September 2024 - Linux-kselftest-mirror

[PATCH] selftests/ftrace: Fix eventfs ownership testcase to find mount point

by Masami Hiramatsu (Google)

From: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Fix eventfs ownership testcase to find mount point if stat -c "%m" failed. This can happen on the system based on busybox. In this case, this will try to use the current working directory, which should be a tracefs top directory (and eventfs is mounted as a part of tracefs.) If it does not work, the test is skipped as UNRESOLVED because of the environmental problem. Fixes: ee9793be08b1 ("tracing/selftests: Add ownership modification tests for eventfs") Signed-off-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> --- .../ftrace/test.d/00basic/test_ownership.tc | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc index c45094d1e1d2..803efd7b56c7 100644 --- a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc +++ b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc @@ -6,6 +6,18 @@ original_group=`stat -c "%g" .` original_owner=`stat -c "%u" .` mount_point=`stat -c '%m' .` + +# If stat -c '%m' does not work (e.g. busybox) or failed, try to use the +# current working directory (which should be a tracefs) as the mount point. +if [ ! -d "$mount_point" ]; then + if mount | grep -qw $PWD ; then + mount_point=$PWD + else + # If PWD doesn't work, that is an environmental problem. + exit_unresolved + fi +fi + mount_options=`mount | grep "$mount_point" | sed -e 's/.*($.*$).*/\1/'` # find another owner and group that is not the original

3 months, 2 weeks

3
2
0 0

[PATCH net-next 0/3] selftests: mptcp: add time per subtests in TAP output

by Matthieu Baerts (NGI0)

Patches here add 'time=<N>ms' in the diagnostic data of the TAP output, e.g. ok 1 - pm_netlink: defaults addr list # time=9ms This addition is useful to quickly identify which subtests are taking a longer time than the others, or more than expected. Note that there are no specific formats to follow to show this time according to the TAP 13, TAP 14 and KTAP specifications, but we follow the format being parsed by NIPA [1]. Patch 1 modifies mptcp_lib.sh to add this support to all MPTCP selftests. Patch 2 removes the now duplicated info in mptcp_connect.sh Patch 3 slightly improves the precision of the first subtests in all MPTCP subtests. Link: https://github.com/linux-netdev/nipa/pull/36 Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Matthieu Baerts (NGI0) (3): selftests: mptcp: lib: add time per subtests in TAP output sefltests: mptcp: connect: remote time in TAP output selftests: mptcp: reset the last TS before the first test tools/testing/selftests/net/mptcp/mptcp_connect.sh | 3 ++- tools/testing/selftests/net/mptcp/mptcp_join.sh | 3 ++- tools/testing/selftests/net/mptcp/mptcp_lib.sh | 17 ++++++++++++++++- tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 1 + tools/testing/selftests/net/mptcp/pm_netlink.sh | 2 ++ tools/testing/selftests/net/mptcp/simult_flows.sh | 1 + tools/testing/selftests/net/mptcp/userspace_pm.sh | 1 + 7 files changed, 25 insertions(+), 3 deletions(-) --- base-commit: 221f9cce949ac8042f65b71ed1fde13b99073256 change-id: 20240902-net-next-mptcp-ksft-subtest-time-a83cec43d894 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

3 months, 2 weeks

3
9
0 0

[PATCH] selftests: bpf: Replace sizeof(arr)/sizeof(arr[0]) with ARRAY_SIZE

by yangfeng

From: Feng Yang <yangfeng(a)kylinos.cn> The ARRAY_SIZE macro is more compact and more formal in linux source. Signed-off-by: Feng Yang <yangfeng(a)kylinos.cn> --- tools/testing/selftests/bpf/prog_tests/fexit_stress.c | 3 ++- tools/testing/selftests/bpf/prog_tests/log_buf.c | 5 +++-- .../testing/selftests/bpf/prog_tests/module_fentry_shadow.c | 3 ++- .../bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c | 3 ++- .../selftests/bpf/prog_tests/raw_tp_writable_test_run.c | 5 +++-- tools/testing/selftests/bpf/prog_tests/tc_opts.c | 2 +- tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c | 3 ++- tools/testing/selftests/bpf/progs/syscall.c | 3 ++- tools/testing/selftests/bpf/progs/test_rdonly_maps.c | 3 ++- tools/testing/selftests/bpf/progs/verifier_bits_iter.c | 2 +- 10 files changed, 20 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c index 49b1ffc9af1f..14c91b6f1e83 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> +#include "bpf_util.h" void serial_test_fexit_stress(void) { @@ -36,7 +37,7 @@ void serial_test_fexit_stress(void) for (i = 0; i < bpf_max_tramp_links; i++) { fexit_fd[i] = bpf_prog_load(BPF_PROG_TYPE_TRACING, NULL, "GPL", trace_program, - sizeof(trace_program) / sizeof(struct bpf_insn), + ARRAY_SIZE(trace_program), &trace_opts); if (!ASSERT_GE(fexit_fd[i], 0, "fexit load")) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c index 0f7ea4d7d9f6..46611040dec3 100644 --- a/tools/testing/selftests/bpf/prog_tests/log_buf.c +++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c @@ -5,6 +5,7 @@ #include <bpf/btf.h> #include "test_log_buf.skel.h" +#include "bpf_util.h" static size_t libbpf_log_pos; static char libbpf_log_buf[1024 * 1024]; @@ -143,11 +144,11 @@ static void bpf_prog_load_log_buf(void) BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - const size_t good_prog_insn_cnt = sizeof(good_prog_insns) / sizeof(struct bpf_insn); + const size_t good_prog_insn_cnt = ARRAY_SIZE(good_prog_insns); const struct bpf_insn bad_prog_insns[] = { BPF_EXIT_INSN(), }; - size_t bad_prog_insn_cnt = sizeof(bad_prog_insns) / sizeof(struct bpf_insn); + size_t bad_prog_insn_cnt = ARRAY_SIZE(bad_prog_insns); LIBBPF_OPTS(bpf_prog_load_opts, opts); const size_t log_buf_sz = 1024 * 1024; char *log_buf; diff --git a/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c b/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c index aa9f67eb1c95..bea05f78de5f 100644 --- a/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c +++ b/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c @@ -4,6 +4,7 @@ #include <bpf/btf.h> #include "bpf/libbpf_internal.h" #include "cgroup_helpers.h" +#include "bpf_util.h" static const char *module_name = "bpf_testmod"; static const char *symbol_name = "bpf_fentry_shadow_test"; @@ -100,7 +101,7 @@ void test_module_fentry_shadow(void) load_opts.attach_btf_obj_fd = btf_fd[i]; prog_fd[i] = bpf_prog_load(BPF_PROG_TYPE_TRACING, NULL, "GPL", trace_program, - sizeof(trace_program) / sizeof(struct bpf_insn), + ARRAY_SIZE(trace_program), &load_opts); if (!ASSERT_GE(prog_fd[i], 0, "bpf_prog_load")) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c index e2f1445b0e10..216b0dfac0fe 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c @@ -2,6 +2,7 @@ #include <test_progs.h> #include <linux/nbd.h> +#include "bpf_util.h" void test_raw_tp_writable_reject_nbd_invalid(void) { @@ -25,7 +26,7 @@ void test_raw_tp_writable_reject_nbd_invalid(void) ); bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2", - program, sizeof(program) / sizeof(struct bpf_insn), + program, ARRAY_SIZE(program), &opts); if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable load", "failed: %d errno %d\n", bpf_fd, errno)) diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c index f4aa7dab4766..e3668058b7bb 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c @@ -2,6 +2,7 @@ #include <test_progs.h> #include <linux/nbd.h> +#include "bpf_util.h" /* NOTE: conflict with other tests. */ void serial_test_raw_tp_writable_test_run(void) @@ -24,7 +25,7 @@ void serial_test_raw_tp_writable_test_run(void) ); int bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2", - trace_program, sizeof(trace_program) / sizeof(struct bpf_insn), + trace_program, ARRAY_SIZE(trace_program), &trace_opts); if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable loaded", "failed: %d errno %d\n", bpf_fd, errno)) @@ -41,7 +42,7 @@ void serial_test_raw_tp_writable_test_run(void) ); int filter_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL v2", - skb_program, sizeof(skb_program) / sizeof(struct bpf_insn), + skb_program, ARRAY_SIZE(skb_program), &skb_opts); if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n", filter_fd, errno)) diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c index 196abf223465..f77f604389aa 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c @@ -2384,7 +2384,7 @@ static int generate_dummy_prog(void) BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - const size_t prog_insn_cnt = sizeof(prog_insns) / sizeof(struct bpf_insn); + const size_t prog_insn_cnt = ARRAY_SIZE(prog_insns); LIBBPF_OPTS(bpf_prog_load_opts, opts); const size_t log_buf_sz = 256; char log_buf[log_buf_sz]; diff --git a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c index 0adf8d9475cb..472f4f9fa95f 100644 --- a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c +++ b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c @@ -7,6 +7,7 @@ #include "test_unpriv_bpf_disabled.skel.h" #include "cap_helpers.h" +#include "bpf_util.h" /* Using CAP_LAST_CAP is risky here, since it can get pulled in from * an old /usr/include/linux/capability.h and be < CAP_BPF; as a result @@ -146,7 +147,7 @@ static void test_unpriv_bpf_disabled_negative(struct test_unpriv_bpf_disabled *s BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - const size_t prog_insn_cnt = sizeof(prog_insns) / sizeof(struct bpf_insn); + const size_t prog_insn_cnt = ARRAY_SIZE(prog_insns); LIBBPF_OPTS(bpf_prog_load_opts, load_opts); struct bpf_map_info map_info = {}; __u32 map_info_len = sizeof(map_info); diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c index 3d3cafdebe72..0f4dfb770c32 100644 --- a/tools/testing/selftests/bpf/progs/syscall.c +++ b/tools/testing/selftests/bpf/progs/syscall.c @@ -8,6 +8,7 @@ #include <linux/btf.h> #include <string.h> #include <errno.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -119,7 +120,7 @@ int load_prog(struct args *ctx) static __u64 value = 34; static union bpf_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, - .insn_cnt = sizeof(insns) / sizeof(insns[0]), + .insn_cnt = ARRAY_SIZE(insns), }; int ret; diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c index fc8e8a34a3db..7035fb4d4165 100644 --- a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c +++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c @@ -4,6 +4,7 @@ #include <linux/ptrace.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" const struct { unsigned a[4]; @@ -64,7 +65,7 @@ int full_loop(struct pt_regs *ctx) { /* prevent compiler to optimize everything out */ unsigned * volatile p = (void *)&rdonly_values.a; - int i = sizeof(rdonly_values.a) / sizeof(rdonly_values.a[0]); + int i = ARRAY_SIZE(rdonly_values.a); unsigned iters = 0, sum = 0; /* validate verifier can allow full loop as well */ diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c index 716113c2bce2..f4da4d508ddb 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c +++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c @@ -87,7 +87,7 @@ int bits_memalloc(void) int *bit; __builtin_memset(&data, 0xf0, sizeof(data)); /* 4 * 16 */ - bpf_for_each(bits, bit, &data[0], sizeof(data) / sizeof(u64)) + bpf_for_each(bits, bit, &data[0], ARRAY_SIZE(data)) nr++; return nr; } -- 2.27.0

3 months, 2 weeks

2
1
0 0

[PATCH v2] mm/damon/tests/vaddr-kunit: init maple tree without MT_FLAGS_LOCK_EXTERN

by SeongJae Park

damon_test_three_regions_in_vmas() initializes a maple tree with MM_MT_FLAGS. The flags contains MT_FLAGS_LOCK_EXTERN, which means mt_lock of the maple tree will not be used. And therefore the maple tree initialization code skips initialization of the mt_lock. However, __link_vmas(), which adds vmas for test to the maple tree, uses the mt_lock. In other words, the uninitialized spinlock is used. The problem becomes clear when spinlock debugging is turned on, since it reports spinlock bad magic bug. Fix the issue by excluding MT_FLAGS_LOCK_EXTERN from the maple tree initialization flags. Note that we don't use empty flags to make it further similar to the usage of mm maple tree, and to be prepared for possible future changes, as suggested by Liam. Reported-by: Guenter Roeck <linux(a)roeck-us.net> Closes: https://lore.kernel.org/1453b2b2-6119-4082-ad9e-f3c5239bf87e@roeck-us.net Fixes: d0cf3dd47f0d ("damon: convert __damon_va_three_regions to use the VMA iterator") Suggested-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Signed-off-by: SeongJae Park <sj(a)kernel.org> --- Changes from v1 (https://lore.kernel.org/20240904004534.1189-1-sj@kernel.org) - Keep lock usage and update the initialization flags (Liam) - Fix a typo: s/celar/clear/ (Guenter) mm/damon/tests/vaddr-kunit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/damon/tests/vaddr-kunit.h b/mm/damon/tests/vaddr-kunit.h index 83626483f82b..a339d117150f 100644 --- a/mm/damon/tests/vaddr-kunit.h +++ b/mm/damon/tests/vaddr-kunit.h @@ -77,7 +77,7 @@ static void damon_test_three_regions_in_vmas(struct kunit *test) (struct vm_area_struct) {.vm_start = 307, .vm_end = 330}, }; - mt_init_flags(&mm.mm_mt, MM_MT_FLAGS); + mt_init_flags(&mm.mm_mt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_USE_RCU); if (__link_vmas(&mm.mm_mt, vmas, ARRAY_SIZE(vmas))) kunit_skip(test, "Failed to create VMA tree"); -- 2.39.2

3 months, 2 weeks

3
4
0 0

[PATCH bpf,v2,0/2] bpf: fix incorrect name check pass logic in btf_name_valid_section

by Jeongjun Park

This patch was written to fix an issue where btf_name_valid_section() would not properly check names with certain conditions and would throw an OOB vuln. And selftest was added to verify this patch. Jeongjun Park (2): bpf: add check for invalid name in btf_name_valid_section() selftest/bpf : Add a selftest test case to check for incorrect names kernel/bpf/btf.c | 4 ++- tools/testing/selftests/bpf/prog_tests/btf.c | 34 ++++++++++++++++++++ 2 files changed, 37 insertions(+), 1 deletion(-)

3 months, 2 weeks

3
4
0 0

[PATCH v2 1/1] selftests/bpf: Fix procmap_query()'s params mismatch and compilation warning

by Yuan Chen

From: Yuan Chen <chenyuan(a)kylinos.cn> When the PROCMAP_QUERY is not defined, a compilation error occurs due to the mismatch of the procmap_query()'s params, procmap_query() only be called in the file where the function is defined, modify the params so they can match. We get a warning when build samples/bpf: trace_helpers.c:252:5: warning: no previous prototype for ‘procmap_query’ [-Wmissing-prototypes] 252 | int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) | ^~~~~~~~~~~~~ As this function is only used in the file, mark it as 'static'. Fixes: 4e9e07603ecd ("selftests/bpf: make use of PROCMAP_QUERY ioctl if available") Signed-off-by: Yuan Chen <chenyuan(a)kylinos.cn> --- tools/testing/selftests/bpf/trace_helpers.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 1bfd881c0e07..2d742fdac6b9 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -249,7 +249,7 @@ int kallsyms_find(const char *sym, unsigned long long *addr) #ifdef PROCMAP_QUERY int env_verbosity __weak = 0; -int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) +static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) { char path_buf[PATH_MAX], build_id_buf[20]; struct procmap_query q; @@ -293,7 +293,7 @@ int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, si return 0; } #else -int procmap_query(int fd, const void *addr, size_t *start, size_t *offset, int *flags) +static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) { return -EOPNOTSUPP; } -- 2.46.0

3 months, 2 weeks

2
1
0 0

[PATCH] selftests: futex: Fix missing free in main

by zhangjiao2

From: zhang jiao <zhangjiao2(a)cmss.chinamobile.com> Free string allocated by asprintf(). Signed-off-by: zhang jiao <zhangjiao2(a)cmss.chinamobile.com> --- tools/testing/selftests/futex/functional/futex_requeue_pi.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi.c b/tools/testing/selftests/futex/functional/futex_requeue_pi.c index 215c6cb539b4..fb2dab46087f 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue_pi.c +++ b/tools/testing/selftests/futex/functional/futex_requeue_pi.c @@ -416,5 +416,8 @@ int main(int argc, char *argv[]) ret = unit_test(broadcast, locked, owner, timeout_ns); print_result(test_name, ret); + if (strlen(test_name) > strlen(TEST_NAME)) + free(test_name); + return ret; } -- 2.33.0

3 months, 2 weeks

2
1
0 0

[PATCH] iommufd/selftest:fix a resource leak

by Liu Jing

If the file fails to open, not only return return1 but also close the file descriptor,otherwise resource leak will occur Signed-off-by: Liu Jing <liujing(a)cmss.chinamobile.com> --- .../selftests/iommu/iommufd_fail_nth.c | 143 ++++++++++-------- 1 file changed, 83 insertions(+), 60 deletions(-) diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c index c5d5e69452b0..ff4e5d8aad57 100644 --- a/tools/testing/selftests/iommu/iommufd_fail_nth.c +++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c @@ -237,10 +237,10 @@ TEST_FAIL_NTH(basic_fail_nth, basic) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; { struct iommu_ioas_iova_ranges ranges_cmd = { @@ -250,7 +250,7 @@ TEST_FAIL_NTH(basic_fail_nth, basic) .allowed_iovas = (uintptr_t)ranges, }; if (ioctl(self->fd, IOMMU_IOAS_IOVA_RANGES, &ranges_cmd)) - return -1; + goto close; } { @@ -264,13 +264,13 @@ TEST_FAIL_NTH(basic_fail_nth, basic) ranges[0].start = 16*1024; ranges[0].last = BUFFER_SIZE + 16 * 1024 * 600 - 1; if (ioctl(self->fd, IOMMU_IOAS_ALLOW_IOVAS, &allow_cmd)) - return -1; + goto close; } if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, BUFFER_SIZE, &iova, IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; { struct iommu_ioas_copy copy_cmd = { @@ -284,15 +284,19 @@ TEST_FAIL_NTH(basic_fail_nth, basic) }; if (ioctl(self->fd, IOMMU_IOAS_COPY, &copy_cmd)) - return -1; + goto close; } if (_test_ioctl_ioas_unmap(self->fd, ioas_id, iova, BUFFER_SIZE, NULL)) - return -1; + goto close; /* Failure path of no IOVA to unmap */ _test_ioctl_ioas_unmap(self->fd, ioas_id, iova, BUFFER_SIZE, NULL); return 0; + +close: + close(self->fd); + return -1; } /* iopt_area_fill_domains() and iopt_area_fill_domain() */ @@ -305,30 +309,33 @@ TEST_FAIL_NTH(basic_fail_nth, map_domain) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) - return -1; + goto close; fail_nth_enable(); if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) - return -1; + goto close; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, 262144, &iova, IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; if (_test_ioctl_destroy(self->fd, stdev_id)) - return -1; + goto close; if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) - return -1; + goto close; return 0; +close: + close(self->fd); + return -1; } TEST_FAIL_NTH(basic_fail_nth, map_two_domains) @@ -342,40 +349,43 @@ TEST_FAIL_NTH(basic_fail_nth, map_two_domains) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) - return -1; + goto close; if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) - return -1; + goto close; fail_nth_enable(); if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id2, &hwpt_id2, NULL)) - return -1; + goto close; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, 262144, &iova, IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; if (_test_ioctl_destroy(self->fd, stdev_id)) - return -1; + goto close; if (_test_ioctl_destroy(self->fd, stdev_id2)) - return -1; + goto close; if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) - return -1; + goto close; if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id2, &hwpt_id2, NULL)) - return -1; + goto close; return 0; +close: + close(self->fd); + return -1; } TEST_FAIL_NTH(basic_fail_nth, access_rw) @@ -387,23 +397,23 @@ TEST_FAIL_NTH(basic_fail_nth, access_rw) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) - return -1; + goto close; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, 262144, &iova, IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; fail_nth_enable(); if (_test_cmd_create_access(self->fd, ioas_id, &self->access_id, 0)) - return -1; + goto close; { struct iommu_test_cmd access_cmd = { @@ -418,22 +428,22 @@ TEST_FAIL_NTH(basic_fail_nth, access_rw) // READ if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; access_cmd.access_rw.flags = MOCK_ACCESS_RW_WRITE; if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; access_cmd.access_rw.flags = MOCK_ACCESS_RW_SLOW_PATH; if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; access_cmd.access_rw.flags = MOCK_ACCESS_RW_SLOW_PATH | MOCK_ACCESS_RW_WRITE; if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; } { @@ -449,12 +459,15 @@ TEST_FAIL_NTH(basic_fail_nth, access_rw) if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; } if (_test_cmd_destroy_access(self->access_id)) return -1; self->access_id = 0; return 0; +close: + close(self->fd); + return -1; } /* pages.c access functions */ @@ -466,22 +479,22 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) - return -1; + goto close; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, BUFFER_SIZE, &iova, IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; if (_test_cmd_create_access(self->fd, ioas_id, &self->access_id, MOCK_FLAGS_ACCESS_CREATE_NEEDS_PIN_PAGES)) - return -1; + goto close; fail_nth_enable(); @@ -497,18 +510,21 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin) if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; access_pages_id = access_cmd.access_pages.out_access_pages_id; } if (_test_cmd_destroy_access_pages(self->fd, self->access_id, access_pages_id)) - return -1; + goto close; if (_test_cmd_destroy_access(self->access_id)) return -1; self->access_id = 0; return 0; +close: + close(self->fd); + return -1; } /* iopt_pages_fill_xarray() */ @@ -522,25 +538,25 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin_domain) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) - return -1; + goto close; if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) - return -1; + goto close; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, BUFFER_SIZE, &iova, IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; if (_test_cmd_create_access(self->fd, ioas_id, &self->access_id, MOCK_FLAGS_ACCESS_CREATE_NEEDS_PIN_PAGES)) - return -1; + goto close; fail_nth_enable(); @@ -556,21 +572,24 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin_domain) if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; access_pages_id = access_cmd.access_pages.out_access_pages_id; } if (_test_cmd_destroy_access_pages(self->fd, self->access_id, access_pages_id)) - return -1; + goto close; if (_test_cmd_destroy_access(self->access_id)) return -1; self->access_id = 0; if (_test_ioctl_destroy(self->fd, stdev_id)) - return -1; + goto close; return 0; +close: + close(self->fd); + return -1; } /* device.c */ @@ -586,45 +605,49 @@ TEST_FAIL_NTH(basic_fail_nth, device) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id2)) - return -1; + goto close; iova = MOCK_APERTURE_START; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, PAGE_SIZE, &iova, IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; if (_test_ioctl_ioas_map(self->fd, ioas_id2, buffer, PAGE_SIZE, &iova, IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; fail_nth_enable(); if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, NULL, &idev_id)) - return -1; + goto close; if (_test_cmd_get_hw_info(self->fd, idev_id, &info, sizeof(info), NULL)) - return -1; + goto close; if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, 0, 0, &hwpt_id, IOMMU_HWPT_DATA_NONE, 0, 0)) - return -1; + goto close; if (_test_cmd_mock_domain_replace(self->fd, stdev_id, ioas_id2, NULL)) - return -1; + goto close; if (_test_cmd_mock_domain_replace(self->fd, stdev_id, hwpt_id, NULL)) - return -1; + goto close; return 0; +close: + close(self->fd); + return -1; + } TEST_HARNESS_MAIN -- 2.33.0

3 months, 2 weeks

2
1
0 0

[PATCH] um: kunit: resolve missing prototypes warning

by Gabriele Monaco

While building for KUnit with default settings, the build is generating the following compilation warnings. ``` $ make ARCH=um O=.kunit --jobs=16 ../lib/iomap.c:156:5: warning: no previous prototype for ‘ioread64_lo_hi’ [-Wmissing-prototypes] 156 | u64 ioread64_lo_hi(const void __iomem *addr) | ^~~~~~~~~~~~~~ [...] ``` The warning happens because the prototypes are defined in `asm-generic/iomap.h` only when `readq` and `writeq` are defined. For UM, those function get some default definitions but are currently defined _after_ the prototypes for `ioread64*`/`iowrite64*` functions. Moving the inclusion of `asm-generic/iomap.h` fixes it. Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com> --- include/asm-generic/io.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 80de699bf6af..0b02c8e38f20 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -13,10 +13,6 @@ #include <linux/types.h> #include <linux/instruction_pointer.h> -#ifdef CONFIG_GENERIC_IOMAP -#include <asm-generic/iomap.h> -#endif - #include <asm/mmiowb.h> #include <asm-generic/pci_iomap.h> @@ -295,6 +291,10 @@ static inline void writeq(u64 value, volatile void __iomem *addr) #endif #endif /* CONFIG_64BIT */ +#ifdef CONFIG_GENERIC_IOMAP +#include <asm-generic/iomap.h> +#endif + /* * {read,write}{b,w,l,q}_relaxed() are like the regular version, but * are not guaranteed to provide ordering against spinlocks or memory base-commit: 67784a74e258a467225f0e68335df77acd67b7ab -- 2.46.0

3 months, 2 weeks

2
2
0 0

[PATCH net-next v17 02/14] mm: move the page fragment allocator from page_alloc into its own file

by Yunsheng Lin

Inspired by [1], move the page fragment allocator from page_alloc into its own c file and header file, as we are about to make more change for it to replace another page_frag implementation in sock.c As this patchset is going to replace 'struct page_frag' with 'struct page_frag_cache' in sched.h, including page_frag_cache.h in sched.h has a compiler error caused by interdependence between mm_types.h and mm.h for asm-offsets.c, see [2]. So avoid the compiler error by moving 'struct page_frag_cache' to mm_types_task.h as suggested by Alexander, see [3]. 1. https://lore.kernel.org/all/20230411160902.4134381-3-dhowells@redhat.com/ 2. https://lore.kernel.org/all/15623dac-9358-4597-b3ee-3694a5956920@gmail.com/ 3. https://lore.kernel.org/all/CAKgT0UdH1yD=LSCXFJ=YM_aiA4OomD-2wXykO42bizaWMt… CC: David Howells <dhowells(a)redhat.com> CC: Alexander Duyck <alexander.duyck(a)gmail.com> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> Acked-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/gfp.h | 22 --- include/linux/mm_types.h | 18 --- include/linux/mm_types_task.h | 18 +++ include/linux/page_frag_cache.h | 31 ++++ include/linux/skbuff.h | 1 + mm/Makefile | 1 + mm/page_alloc.c | 136 ---------------- mm/page_frag_cache.c | 145 ++++++++++++++++++ .../selftests/mm/page_frag/page_frag_test.c | 2 +- 9 files changed, 197 insertions(+), 177 deletions(-) create mode 100644 include/linux/page_frag_cache.h create mode 100644 mm/page_frag_cache.c diff --git a/include/linux/gfp.h b/include/linux/gfp.h index f53f76e0b17e..01a49be7c98d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -371,28 +371,6 @@ __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mas extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); -struct page_frag_cache; -void page_frag_cache_drain(struct page_frag_cache *nc); -extern void __page_frag_cache_drain(struct page *page, unsigned int count); -void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, - gfp_t gfp_mask, unsigned int align_mask); - -static inline void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align) -{ - WARN_ON_ONCE(!is_power_of_2(align)); - return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); -} - -static inline void *page_frag_alloc(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask) -{ - return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); -} - -extern void page_frag_free(void *addr); - #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 485424979254..843d75412105 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -521,9 +521,6 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) -#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) -#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) - /* * page_private can be used on tail pages. However, PagePrivate is only * checked by the VM on the head page. So page_private on the tail pages @@ -542,21 +539,6 @@ static inline void *folio_get_private(struct folio *folio) return folio->private; } -struct page_frag_cache { - void * va; -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - __u16 offset; - __u16 size; -#else - __u32 offset; -#endif - /* we maintain a pagecount bias, so that we dont dirty cache line - * containing page->_refcount every time we allocate a fragment. - */ - unsigned int pagecnt_bias; - bool pfmemalloc; -}; - typedef unsigned long vm_flags_t; /* diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index a2f6179b672b..cdc1e3696439 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -8,6 +8,7 @@ * (These are defined separately to decouple sched.h from mm_types.h as much as possible.) */ +#include <linux/align.h> #include <linux/types.h> #include <asm/page.h> @@ -46,6 +47,23 @@ struct page_frag { #endif }; +#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) +#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) +struct page_frag_cache { + void *va; +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + __u16 offset; + __u16 size; +#else + __u32 offset; +#endif + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_refcount every time we allocate a fragment. + */ + unsigned int pagecnt_bias; + bool pfmemalloc; +}; + /* Track pages that require TLB flushes */ struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h new file mode 100644 index 000000000000..67ac8626ed9b --- /dev/null +++ b/include/linux/page_frag_cache.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_PAGE_FRAG_CACHE_H +#define _LINUX_PAGE_FRAG_CACHE_H + +#include <linux/log2.h> +#include <linux/mm_types_task.h> +#include <linux/types.h> + +void page_frag_cache_drain(struct page_frag_cache *nc); +void __page_frag_cache_drain(struct page *page, unsigned int count); +void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, + gfp_t gfp_mask, unsigned int align_mask); + +static inline void *page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); +} + +static inline void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) +{ + return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); +} + +void page_frag_free(void *addr); + +#endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cf8f6ce06742..7482997c719f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -31,6 +31,7 @@ #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> +#include <linux/page_frag_cache.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> diff --git a/mm/Makefile b/mm/Makefile index d2915f8c9dc0..e9d342fa8058 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -65,6 +65,7 @@ page-alloc-$(CONFIG_SHUFFLE_PAGE_ALLOCATOR) += shuffle.o memory-hotplug-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-y += page-alloc.o +obj-y += page_frag_cache.o obj-y += init-mm.o obj-y += memblock.o obj-y += $(memory-hotplug-y) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c565de8f48e9..d0e88aa6eb0d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4798,142 +4798,6 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); -/* - * Page Fragment: - * An arbitrary-length arbitrary-offset area of memory which resides - * within a 0 or higher order page. Multiple fragments within that page - * are individually refcounted, in the page's reference counter. - * - * The page_frag functions below provide a simple allocation framework for - * page fragments. This is used by the network stack and network device - * drivers to provide a backing region of memory for use as either an - * sk_buff->head, or to be used in the "frags" portion of skb_shared_info. - */ -static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, - gfp_t gfp_mask) -{ - struct page *page = NULL; - gfp_t gfp = gfp_mask; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | - __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; - page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, - PAGE_FRAG_CACHE_MAX_ORDER); - nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; -#endif - if (unlikely(!page)) - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - - nc->va = page ? page_address(page) : NULL; - - return page; -} - -void page_frag_cache_drain(struct page_frag_cache *nc) -{ - if (!nc->va) - return; - - __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); - nc->va = NULL; -} -EXPORT_SYMBOL(page_frag_cache_drain); - -void __page_frag_cache_drain(struct page *page, unsigned int count) -{ - VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); - - if (page_ref_sub_and_test(page, count)) - free_unref_page(page, compound_order(page)); -} -EXPORT_SYMBOL(__page_frag_cache_drain); - -void *__page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) -{ - unsigned int size = PAGE_SIZE; - struct page *page; - int offset; - - if (unlikely(!nc->va)) { -refill: - page = __page_frag_cache_refill(nc, gfp_mask); - if (!page) - return NULL; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size = nc->size; -#endif - /* Even if we own the page, we do not use atomic_set(). - * This would break get_page_unless_zero() users. - */ - page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); - - /* reset page count bias and offset to start of new frag */ - nc->pfmemalloc = page_is_pfmemalloc(page); - nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; - nc->offset = size; - } - - offset = nc->offset - fragsz; - if (unlikely(offset < 0)) { - page = virt_to_page(nc->va); - - if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) - goto refill; - - if (unlikely(nc->pfmemalloc)) { - free_unref_page(page, compound_order(page)); - goto refill; - } - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size = nc->size; -#endif - /* OK, page count is 0, we can safely set it */ - set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); - - /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; - offset = size - fragsz; - if (unlikely(offset < 0)) { - /* - * The caller is trying to allocate a fragment - * with fragsz > PAGE_SIZE but the cache isn't big - * enough to satisfy the request, this may - * happen in low memory conditions. - * We don't release the cache page because - * it could make memory pressure worse - * so we simply return NULL here. - */ - return NULL; - } - } - - nc->pagecnt_bias--; - offset &= align_mask; - nc->offset = offset; - - return nc->va + offset; -} -EXPORT_SYMBOL(__page_frag_alloc_align); - -/* - * Frees a page fragment allocated out of either a compound or order 0 page. - */ -void page_frag_free(void *addr) -{ - struct page *page = virt_to_head_page(addr); - - if (unlikely(put_page_testzero(page))) - free_unref_page(page, compound_order(page)); -} -EXPORT_SYMBOL(page_frag_free); - static void *make_alloc_exact(unsigned long addr, unsigned int order, size_t size) { diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c new file mode 100644 index 000000000000..609a485cd02a --- /dev/null +++ b/mm/page_frag_cache.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Page fragment allocator + * + * Page Fragment: + * An arbitrary-length arbitrary-offset area of memory which resides within a + * 0 or higher order page. Multiple fragments within that page are + * individually refcounted, in the page's reference counter. + * + * The page_frag functions provide a simple allocation framework for page + * fragments. This is used by the network stack and network device drivers to + * provide a backing region of memory for use as either an sk_buff->head, or to + * be used in the "frags" portion of skb_shared_info. + */ + +#include <linux/export.h> +#include <linux/gfp_types.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/page_frag_cache.h> +#include "internal.h" + +static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, + gfp_t gfp_mask) +{ + struct page *page = NULL; + gfp_t gfp = gfp_mask; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | + __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; + page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, + PAGE_FRAG_CACHE_MAX_ORDER); + nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; +#endif + if (unlikely(!page)) + page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); + + nc->va = page ? page_address(page) : NULL; + + return page; +} + +void page_frag_cache_drain(struct page_frag_cache *nc) +{ + if (!nc->va) + return; + + __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); + nc->va = NULL; +} +EXPORT_SYMBOL(page_frag_cache_drain); + +void __page_frag_cache_drain(struct page *page, unsigned int count) +{ + VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); + + if (page_ref_sub_and_test(page, count)) + free_unref_page(page, compound_order(page)); +} +EXPORT_SYMBOL(__page_frag_cache_drain); + +void *__page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask) +{ + unsigned int size = PAGE_SIZE; + struct page *page; + int offset; + + if (unlikely(!nc->va)) { +refill: + page = __page_frag_cache_refill(nc, gfp_mask); + if (!page) + return NULL; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* Even if we own the page, we do not use atomic_set(). + * This would break get_page_unless_zero() users. + */ + page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); + + /* reset page count bias and offset to start of new frag */ + nc->pfmemalloc = page_is_pfmemalloc(page); + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; + nc->offset = size; + } + + offset = nc->offset - fragsz; + if (unlikely(offset < 0)) { + page = virt_to_page(nc->va); + + if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) + goto refill; + + if (unlikely(nc->pfmemalloc)) { + free_unref_page(page, compound_order(page)); + goto refill; + } + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* OK, page count is 0, we can safely set it */ + set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); + + /* reset page count bias and offset to start of new frag */ + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; + offset = size - fragsz; + if (unlikely(offset < 0)) { + /* + * The caller is trying to allocate a fragment + * with fragsz > PAGE_SIZE but the cache isn't big + * enough to satisfy the request, this may + * happen in low memory conditions. + * We don't release the cache page because + * it could make memory pressure worse + * so we simply return NULL here. + */ + return NULL; + } + } + + nc->pagecnt_bias--; + offset &= align_mask; + nc->offset = offset; + + return nc->va + offset; +} +EXPORT_SYMBOL(__page_frag_alloc_align); + +/* + * Frees a page fragment allocated out of either a compound or order 0 page. + */ +void page_frag_free(void *addr) +{ + struct page *page = virt_to_head_page(addr); + + if (unlikely(put_page_testzero(page))) + free_unref_page(page, compound_order(page)); +} +EXPORT_SYMBOL(page_frag_free); diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c index 6d6f31936b10..5395a36e4030 100644 --- a/tools/testing/selftests/mm/page_frag/page_frag_test.c +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -6,12 +6,12 @@ * Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> */ -#include <linux/mm.h> #include <linux/module.h> #include <linux/cpumask.h> #include <linux/completion.h> #include <linux/ptr_ring.h> #include <linux/kthread.h> +#include <linux/page_frag_cache.h> static struct ptr_ring ptr_ring; static int nr_objs = 512; -- 2.33.0

3 months, 2 weeks

2
1
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror September 2024