_t pagesize; + int dev_mem_fd; + char *addr1; + size_t size1; + char *addr2; + size_t size2; +}; + +FIXTURE_SETUP(pfnmap) +{ + self->pagesize = getpagesize(); + + self->dev_mem_fd = open("/dev/mem", O_RDONLY); + if (self->dev_mem_fd < 0) + SKIP(return, "Cannot open '/dev/mem'\n"); + + /* We'll require the first two pages throughout our tests ... */ + self->size1 = self->pagesize * 2; + self->addr1 = mmap(NULL, self->size1, PROT_READ, MAP_SHARED, + self->dev_mem_fd, 0); + if (self->addr1 == MAP_FAILED) + SKIP(return, "Cannot mmap '/dev/mem'\n"); + + /* ... and want to be able to read from them. */ + if (test_read_access(self->addr1, self->size1, self->pagesize)) + SKIP(return, "Cannot read-access mmap'ed '/dev/mem'\n"); + + self->size2 = 0; + self->addr2 = MAP_FAILED; +} + +FIXTURE_TEARDOWN(pfnmap) +{ + if (self->addr2 != MAP_FAILED) + munmap(self->addr2, self->size2); + if (self->addr1 != MAP_FAILED) + munmap(self->addr1, self->size1); + if (self->dev_mem_fd >= 0) + close(self->dev_mem_fd); +} + +TEST_F(pfnmap, madvise_disallowed) +{ + int advices[] = { + MADV_DONTNEED, + MADV_DONTNEED_LOCKED, + MADV_FREE, + MADV_WIPEONFORK, + MADV_COLD, + MADV_PAGEOUT, + MADV_POPULATE_READ, + MADV_POPULATE_WRITE, + }; + int i; + + /* All these advices must be rejected. */ + for (i = 0; i < ARRAY_SIZE(advices); i++) { + EXPECT_LT(madvise(self->addr1, self->pagesize, advices[i]), 0); + EXPECT_EQ(errno, EINVAL); + } +} + +TEST_F(pfnmap, munmap_split) +{ + /* + * Unmap the first page. This munmap() call is not really expected to + * fail, but we might be able to trigger other internal issues. + */ + ASSERT_EQ(munmap(self->addr1, self->pagesize), 0); + + /* + * Remap the first page while the second page is still mapped. This + * makes sure that any PAT tracking on x86 will allow for mmap()'ing + * a page again while some parts of the first mmap() are still + * around. + */ + self->size2 = self->pagesize; + self->addr2 = mmap(NULL, self->pagesize, PROT_READ, MAP_SHARED, + self->dev_mem_fd, 0); + ASSERT_NE(self->addr2, MAP_FAILED); +} + +TEST_F(pfnmap, mremap_fixed) +{ + char *ret; + + /* Reserve a destination area. */ + self->size2 = self->size1; + self->addr2 = mmap(NULL, self->size2, PROT_READ, MAP_ANON | MAP_PRIVATE, + -1, 0); + ASSERT_NE(self->addr2, MAP_FAILED); + + /* mremap() over our destination. */ + ret = mremap(self->addr1, self->size1, self->size2, + MREMAP_FIXED | MREMAP_MAYMOVE, self->addr2); + ASSERT_NE(ret, MAP_FAILED); +} + +TEST_F(pfnmap, mremap_shrink) +{ + char *ret; + + /* Shrinking is expected to work. */ + ret = mremap(self->addr1, self->size1, self->size1 - self->pagesize, 0); + ASSERT_NE(ret, MAP_FAILED); +} + +TEST_F(pfnmap, mremap_expand) +{ + /* + * Growing is not expected to work, and getting it right would + * be challenging. So this test primarily serves as an early warning + * that something that probably should never work suddenly works. + */ + self->size2 = self->size1 + self->pagesize; + self->addr2 = mremap(self->addr1, self->size1, self->size2, MREMAP_MAYMOVE); + ASSERT_EQ(self->addr2, MAP_FAILED); +} + +TEST_F(pfnmap, fork) +{ + pid_t pid; + int ret; + + /* fork() a child and test if the child can access the pages. */ + pid = fork(); + ASSERT_GE(pid, 0); + + if (!pid) { + EXPECT_EQ(test_read_access(self->addr1, self->size1, + self->pagesize), 0); + exit(0); + } + + wait(&ret); + if (WIFEXITED(ret)) + ret = WEXITSTATUS(ret); + else + ret = -EINVAL; + ASSERT_EQ(ret, 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 188b125bf1f6b..dddd1dd8af145 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -63,6 +63,8 @@ separated by spaces: test soft dirty page bit semantics - pagemap test pagemap_scan IOCTL +- pfnmap + tests for VM_PFNMAP handling - cow test copy-on-write semantics - thp @@ -472,6 +474,8 @@ fi CATEGORY="pagemap" run_test ./pagemap_ioctl +CATEGORY="pfnmap" run_test ./pfnmap + # COW tests CATEGORY="cow" run_test ./cow -- 2.49.0

5 months, 3 weeks

4
12
0 0

[PATCH v2] rust: kunit: use crate-level mapping for `c_void`

by Jesung Yang

Use `kernel::ffi::c_void` instead of `core::ffi::c_void` for consistency and to centralize abstraction. Since `kernel::ffi::c_void` is a straightforward re-export of `core::ffi::c_void`, both are functionally equivalent. However, using `kernel::ffi::c_void` improves consistency across the kernel's Rust code and provides a unified reference point in case the definition ever needs to change, even if such a change is unlikely. Signed-off-by: Jesung Yang <y.j3ms.n(a)gmail.com> Link: https://rust-for-linux.zulipchat.com/#narrow/channel/288089/topic/x/near/52… --- So in sum, I believe it's reasonable to keep the diff unchanged... but I'm happy to adjust if you'd prefer a different approach. --- Changes in v2: - Add "Link" tag to the related discussion on Zulip - Reword the commit message to clarify `kernel::ffi::c_void` is a re-export - Link to v1: https://lore.kernel.org/rust-for-linux/20250526162429.1114862-1-y.j3ms.n@gm… --- rust/kernel/kunit.rs | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs index 81833a687b75..bd6fc712dd79 100644 --- a/rust/kernel/kunit.rs +++ b/rust/kernel/kunit.rs @@ -6,7 +6,8 @@ //! //! Reference: <https://docs.kernel.org/dev-tools/kunit/index.html> -use core::{ffi::c_void, fmt}; +use core::fmt; +use kernel::ffi::c_void; /// Prints a KUnit error-level message. /// base-commit: f4daa80d6be7d3c55ca72a8e560afc4e21f886aa -- 2.39.5

5 months, 3 weeks

3
2
0 0

[PATCH] rust: replace length checks with match

by Tamir Duberstein

Use a match expression with slice patterns instead of length checks and indexing. The result is more idiomatic, which is a better example for future Rust code authors. Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- scripts/rustdoc_test_gen.rs | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) diff --git a/scripts/rustdoc_test_gen.rs b/scripts/rustdoc_test_gen.rs index 1ca253594d38..a3dc251221e0 100644 --- a/scripts/rustdoc_test_gen.rs +++ b/scripts/rustdoc_test_gen.rs @@ -85,24 +85,25 @@ fn find_candidates( } } - assert!( - valid_paths.len() > 0, - "No path candidates found for `{file}`. This is likely a bug in the build system, or some \ - files went away while compiling." - ); - - if valid_paths.len() > 1 { - eprintln!("Several path candidates found:"); - for path in valid_paths { - eprintln!(" {path:?}"); + match valid_paths.as_slice() { + [] => panic!( + "No path candidates found for `{file}`. This is likely a bug in the build system, or \ + some files went away while compiling." + ), + [valid_path] => { + valid_path.to_str().unwrap() + } + valid_paths => { + eprintln!("Several path candidates found:"); + for path in valid_paths { + eprintln!(" {path:?}"); + } + panic!( + "Several path candidates found for `{file}`, please resolve the ambiguity by \ + renaming a file or folder." + ); } - panic!( - "Several path candidates found for `{file}`, please resolve the ambiguity by renaming \ - a file or folder." - ); } - - valid_paths[0].to_str().unwrap() } fn main() { --- base-commit: bfc3cd87559bc593bb32bb1482f9cae3308b6398 change-id: 20250527-idiomatic-match-slice-26a79d100e4d Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

5 months, 3 weeks

3
3
0 0

[PATCH next] tools/testing: Check correct variable in open_procmap()

by Dan Carpenter

Check if "procmap_out->fd" is negative instead of "procmap_out" (which is a pointer). Fixes: bd23f293a0d5 ("tools/testing: add PROCMAP_QUERY helper functions in mm self tests") Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> --- 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 1357e2d6a7b6..61d7bf1f8c62 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -439,7 +439,7 @@ int open_procmap(pid_t pid, struct procmap_fd *procmap_out) sprintf(path, "/proc/%d/maps", pid); procmap_out->query.size = sizeof(procmap_out->query); procmap_out->fd = open(path, O_RDONLY); - if (procmap_out < 0) + if (procmap_out->fd < 0) ret = -errno; return ret; -- 2.47.2

5 months, 3 weeks

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror