diff options
| author | Jiri Kosina <jkosina@suse.com> | 2026-04-16 21:01:18 +0200 |
|---|---|---|
| committer | Jiri Kosina <jkosina@suse.com> | 2026-04-16 21:01:18 +0200 |
| commit | d4eb7b2da66c848709e31585b9c371fa234abc39 (patch) | |
| tree | 5c6311cfa45567ecdcb8946a2252da7d55d1ac10 /tools/testing | |
| parent | 8b9a097eb2fc37b486afd81388c693bf3ab44466 (diff) | |
| parent | 69c02ffde6ed4d535fa4e693a9e572729cad3d0d (diff) | |
Merge branch 'for-7.1/core-v2' into for-linus
- fixed handling of 0-sized reports (Dmitry Torokhov)
- convert core code to __free() (Dmitry Torokhov)
- support for multiple batteries per HID device (Lucas Zampieri)
Diffstat (limited to 'tools/testing')
159 files changed, 5822 insertions, 2698 deletions
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 260d8d9aa1db..2998e1bc088b 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -346,8 +346,10 @@ class LinuxSourceTree: return self.validate_config(build_dir) def run_kernel(self, args: Optional[List[str]]=None, build_dir: str='', filter_glob: str='', filter: str='', filter_action: Optional[str]=None, timeout: Optional[int]=None) -> Iterator[str]: - if not args: - args = [] + # Copy to avoid mutating the caller-supplied list. exec_tests() reuses + # the same args across repeated run_kernel() calls (e.g. --run_isolated), + # so appending to the original would accumulate stale flags on each call. + args = list(args) if args else [] if filter_glob: args.append('kunit.filter_glob=' + filter_glob) if filter: diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index b67408147c1f..f6383884c599 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -503,6 +503,32 @@ class LinuxSourceTreeTest(unittest.TestCase): with open(kunit_kernel.get_outfile_path(build_dir), 'rt') as outfile: self.assertEqual(outfile.read(), 'hi\nbye\n', msg='Missing some output') + def test_run_kernel_args_not_mutated(self): + """Verify run_kernel() copies args so callers can reuse them.""" + start_calls = [] + + def fake_start(start_args, unused_build_dir): + start_calls.append(list(start_args)) + return subprocess.Popen(['printf', 'KTAP version 1\n'], + text=True, stdout=subprocess.PIPE) + + with tempfile.TemporaryDirectory('') as build_dir: + tree = kunit_kernel.LinuxSourceTree(build_dir, + kunitconfig_paths=[os.devnull]) + with mock.patch.object(tree._ops, 'start', side_effect=fake_start), \ + mock.patch.object(kunit_kernel.subprocess, 'call'): + kernel_args = ['mem=1G'] + for _ in tree.run_kernel(args=kernel_args, build_dir=build_dir, + filter_glob='suite.test1'): + pass + for _ in tree.run_kernel(args=kernel_args, build_dir=build_dir, + filter_glob='suite.test2'): + pass + self.assertEqual(kernel_args, ['mem=1G'], + 'run_kernel() should not modify caller args') + self.assertIn('kunit.filter_glob=suite.test1', start_calls[0]) + self.assertIn('kunit.filter_glob=suite.test2', start_calls[1]) + def test_build_reconfig_no_config(self): with tempfile.TemporaryDirectory('') as build_dir: with open(kunit_kernel.get_kunitconfig_path(build_dir), 'w') as f: diff --git a/tools/testing/memblock/internal.h b/tools/testing/memblock/internal.h index 0ab4b53bb4f3..009b97bbdd22 100644 --- a/tools/testing/memblock/internal.h +++ b/tools/testing/memblock/internal.h @@ -15,8 +15,7 @@ bool mirrored_kernelcore = false; struct page {}; -void memblock_free_pages(struct page *page, unsigned long pfn, - unsigned int order) +void memblock_free_pages(unsigned long pfn, unsigned int order) { } diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 9d2df1f3e6bb..c2661a312fc9 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -475,8 +475,8 @@ static void sve2_sigill(void) static void sve2p1_sigill(void) { - /* BFADD Z0.H, Z0.H, Z0.H */ - asm volatile(".inst 0x65000000" : : : "z0"); + /* LD1Q {Z0.Q}, P0/Z, [Z0.D, X0] */ + asm volatile(".inst 0xC400A000" : : : "z0"); } static void sve2p2_sigill(void) diff --git a/tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c b/tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c new file mode 100644 index 000000000000..2259f454a202 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2026 ARM Limited + */ + +#include <errno.h> +#include <signal.h> +#include <unistd.h> + +#include <sys/mman.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +static uint64_t *gcs_page; +static bool post_mprotect; + +#ifndef __NR_map_shadow_stack +#define __NR_map_shadow_stack 453 +#endif + +static bool alloc_gcs(struct tdescr *td) +{ + long page_size = sysconf(_SC_PAGE_SIZE); + + gcs_page = (void *)syscall(__NR_map_shadow_stack, 0, + page_size, 0); + if (gcs_page == MAP_FAILED) { + fprintf(stderr, "Failed to map %ld byte GCS: %d\n", + page_size, errno); + return false; + } + + return true; +} + +static int gcs_prot_none_fault_trigger(struct tdescr *td) +{ + /* Verify that the page is readable (ie, not completely unmapped) */ + fprintf(stderr, "Read value 0x%lx\n", gcs_page[0]); + + if (mprotect(gcs_page, sysconf(_SC_PAGE_SIZE), PROT_NONE) != 0) { + fprintf(stderr, "mprotect(PROT_NONE) failed: %d\n", errno); + return 0; + } + post_mprotect = true; + + /* This should trigger a fault if PROT_NONE is honoured for the GCS page */ + fprintf(stderr, "Read value after mprotect(PROT_NONE) 0x%lx\n", gcs_page[0]); + return 0; +} + +static int gcs_prot_none_fault_signal(struct tdescr *td, siginfo_t *si, + ucontext_t *uc) +{ + ASSERT_GOOD_CONTEXT(uc); + + /* A fault before mprotect(PROT_NONE) is unexpected. */ + if (!post_mprotect) + return 0; + + return 1; +} + +struct tdescr tde = { + .name = "GCS PROT_NONE fault", + .descr = "Read from GCS after mprotect(PROT_NONE) segfaults", + .feats_required = FEAT_GCS, + .timeout = 3, + .sig_ok = SIGSEGV, + .sanity_disabled = true, + .init = alloc_gcs, + .trigger = gcs_prot_none_fault_trigger, + .run = gcs_prot_none_fault_signal, +}; diff --git a/tools/testing/selftests/bpf/DENYLIST.asan b/tools/testing/selftests/bpf/DENYLIST.asan new file mode 100644 index 000000000000..d7fe372a2293 --- /dev/null +++ b/tools/testing/selftests/bpf/DENYLIST.asan @@ -0,0 +1,3 @@ +*arena* +task_local_data +uprobe_multi_test diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index c6bf4dfb1495..d5acbeba0383 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -27,7 +27,11 @@ ifneq ($(wildcard $(GENHDR)),) endif BPF_GCC ?= $(shell command -v bpf-gcc;) +ifdef ASAN +SAN_CFLAGS ?= -fsanitize=address -fno-omit-frame-pointer +else SAN_CFLAGS ?= +endif SAN_LDFLAGS ?= $(SAN_CFLAGS) RELEASE ?= OPT_FLAGS ?= $(if $(RELEASE),-O2,-O0) @@ -326,8 +330,8 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" \ - EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS)' \ - EXTRA_LDFLAGS='$(EXTRA_LDFLAGS)' \ + EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)' \ + EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' \ OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \ LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/ \ @@ -338,8 +342,8 @@ $(CROSS_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ $(BPFOBJ) | $(BUILD_DIR)/bpftool $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) \ - EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS)' \ - EXTRA_LDFLAGS='$(EXTRA_LDFLAGS)' \ + EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)' \ + EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' \ OUTPUT=$(BUILD_DIR)/bpftool/ \ LIBBPF_OUTPUT=$(BUILD_DIR)/libbpf/ \ LIBBPF_DESTDIR=$(SCRATCH_DIR)/ \ @@ -404,6 +408,8 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids \ $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids \ CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \ LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \ + EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' \ + HOSTPKG_CONFIG=$(PKG_CONFIG) \ OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ) # Get Clang's default includes on this system, as opposed to those seen by @@ -723,7 +729,7 @@ $(VERIFICATION_CERT) $(PRIVATE_KEY): $(VERIFY_SIG_SETUP) # Generates a header with C array declaration, containing test_progs_verification_cert bytes $(VERIFY_SIG_HDR): $(VERIFICATION_CERT) $(Q)(echo "unsigned char test_progs_verification_cert[] = {"; \ - hexdump -v -e '12/1 " 0x%02x," "\n"' $< | sed 's/0x ,//g; $$s/,$$//'; \ + od -v -t 'xC' -w12 $< | sed 's/ \(\S\+\)/ 0x\1,/g;s/^\S\+/ /;$$d'; \ echo "};"; \ echo "unsigned int test_progs_verification_cert_len = $$(wc -c < $<);") > $@ diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index aeec9edd3851..f74b313d6ae4 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -230,8 +230,8 @@ static void trigger_fentry_setup(void) static void attach_ksyms_all(struct bpf_program *empty, bool kretprobe) { LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); - char **syms = NULL; - size_t cnt = 0; + struct bpf_link *link = NULL; + struct ksyms *ksyms = NULL; /* Some recursive functions will be skipped in * bpf_get_ksyms -> skip_entry, as they can introduce sufficient @@ -241,16 +241,18 @@ static void attach_ksyms_all(struct bpf_program *empty, bool kretprobe) * So, don't run the kprobe-multi-all and kretprobe-multi-all on * a debug kernel. */ - if (bpf_get_ksyms(&syms, &cnt, true)) { + if (bpf_get_ksyms(&ksyms, true)) { fprintf(stderr, "failed to get ksyms\n"); exit(1); } - opts.syms = (const char **) syms; - opts.cnt = cnt; + opts.syms = (const char **)ksyms->filtered_syms; + opts.cnt = ksyms->filtered_cnt; opts.retprobe = kretprobe; /* attach empty to all the kernel functions except bpf_get_numa_node_id. */ - if (!bpf_program__attach_kprobe_multi_opts(empty, NULL, &opts)) { + link = bpf_program__attach_kprobe_multi_opts(empty, NULL, &opts); + free_kallsyms_local(ksyms); + if (!link) { fprintf(stderr, "failed to attach bpf_program__attach_kprobe_multi_opts to all\n"); exit(1); } diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index 4bc2d25f33e1..6cb56501a505 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -8,6 +8,7 @@ #include <errno.h> #include <syscall.h> #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ +#include <linux/args.h> static inline unsigned int bpf_num_possible_cpus(void) { @@ -21,25 +22,43 @@ static inline unsigned int bpf_num_possible_cpus(void) return possible_cpus; } -/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst - * is zero-terminated string no matter what (unless sz == 0, in which case - * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs - * in what is returned. Given this is internal helper, it's trivial to extend - * this, when necessary. Use this instead of strncpy inside libbpf source code. +/* + * Simplified strscpy() implementation. The kernel one is in lib/string.c */ -static inline void bpf_strlcpy(char *dst, const char *src, size_t sz) +static inline ssize_t sized_strscpy(char *dest, const char *src, size_t count) { - size_t i; + long res = 0; - if (sz == 0) - return; + if (count == 0) + return -E2BIG; - sz--; - for (i = 0; i < sz && src[i]; i++) - dst[i] = src[i]; - dst[i] = '\0'; + while (count > 1) { + char c; + + c = src[res]; + dest[res] = c; + if (!c) + return res; + res++; + count--; + } + + /* Force NUL-termination. */ + dest[res] = '\0'; + + /* Return E2BIG if the source didn't stop */ + return src[res] ? -E2BIG : res; } +#define __strscpy0(dst, src, ...) \ + sized_strscpy(dst, src, sizeof(dst)) +#define __strscpy1(dst, src, size) \ + sized_strscpy(dst, src, size) + +#undef strscpy /* Redefine the placeholder from tools/include/linux/string.h */ +#define strscpy(dst, src, ...) \ + CONCATENATE(__strscpy, COUNT_ARGS(__VA_ARGS__))(dst, src, __VA_ARGS__) + #define __bpf_percpu_val_align __attribute__((__aligned__(8))) #define BPF_DECLARE_PERCPU(type, name) \ diff --git a/tools/testing/selftests/bpf/bpftool_helpers.c b/tools/testing/selftests/bpf/bpftool_helpers.c index a5824945a4a5..929fc257f431 100644 --- a/tools/testing/selftests/bpf/bpftool_helpers.c +++ b/tools/testing/selftests/bpf/bpftool_helpers.c @@ -1,24 +1,37 @@ // SPDX-License-Identifier: GPL-2.0-only -#include "bpftool_helpers.h" #include <unistd.h> #include <string.h> #include <stdbool.h> +#include "bpf_util.h" +#include "bpftool_helpers.h" + #define BPFTOOL_PATH_MAX_LEN 64 #define BPFTOOL_FULL_CMD_MAX_LEN 512 #define BPFTOOL_DEFAULT_PATH "tools/sbin/bpftool" -static int detect_bpftool_path(char *buffer) +static int detect_bpftool_path(char *buffer, size_t size) { char tmp[BPFTOOL_PATH_MAX_LEN]; + const char *env_path; + + /* First, check if BPFTOOL environment variable is set */ + env_path = getenv("BPFTOOL"); + if (env_path && access(env_path, X_OK) == 0) { + strscpy(buffer, env_path, size); + return 0; + } else if (env_path) { + fprintf(stderr, "bpftool '%s' doesn't exist or is not executable\n", env_path); + return 1; + } /* Check default bpftool location (will work if we are running the * default flavor of test_progs) */ snprintf(tmp, BPFTOOL_PATH_MAX_LEN, "./%s", BPFTOOL_DEFAULT_PATH); if (access(tmp, X_OK) == 0) { - strncpy(buffer, tmp, BPFTOOL_PATH_MAX_LEN); + strscpy(buffer, tmp, size); return 0; } @@ -27,11 +40,11 @@ static int detect_bpftool_path(char *buffer) */ snprintf(tmp, BPFTOOL_PATH_MAX_LEN, "../%s", BPFTOOL_DEFAULT_PATH); if (access(tmp, X_OK) == 0) { - strncpy(buffer, tmp, BPFTOOL_PATH_MAX_LEN); + strscpy(buffer, tmp, size); return 0; } - /* Failed to find bpftool binary */ + fprintf(stderr, "Failed to detect bpftool path, use BPFTOOL env var to override\n"); return 1; } @@ -44,7 +57,7 @@ static int run_command(char *args, char *output_buf, size_t output_max_len) int ret; /* Detect and cache bpftool binary location */ - if (bpftool_path[0] == 0 && detect_bpftool_path(bpftool_path)) + if (bpftool_path[0] == 0 && detect_bpftool_path(bpftool_path, sizeof(bpftool_path))) return 1; ret = snprintf(command, BPFTOOL_FULL_CMD_MAX_LEN, "%s %s%s", diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 20cede4db3ce..45cd0b479fe3 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -86,7 +86,7 @@ static int __enable_controllers(const char *cgroup_path, const char *controllers enable[len] = 0; close(fd); } else { - bpf_strlcpy(enable, controllers, sizeof(enable)); + strscpy(enable, controllers); } snprintf(path, sizeof(path), "%s/cgroup.subtree_control", cgroup_path); diff --git a/tools/testing/selftests/bpf/jit_disasm_helpers.c b/tools/testing/selftests/bpf/jit_disasm_helpers.c index febd6b12e372..364c557c5115 100644 --- a/tools/testing/selftests/bpf/jit_disasm_helpers.c +++ b/tools/testing/selftests/bpf/jit_disasm_helpers.c @@ -122,15 +122,15 @@ static int disasm_one_func(FILE *text_out, uint8_t *image, __u32 len) pc += cnt; } qsort(labels.pcs, labels.cnt, sizeof(*labels.pcs), cmp_u32); - for (i = 0; i < labels.cnt; ++i) - /* gcc is unable to infer upper bound for labels.cnt and assumes - * it to be U32_MAX. U32_MAX takes 10 decimal digits. - * snprintf below prints into labels.names[*], - * which has space only for two digits and a letter. - * To avoid truncation warning use (i % MAX_LOCAL_LABELS), - * which informs gcc about printed value upper bound. - */ - snprintf(labels.names[i], sizeof(labels.names[i]), "L%d", i % MAX_LOCAL_LABELS); + /* gcc is unable to infer upper bound for labels.cnt and + * assumes it to be U32_MAX. U32_MAX takes 10 decimal digits. + * snprintf below prints into labels.names[*], which has space + * only for two digits and a letter. To avoid truncation + * warning use (i < MAX_LOCAL_LABELS), which informs gcc about + * printed value upper bound. + */ + for (i = 0; i < labels.cnt && i < MAX_LOCAL_LABELS; ++i) + snprintf(labels.names[i], sizeof(labels.names[i]), "L%d", i); /* now print with labels */ labels.print_phase = true; diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 0a6a5561bed3..b82f572641b7 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -432,7 +432,7 @@ int make_sockaddr(int family, const char *addr_str, __u16 port, memset(addr, 0, sizeof(*sun)); sun->sun_family = family; sun->sun_path[0] = 0; - strcpy(sun->sun_path + 1, addr_str); + strscpy(sun->sun_path + 1, addr_str, sizeof(sun->sun_path) - 1); if (len) *len = offsetof(struct sockaddr_un, sun_path) + 1 + strlen(addr_str); return 0; @@ -581,8 +581,7 @@ int open_tuntap(const char *dev_name, bool need_mac) return -1; ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN); - strncpy(ifr.ifr_name, dev_name, IFNAMSIZ - 1); - ifr.ifr_name[IFNAMSIZ - 1] = '\0'; + strscpy(ifr.ifr_name, dev_name); err = ioctl(fd, TUNSETIFF, &ifr); if (!ASSERT_OK(err, "ioctl(TUNSETIFF)")) { diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 5225d69bf79b..c69080ca14f5 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -346,8 +346,7 @@ static void test_task_sleepable(void) close(finish_pipe[1]); test_data = malloc(sizeof(char) * 10); - strncpy(test_data, "test_data", 10); - test_data[9] = '\0'; + strscpy(test_data, "test_data", 10); test_data_long = malloc(sizeof(char) * 5000); for (int i = 0; i < 5000; ++i) { diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index b7d1b52309d0..f829b6f09bc9 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -281,7 +281,7 @@ static void test_dctcp_fallback(void) dctcp_skel = bpf_dctcp__open(); if (!ASSERT_OK_PTR(dctcp_skel, "dctcp_skel")) return; - strcpy(dctcp_skel->rodata->fallback_cc, "cubic"); + strscpy(dctcp_skel->rodata->fallback_cc, "cubic"); if (!ASSERT_OK(bpf_dctcp__load(dctcp_skel), "bpf_dctcp__load")) goto done; diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c index 9015e2c2ab12..478a77cb67e6 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c @@ -202,7 +202,7 @@ static void test_cgroup_iter_sleepable(int cgroup_fd, __u64 cgroup_id) iter_fd = bpf_iter_create(bpf_link__fd(link)); if (!ASSERT_GE(iter_fd, 0, "iter_create")) - goto out; + goto out_link; /* trigger the program run */ (void)read(iter_fd, buf, sizeof(buf)); @@ -210,6 +210,8 @@ static void test_cgroup_iter_sleepable(int cgroup_fd, __u64 cgroup_id) ASSERT_EQ(skel->bss->cgroup_id, cgroup_id, "cgroup_id"); close(iter_fd); +out_link: + bpf_link__destroy(link); out: cgrp_ls_sleepable__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c index dd75ccb03770..469e92869523 100644 --- a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c +++ b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c @@ -308,8 +308,10 @@ static int find_field_offset(struct btf *btf, char *pattern, regmatch_t *matches return -1; } - strncpy(type_str, type, type_sz); - strncpy(field_str, field, field_sz); + memcpy(type_str, type, type_sz); + type_str[type_sz] = '\0'; + memcpy(field_str, field, field_sz); + field_str[field_sz] = '\0'; btf_id = btf__find_by_name(btf, type_str); if (btf_id < 0) { PRINT_FAIL("No BTF info for type %s\n", type_str); diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c index b9f86cb91e81..5fda11590708 100644 --- a/tools/testing/selftests/bpf/prog_tests/dynptr.c +++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c @@ -137,11 +137,14 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ ); link = bpf_program__attach(prog); - if (!ASSERT_OK_PTR(link, "bpf_program__attach")) + if (!ASSERT_OK_PTR(link, "bpf_program__attach")) { + bpf_object__close(obj); goto cleanup; + } err = bpf_prog_test_run_opts(aux_prog_fd, &topts); bpf_link__destroy(link); + bpf_object__close(obj); if (!ASSERT_OK(err, "test_run")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c index c534b4d5f9da..3078d8264deb 100644 --- a/tools/testing/selftests/bpf/prog_tests/fd_array.c +++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c @@ -412,8 +412,8 @@ static void check_fd_array_cnt__fd_array_too_big(void) ASSERT_EQ(prog_fd, -E2BIG, "prog should have been rejected with -E2BIG"); cleanup_fds: - while (i > 0) - Close(extra_fds[--i]); + while (i-- > 0) + Close(extra_fds[i]); } void test_fd_array_cnt(void) diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index 08bae13248c4..fb4892681464 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -570,7 +570,7 @@ static int create_tap(const char *ifname) }; int fd, ret; - strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name)); + strscpy(ifr.ifr_name, ifname); fd = open("/dev/net/tun", O_RDWR); if (fd < 0) @@ -599,7 +599,7 @@ static int ifup(const char *ifname) struct ifreq ifr = {}; int sk, ret; - strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name)); + strscpy(ifr.ifr_name, ifname); sk = socket(PF_INET, SOCK_DGRAM, 0); if (sk < 0) diff --git a/tools/testing/selftests/bpf/prog_tests/htab_update.c b/tools/testing/selftests/bpf/prog_tests/htab_update.c index d0b405eb2966..ea1a6766fbe9 100644 --- a/tools/testing/selftests/bpf/prog_tests/htab_update.c +++ b/tools/testing/selftests/bpf/prog_tests/htab_update.c @@ -61,6 +61,7 @@ static void test_reenter_update(void) ASSERT_EQ(skel->bss->update_err, -EDEADLK, "no reentrancy"); out: + free(value); htab_update__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c index 6e35e13c2022..399fe9103f83 100644 --- a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c @@ -104,11 +104,8 @@ void test_kmem_cache_iter(void) if (!ASSERT_GE(iter_fd, 0, "iter_create")) goto destroy; - memset(buf, 0, sizeof(buf)); - while (read(iter_fd, buf, sizeof(buf)) > 0) { - /* Read out all contents */ - printf("%s", buf); - } + while (read(iter_fd, buf, sizeof(buf)) > 0) + ; /* Read out all contents */ /* Next reads should return 0 */ ASSERT_EQ(read(iter_fd, buf, sizeof(buf)), 0, "read"); diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index 9caef222e528..f81dcd609ee9 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -456,25 +456,23 @@ static void test_kprobe_multi_bench_attach(bool kernel) { LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); struct kprobe_multi_empty *skel = NULL; - char **syms = NULL; - size_t cnt = 0; + struct ksyms *ksyms = NULL; - if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "bpf_get_ksyms")) + if (!ASSERT_OK(bpf_get_ksyms(&ksyms, kernel), "bpf_get_ksyms")) return; skel = kprobe_multi_empty__open_and_load(); if (!ASSERT_OK_PTR(skel, "kprobe_multi_empty__open_and_load")) goto cleanup; - opts.syms = (const char **) syms; - opts.cnt = cnt; + opts.syms = (const char **)ksyms->filtered_syms; + opts.cnt = ksyms->filtered_cnt; do_bench_test(skel, &opts); cleanup: kprobe_multi_empty__destroy(skel); - if (syms) - free(syms); + free_kallsyms_local(ksyms); } static void test_kprobe_multi_bench_attach_addr(bool kernel) diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c index 3bc730b7c7fa..1b25d5c5f8fb 100644 --- a/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c +++ b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c @@ -117,7 +117,7 @@ void test_lwt_seg6local(void) const char *ns1 = NETNS_BASE "1"; const char *ns6 = NETNS_BASE "6"; struct nstoken *nstoken = NULL; - const char *foobar = "foobar"; + const char foobar[] = "foobar"; ssize_t bytes; int sfd, cfd; char buf[7]; diff --git a/tools/testing/selftests/bpf/prog_tests/map_kptr.c b/tools/testing/selftests/bpf/prog_tests/map_kptr.c index f372162c0280..03b46f17cf53 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_kptr.c +++ b/tools/testing/selftests/bpf/prog_tests/map_kptr.c @@ -118,15 +118,16 @@ exit: static int kern_sync_rcu_tasks_trace(struct rcu_tasks_trace_gp *rcu) { - long gp_seq = READ_ONCE(rcu->bss->gp_seq); LIBBPF_OPTS(bpf_test_run_opts, opts); + int ret; - if (!ASSERT_OK(bpf_prog_test_run_opts(bpf_program__fd(rcu->progs.do_call_rcu_tasks_trace), - &opts), "do_call_rcu_tasks_trace")) + WRITE_ONCE(rcu->bss->done, 0); + ret = bpf_prog_test_run_opts(bpf_program__fd(rcu->progs.call_rcu_tasks_trace), &opts); + if (!ASSERT_OK(ret, "call_rcu_tasks_trace")) return -EFAULT; - if (!ASSERT_OK(opts.retval, "opts.retval == 0")) + if (!ASSERT_OK(opts.retval, "call_rcu_tasks_trace retval")) return -EFAULT; - while (gp_seq == READ_ONCE(rcu->bss->gp_seq)) + while (!READ_ONCE(rcu->bss->done)) sched_yield(); return 0; } @@ -159,8 +160,6 @@ void serial_test_map_kptr(void) skel = rcu_tasks_trace_gp__open_and_load(); if (!ASSERT_OK_PTR(skel, "rcu_tasks_trace_gp__open_and_load")) return; - if (!ASSERT_OK(rcu_tasks_trace_gp__attach(skel), "rcu_tasks_trace_gp__attach")) - goto end; if (test__start_subtest("success-map")) { test_map_kptr_success(true); @@ -180,7 +179,5 @@ void serial_test_map_kptr(void) test_map_kptr_success(true); } -end: rcu_tasks_trace_gp__destroy(skel); - return; } diff --git a/tools/testing/selftests/bpf/prog_tests/map_kptr_race.c b/tools/testing/selftests/bpf/prog_tests/map_kptr_race.c new file mode 100644 index 000000000000..506ed55e8528 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/map_kptr_race.c @@ -0,0 +1,218 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ +#include <test_progs.h> +#include <network_helpers.h> + +#include "map_kptr_race.skel.h" + +static int get_map_id(int map_fd) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + + if (!ASSERT_OK(bpf_map_get_info_by_fd(map_fd, &info, &len), "get_map_info")) + return -1; + return info.id; +} + +static int read_refs(struct map_kptr_race *skel) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts); + int ret; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.count_ref), &opts); + if (!ASSERT_OK(ret, "count_ref run")) + return -1; + if (!ASSERT_OK(opts.retval, "count_ref retval")) + return -1; + return skel->bss->num_of_refs; +} + +static void test_htab_leak(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct map_kptr_race *skel, *watcher; + int ret, map_id; + + skel = map_kptr_race__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_htab_leak), &opts); + if (!ASSERT_OK(ret, "test_htab_leak run")) + goto out_skel; + if (!ASSERT_OK(opts.retval, "test_htab_leak retval")) + goto out_skel; + + map_id = get_map_id(bpf_map__fd(skel->maps.race_hash_map)); + if (!ASSERT_GE(map_id, 0, "map_id")) + goto out_skel; + + watcher = map_kptr_race__open_and_load(); + if (!ASSERT_OK_PTR(watcher, "watcher open_and_load")) + goto out_skel; + + watcher->bss->target_map_id = map_id; + watcher->links.map_put = bpf_program__attach(watcher->progs.map_put); + if (!ASSERT_OK_PTR(watcher->links.map_put, "attach fentry")) + goto out_watcher; + watcher->links.htab_map_free = bpf_program__attach(watcher->progs.htab_map_free); + if (!ASSERT_OK_PTR(watcher->links.htab_map_free, "attach fexit")) + goto out_watcher; + + map_kptr_race__destroy(skel); + skel = NULL; + + kern_sync_rcu(); + + while (!READ_ONCE(watcher->bss->map_freed)) + sched_yield(); + + ASSERT_EQ(watcher->bss->map_freed, 1, "map_freed"); + ASSERT_EQ(read_refs(watcher), 2, "htab refcount"); + +out_watcher: + map_kptr_race__destroy(watcher); +out_skel: + map_kptr_race__destroy(skel); +} + +static void test_percpu_htab_leak(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct map_kptr_race *skel, *watcher; + int ret, map_id; + + skel = map_kptr_race__open(); + if (!ASSERT_OK_PTR(skel, "open")) + return; + + skel->rodata->nr_cpus = libbpf_num_possible_cpus(); + if (skel->rodata->nr_cpus > 16) + skel->rodata->nr_cpus = 16; + + ret = map_kptr_race__load(skel); + if (!ASSERT_OK(ret, "load")) + goto out_skel; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_percpu_htab_leak), &opts); + if (!ASSERT_OK(ret, "test_percpu_htab_leak run")) + goto out_skel; + if (!ASSERT_OK(opts.retval, "test_percpu_htab_leak retval")) + goto out_skel; + + map_id = get_map_id(bpf_map__fd(skel->maps.race_percpu_hash_map)); + if (!ASSERT_GE(map_id, 0, "map_id")) + goto out_skel; + + watcher = map_kptr_race__open_and_load(); + if (!ASSERT_OK_PTR(watcher, "watcher open_and_load")) + goto out_skel; + + watcher->bss->target_map_id = map_id; + watcher->links.map_put = bpf_program__attach(watcher->progs.map_put); + if (!ASSERT_OK_PTR(watcher->links.map_put, "attach fentry")) + goto out_watcher; + watcher->links.htab_map_free = bpf_program__attach(watcher->progs.htab_map_free); + if (!ASSERT_OK_PTR(watcher->links.htab_map_free, "attach fexit")) + goto out_watcher; + + map_kptr_race__destroy(skel); + skel = NULL; + + kern_sync_rcu(); + + while (!READ_ONCE(watcher->bss->map_freed)) + sched_yield(); + + ASSERT_EQ(watcher->bss->map_freed, 1, "map_freed"); + ASSERT_EQ(read_refs(watcher), 2, "percpu_htab refcount"); + +out_watcher: + map_kptr_race__destroy(watcher); +out_skel: + map_kptr_race__destroy(skel); +} + +static void test_sk_ls_leak(void) +{ + struct map_kptr_race *skel, *watcher; + int listen_fd = -1, client_fd = -1, map_id; + + skel = map_kptr_race__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + if (!ASSERT_OK(map_kptr_race__attach(skel), "attach")) + goto out_skel; + + listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); + if (!ASSERT_GE(listen_fd, 0, "start_server")) + goto out_skel; + + client_fd = connect_to_fd(listen_fd, 0); + if (!ASSERT_GE(client_fd, 0, "connect_to_fd")) + goto out_skel; + + if (!ASSERT_EQ(skel->bss->sk_ls_leak_done, 1, "sk_ls_leak_done")) + goto out_skel; + + close(client_fd); + client_fd = -1; + close(listen_fd); + listen_fd = -1; + + map_id = get_map_id(bpf_map__fd(skel->maps.race_sk_ls_map)); + if (!ASSERT_GE(map_id, 0, "map_id")) + goto out_skel; + + watcher = map_kptr_race__open_and_load(); + if (!ASSERT_OK_PTR(watcher, "watcher open_and_load")) + goto out_skel; + + watcher->bss->target_map_id = map_id; + watcher->links.map_put = bpf_program__attach(watcher->progs.map_put); + if (!ASSERT_OK_PTR(watcher->links.map_put, "attach fentry")) + goto out_watcher; + watcher->links.sk_map_free = bpf_program__attach(watcher->progs.sk_map_free); + if (!ASSERT_OK_PTR(watcher->links.sk_map_free, "attach fexit")) + goto out_watcher; + + map_kptr_race__destroy(skel); + skel = NULL; + + kern_sync_rcu(); + + while (!READ_ONCE(watcher->bss->map_freed)) + sched_yield(); + + ASSERT_EQ(watcher->bss->map_freed, 1, "map_freed"); + ASSERT_EQ(read_refs(watcher), 2, "sk_ls refcount"); + +out_watcher: + map_kptr_race__destroy(watcher); +out_skel: + if (client_fd >= 0) + close(client_fd); + if (listen_fd >= 0) + close(listen_fd); + map_kptr_race__destroy(skel); +} + +void serial_test_map_kptr_race(void) +{ + if (test__start_subtest("htab_leak")) + test_htab_leak(); + if (test__start_subtest("percpu_htab_leak")) + test_percpu_htab_leak(); + if (test__start_subtest("sk_ls_leak")) + test_sk_ls_leak(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c index a043af9cd6d9..41441325e179 100644 --- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c +++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c @@ -28,9 +28,9 @@ static void test_queue_stack_map_by_type(int type) vals[i] = rand(); if (type == QUEUE) - strncpy(file, "./test_queue_map.bpf.o", sizeof(file)); + strscpy(file, "./test_queue_map.bpf.o"); else if (type == STACK) - strncpy(file, "./test_stack_map.bpf.o", sizeof(file)); + strscpy(file, "./test_stack_map.bpf.o"); else return; diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c index d93a0c7b1786..cb8dd2f63296 100644 --- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c +++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c @@ -422,15 +422,69 @@ static bool is_valid_range(enum num_t t, struct range x) } } -static struct range range_improve(enum num_t t, struct range old, struct range new) +static struct range range_intersection(enum num_t t, struct range old, struct range new) { return range(t, max_t(t, old.a, new.a), min_t(t, old.b, new.b)); } +/* + * Result is precise when 'x' and 'y' overlap or form a continuous range, + * result is an over-approximation if 'x' and 'y' do not overlap. + */ +static struct range range_union(enum num_t t, struct range x, struct range y) +{ + if (!is_valid_range(t, x)) + return y; + if (!is_valid_range(t, y)) + return x; + return range(t, min_t(t, x.a, y.a), max_t(t, x.b, y.b)); +} + +/* + * This function attempts to improve x range intersecting it with y. + * range_cast(... to_t ...) looses precision for ranges that pass to_t + * min/max boundaries. To avoid such precision loses this function + * splits both x and y into halves corresponding to non-overflowing + * sub-ranges: [0, smin] and [smax, -1]. + * Final result is computed as follows: + * + * ((x ∩ [0, smax]) ∩ (y ∩ [0, smax])) ∪ + * ((x ∩ [smin,-1]) ∩ (y ∩ [smin,-1])) + * + * Precision might still be lost if final union is not a continuous range. + */ +static struct range range_refine_in_halves(enum num_t x_t, struct range x, + enum num_t y_t, struct range y) +{ + struct range x_pos, x_neg, y_pos, y_neg, r_pos, r_neg; + u64 smax, smin, neg_one; + + if (t_is_32(x_t)) { + smax = (u64)(u32)S32_MAX; + smin = (u64)(u32)S32_MIN; + neg_one = (u64)(u32)(s32)(-1); + } else { + smax = (u64)S64_MAX; + smin = (u64)S64_MIN; + neg_one = U64_MAX; + } + x_pos = range_intersection(x_t, x, range(x_t, 0, smax)); + x_neg = range_intersection(x_t, x, range(x_t, smin, neg_one)); + y_pos = range_intersection(y_t, y, range(x_t, 0, smax)); + y_neg = range_intersection(y_t, y, range(y_t, smin, neg_one)); + r_pos = range_intersection(x_t, x_pos, range_cast(y_t, x_t, y_pos)); + r_neg = range_intersection(x_t, x_neg, range_cast(y_t, x_t, y_neg)); + return range_union(x_t, r_pos, r_neg); + +} + static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, struct range y) { struct range y_cast; + if (t_is_32(x_t) == t_is_32(y_t)) + x = range_refine_in_halves(x_t, x, y_t, y); + y_cast = range_cast(y_t, x_t, y); /* If we know that @@ -444,7 +498,7 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, */ if (x_t == S64 && y_t == S32 && y_cast.a <= S32_MAX && y_cast.b <= S32_MAX && (s64)x.a >= S32_MIN && (s64)x.b <= S32_MAX) - return range_improve(x_t, x, y_cast); + return range_intersection(x_t, x, y_cast); /* the case when new range knowledge, *y*, is a 32-bit subregister * range, while previous range knowledge, *x*, is a full register @@ -462,25 +516,11 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, x_swap = range(x_t, swap_low32(x.a, y_cast.a), swap_low32(x.b, y_cast.b)); if (!is_valid_range(x_t, x_swap)) return x; - return range_improve(x_t, x, x_swap); - } - - if (!t_is_32(x_t) && !t_is_32(y_t) && x_t != y_t) { - if (x_t == S64 && x.a > x.b) { - if (x.b < y.a && x.a <= y.b) - return range(x_t, x.a, y.b); - if (x.a > y.b && x.b >= y.a) - return range(x_t, y.a, x.b); - } else if (x_t == U64 && y.a > y.b) { - if (y.b < x.a && y.a <= x.b) - return range(x_t, y.a, x.b); - if (y.a > x.b && y.b >= x.a) - return range(x_t, x.a, y.b); - } + return range_intersection(x_t, x, x_swap); } /* otherwise, plain range cast and intersection works */ - return range_improve(x_t, x, y_cast); + return range_intersection(x_t, x, y_cast); } /* ======================= @@ -2091,7 +2131,7 @@ static struct subtest_case crafted_cases[] = { {U64, S64, {0, 0xffffffffULL}, {0x7fffffff, 0x7fffffff}}, {U64, U32, {0, 0x100000000}, {0, 0}}, - {U64, U32, {0xfffffffe, 0x100000000}, {0x80000000, 0x80000000}}, + {U64, U32, {0xfffffffe, 0x300000000}, {0x80000000, 0x80000000}}, {U64, S32, {0, 0xffffffff00000000ULL}, {0, 0}}, /* these are tricky cases where lower 32 bits allow to tighten 64 diff --git a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c index e4dac529d424..77fe1bfb7504 100644 --- a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c @@ -212,7 +212,7 @@ void test_setget_sockopt(void) if (!ASSERT_OK_PTR(skel, "open skel")) goto done; - strcpy(skel->rodata->veth, "binddevtest1"); + strscpy(skel->rodata->veth, "binddevtest1"); skel->rodata->veth_ifindex = if_nametoindex("binddevtest1"); if (!ASSERT_GT(skel->rodata->veth_ifindex, 0, "if_nametoindex")) goto done; diff --git a/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c b/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c index 3eefdfed1db9..657d897958b6 100644 --- a/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c +++ b/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c @@ -34,7 +34,7 @@ void test_skc_to_unix_sock(void) memset(&sockaddr, 0, sizeof(sockaddr)); sockaddr.sun_family = AF_UNIX; - strncpy(sockaddr.sun_path, sock_path, strlen(sock_path)); + strscpy(sockaddr.sun_path, sock_path); sockaddr.sun_path[0] = '\0'; err = bind(sockfd, (struct sockaddr *)&sockaddr, sizeof(sockaddr)); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 256707e7d20d..dd3c757859f6 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -204,7 +204,7 @@ static void test_skmsg_helpers_with_link(enum bpf_map_type map_type) /* Fail since bpf_link for the same prog type has been created. */ link2 = bpf_program__attach_sockmap(prog_clone, map); if (!ASSERT_ERR_PTR(link2, "bpf_program__attach_sockmap")) { - bpf_link__detach(link2); + bpf_link__destroy(link2); goto out; } @@ -230,7 +230,7 @@ static void test_skmsg_helpers_with_link(enum bpf_map_type map_type) if (!ASSERT_OK(err, "bpf_link_update")) goto out; out: - bpf_link__detach(link); + bpf_link__destroy(link); test_skmsg_load_helpers__destroy(skel); } @@ -417,7 +417,7 @@ static void test_sockmap_skb_verdict_attach_with_link(void) if (!ASSERT_OK_PTR(link, "bpf_program__attach_sockmap")) goto out; - bpf_link__detach(link); + bpf_link__destroy(link); err = bpf_prog_attach(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT, 0); if (!ASSERT_OK(err, "bpf_prog_attach")) @@ -426,7 +426,7 @@ static void test_sockmap_skb_verdict_attach_with_link(void) /* Fail since attaching with the same prog/map has been done. */ link = bpf_program__attach_sockmap(prog, map); if (!ASSERT_ERR_PTR(link, "bpf_program__attach_sockmap")) - bpf_link__detach(link); + bpf_link__destroy(link); err = bpf_prog_detach2(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT); if (!ASSERT_OK(err, "bpf_prog_detach2")) @@ -747,13 +747,13 @@ static void test_sockmap_skb_verdict_peek_with_link(void) test_sockmap_skb_verdict_peek_helper(map); ASSERT_EQ(pass->bss->clone_called, 1, "clone_called"); out: - bpf_link__detach(link); + bpf_link__destroy(link); test_sockmap_pass_prog__destroy(pass); } static void test_sockmap_unconnected_unix(void) { - int err, map, stream = 0, dgram = 0, zero = 0; + int err, map, stream = -1, dgram = -1, zero = 0; struct test_sockmap_pass_prog *skel; skel = test_sockmap_pass_prog__open_and_load(); @@ -764,22 +764,22 @@ static void test_sockmap_unconnected_unix(void) stream = xsocket(AF_UNIX, SOCK_STREAM, 0); if (stream < 0) - return; + goto out; dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0); - if (dgram < 0) { - close(stream); - return; - } + if (dgram < 0) + goto out; err = bpf_map_update_elem(map, &zero, &stream, BPF_ANY); - ASSERT_ERR(err, "bpf_map_update_elem(stream)"); + if (!ASSERT_ERR(err, "bpf_map_update_elem(stream)")) + goto out; err = bpf_map_update_elem(map, &zero, &dgram, BPF_ANY); ASSERT_OK(err, "bpf_map_update_elem(dgram)"); - +out: close(stream); close(dgram); + test_sockmap_pass_prog__destroy(skel); } static void test_sockmap_many_socket(void) @@ -1027,7 +1027,7 @@ static void test_sockmap_skb_verdict_vsock_poll(void) if (xrecv_nonblock(conn, &buf, 1, 0) != 1) FAIL("xrecv_nonblock"); detach: - bpf_link__detach(link); + bpf_link__destroy(link); close: xclose(conn); xclose(peer); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index f1bdccc7e4e7..cc0c68bab907 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -899,7 +899,7 @@ static void test_msg_redir_to_listening_with_link(struct test_sockmap_listen *sk redir_to_listening(family, sotype, sock_map, verdict_map, REDIR_EGRESS); - bpf_link__detach(link); + bpf_link__destroy(link); } static void redir_partial(int family, int sotype, int sock_map, int parser_map) diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index ba6b3ec1156a..53637431ec5d 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -142,7 +142,7 @@ static int getsetsockopt(void) /* TCP_CONGESTION can extend the string */ - strcpy(buf.cc, "nv"); + strscpy(buf.cc, "nv"); err = setsockopt(fd, SOL_TCP, TCP_CONGESTION, &buf, strlen("nv")); if (err) { log_err("Failed to call setsockopt(TCP_CONGESTION)"); diff --git a/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c index 4006879ca3fe..d42123a0fb16 100644 --- a/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c +++ b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c @@ -54,9 +54,7 @@ static void test_private_stack_fail(void) } err = struct_ops_private_stack_fail__load(skel); - if (!ASSERT_ERR(err, "struct_ops_private_stack_fail__load")) - goto cleanup; - return; + ASSERT_ERR(err, "struct_ops_private_stack_fail__load"); cleanup: struct_ops_private_stack_fail__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_data.h b/tools/testing/selftests/bpf/prog_tests/task_local_data.h index 0f86b9275cf9..8342e2fe5260 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_local_data.h +++ b/tools/testing/selftests/bpf/prog_tests/task_local_data.h @@ -262,7 +262,7 @@ retry: if (!atomic_compare_exchange_strong(&tld_meta_p->cnt, &cnt, cnt + 1)) goto retry; - strncpy(tld_meta_p->metadata[i].name, name, TLD_NAME_LEN); + strscpy(tld_meta_p->metadata[i].name, name); atomic_store(&tld_meta_p->metadata[i].size, size); return (tld_key_t){(__s16)off}; } diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c index dd7a138d8c3d..2955750ddada 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c @@ -1360,10 +1360,8 @@ static void test_tc_opts_dev_cleanup_target(int target) assert_mprog_count_ifindex(ifindex, target, 4); - ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth"); - ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed"); - ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); - return; + goto cleanup; + cleanup3: err = bpf_prog_detach_opts(fd3, loopback, target, &optd); ASSERT_OK(err, "prog_detach"); diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index 76d72a59365e..64fbda082309 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -1095,7 +1095,7 @@ static int tun_open(char *name) ifr.ifr_flags = IFF_TUN | IFF_NO_PI; if (*name) - strncpy(ifr.ifr_name, name, IFNAMSIZ); + strscpy(ifr.ifr_name, name); err = ioctl(fd, TUNSETIFF, &ifr); if (!ASSERT_OK(err, "ioctl TUNSETIFF")) diff --git a/tools/testing/selftests/bpf/prog_tests/test_sysctl.c b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c index 273dd41ca09e..2a1ff821bc97 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_sysctl.c +++ b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c @@ -27,6 +27,7 @@ struct sysctl_test { OP_EPERM, SUCCESS, } result; + struct bpf_object *obj; }; static struct sysctl_test tests[] = { @@ -1471,6 +1472,7 @@ static int load_sysctl_prog_file(struct sysctl_test *test) return -1; } + test->obj = obj; return prog_fd; } @@ -1573,6 +1575,7 @@ out: /* Detaching w/o checking return code: best effort attempt. */ if (progfd != -1) bpf_prog_detach(cgfd, atype); + bpf_object__close(test->obj); close(progfd); printf("[%s]\n", err ? "FAIL" : "PASS"); return err; diff --git a/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c index 0fe0a8f62486..7fc4d7dd70ef 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c +++ b/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c @@ -699,7 +699,7 @@ void test_tc_tunnel(void) return; if (!ASSERT_OK(setup(), "global setup")) - return; + goto out; for (i = 0; i < ARRAY_SIZE(subtests_cfg); i++) { cfg = &subtests_cfg[i]; @@ -711,4 +711,7 @@ void test_tc_tunnel(void) subtest_cleanup(cfg); } cleanup(); + +out: + test_tc_tunnel__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_veristat.c b/tools/testing/selftests/bpf/prog_tests/test_veristat.c index b38c16b4247f..9aff08ac55c0 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_veristat.c +++ b/tools/testing/selftests/bpf/prog_tests/test_veristat.c @@ -24,9 +24,9 @@ static struct fixture *init_fixture(void) /* for no_alu32 and cpuv4 veristat is in parent folder */ if (access("./veristat", F_OK) == 0) - strcpy(fix->veristat, "./veristat"); + strscpy(fix->veristat, "./veristat"); else if (access("../veristat", F_OK) == 0) - strcpy(fix->veristat, "../veristat"); + strscpy(fix->veristat, "../veristat"); else PRINT_FAIL("Can't find veristat binary"); diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c index bab4a31621c7..7e38ec6e656b 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c +++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c @@ -2003,9 +2003,17 @@ int testapp_stats_tx_invalid_descs(struct test_spec *test) int testapp_stats_rx_full(struct test_spec *test) { - if (pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE)) + struct pkt_stream *tmp; + + tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); + if (!tmp) + return TEST_FAILURE; + test->ifobj_tx->xsk->pkt_stream = tmp; + + tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); + if (!tmp) return TEST_FAILURE; - test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); + test->ifobj_rx->xsk->pkt_stream = tmp; test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS; test->ifobj_rx->release_rx = false; @@ -2015,9 +2023,17 @@ int testapp_stats_rx_full(struct test_spec *test) int testapp_stats_fill_empty(struct test_spec *test) { - if (pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE)) + struct pkt_stream *tmp; + + tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); + if (!tmp) + return TEST_FAILURE; + test->ifobj_tx->xsk->pkt_stream = tmp; + + tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); + if (!tmp) return TEST_FAILURE; - test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); + test->ifobj_rx->xsk->pkt_stream = tmp; test->ifobj_rx->use_fill_ring = false; test->ifobj_rx->validation_func = validate_fill_empty; diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c index 2ee17ef1dae2..56cbea280fbd 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c @@ -62,8 +62,10 @@ static void release_child(struct child *child) return; close(child->go[1]); close(child->go[0]); - if (child->thread) + if (child->thread) { pthread_join(child->thread, NULL); + child->thread = 0; + } close(child->c2p[0]); close(child->c2p[1]); if (child->pid > 0) @@ -331,6 +333,8 @@ test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi { static struct child child; + memset(&child, 0, sizeof(child)); + /* no pid filter */ __test_attach_api(binary, pattern, opts, NULL); diff --git a/tools/testing/selftests/bpf/prog_tests/verifier_log.c b/tools/testing/selftests/bpf/prog_tests/verifier_log.c index 8337c6bc5b95..aaa2854974c0 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier_log.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier_log.c @@ -47,7 +47,7 @@ static int load_prog(struct bpf_prog_load_opts *opts, bool expect_load_error) static void verif_log_subtest(const char *name, bool expect_load_error, int log_level) { LIBBPF_OPTS(bpf_prog_load_opts, opts); - char *exp_log, prog_name[16], op_name[32]; + char *exp_log, prog_name[24], op_name[32]; struct test_log_buf *skel; struct bpf_program *prog; size_t fixed_log_sz; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index fb952703653e..e8ea26464349 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -610,6 +610,61 @@ out: system("ip link del bond"); } +/* + * Test that changing xmit_hash_policy to vlan+srcmac is rejected when a + * native XDP program is loaded on a bond in 802.3ad or balance-xor mode. + * These modes support XDP only when xmit_hash_policy != vlan+srcmac; freely + * changing the policy creates an inconsistency that triggers a WARNING in + * dev_xdp_uninstall() during device teardown. + */ +static void test_xdp_bonding_xmit_policy_compat(struct skeletons *skeletons) +{ + struct nstoken *nstoken = NULL; + int bond_ifindex = -1; + int xdp_fd, err; + + SYS(out, "ip netns add ns_xmit_policy"); + nstoken = open_netns("ns_xmit_policy"); + if (!ASSERT_OK_PTR(nstoken, "open ns_xmit_policy")) + goto out; + + /* 802.3ad with layer2+3 policy: native XDP is supported */ + SYS(out, "ip link add bond0 type bond mode 802.3ad xmit_hash_policy layer2+3"); + SYS(out, "ip link add veth0 type veth peer name veth0p"); + SYS(out, "ip link set veth0 master bond0"); + SYS(out, "ip link set bond0 up"); + + bond_ifindex = if_nametoindex("bond0"); + if (!ASSERT_GT(bond_ifindex, 0, "bond0 ifindex")) + goto out; + + xdp_fd = bpf_program__fd(skeletons->xdp_dummy->progs.xdp_dummy_prog); + if (!ASSERT_GE(xdp_fd, 0, "xdp_dummy fd")) + goto out; + + err = bpf_xdp_attach(bond_ifindex, xdp_fd, XDP_FLAGS_DRV_MODE, NULL); + if (!ASSERT_OK(err, "attach XDP to bond0")) + goto out; + + /* With XDP loaded, switching to vlan+srcmac must be rejected */ + err = system("ip link set bond0 type bond xmit_hash_policy vlan+srcmac 2>/dev/null"); + ASSERT_NEQ(err, 0, "vlan+srcmac change with XDP loaded should fail"); + + /* Detach XDP first, then the same change must succeed */ + ASSERT_OK(bpf_xdp_detach(bond_ifindex, XDP_FLAGS_DRV_MODE, NULL), + "detach XDP from bond0"); + + bond_ifindex = -1; + err = system("ip link set bond0 type bond xmit_hash_policy vlan+srcmac 2>/dev/null"); + ASSERT_OK(err, "vlan+srcmac change without XDP should succeed"); + +out: + if (bond_ifindex > 0) + bpf_xdp_detach(bond_ifindex, XDP_FLAGS_DRV_MODE, NULL); + close_netns(nstoken); + SYS_NOFAIL("ip netns del ns_xmit_policy"); +} + static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { @@ -677,6 +732,9 @@ void serial_test_xdp_bonding(void) test_case->xmit_policy); } + if (test__start_subtest("xdp_bonding_xmit_policy_compat")) + test_xdp_bonding_xmit_policy_compat(&skeletons); + if (test__start_subtest("xdp_bonding_redirect_multi")) test_xdp_bonding_redirect_multi(&skeletons); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c index 3f9146d83d79..325e0b64dc35 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c @@ -67,7 +67,7 @@ void test_xdp_flowtable(void) struct nstoken *tok = NULL; int iifindex, stats_fd; __u32 value, key = 0; - struct bpf_link *link; + struct bpf_link *link = NULL; if (SYS_NOFAIL("nft -v")) { fprintf(stdout, "Missing required nft tool\n"); @@ -160,6 +160,7 @@ void test_xdp_flowtable(void) ASSERT_GE(value, N_PACKETS - 2, "bpf_xdp_flow_lookup failed"); out: + bpf_link__destroy(link); xdp_flowtable__destroy(skel); if (tok) close_netns(tok); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index 19f92affc2da..5c31054ad4a4 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -126,10 +126,10 @@ static int open_xsk(int ifindex, struct xsk *xsk) static void close_xsk(struct xsk *xsk) { - if (xsk->umem) - xsk_umem__delete(xsk->umem); if (xsk->socket) xsk_socket__delete(xsk->socket); + if (xsk->umem) + xsk_umem__delete(xsk->umem); munmap(xsk->umem_area, UMEM_SIZE); } diff --git a/tools/testing/selftests/bpf/progs/dmabuf_iter.c b/tools/testing/selftests/bpf/progs/dmabuf_iter.c index 13cdb11fdeb2..9cbb7442646e 100644 --- a/tools/testing/selftests/bpf/progs/dmabuf_iter.c +++ b/tools/testing/selftests/bpf/progs/dmabuf_iter.c @@ -48,7 +48,7 @@ int dmabuf_collector(struct bpf_iter__dmabuf *ctx) /* Buffers are not required to be named */ if (pname) { - if (bpf_probe_read_kernel(name, sizeof(name), pname)) + if (bpf_probe_read_kernel_str(name, sizeof(name), pname) < 0) return 1; /* Name strings can be provided by userspace */ diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c index a01c2736890f..858af5988a38 100644 --- a/tools/testing/selftests/bpf/progs/exceptions_assert.c +++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c @@ -18,43 +18,43 @@ return *(u64 *)num; \ } -__msg(": R0=0xffffffff80000000") +__msg("R{{.}}=0xffffffff80000000") check_assert(s64, ==, eq_int_min, INT_MIN); -__msg(": R0=0x7fffffff") +__msg("R{{.}}=0x7fffffff") check_assert(s64, ==, eq_int_max, INT_MAX); -__msg(": R0=0") +__msg("R{{.}}=0") check_assert(s64, ==, eq_zero, 0); -__msg(": R0=0x8000000000000000 R1=0x8000000000000000") +__msg("R{{.}}=0x8000000000000000") check_assert(s64, ==, eq_llong_min, LLONG_MIN); -__msg(": R0=0x7fffffffffffffff R1=0x7fffffffffffffff") +__msg("R{{.}}=0x7fffffffffffffff") check_assert(s64, ==, eq_llong_max, LLONG_MAX); -__msg(": R0=scalar(id=1,smax=0x7ffffffe)") +__msg("R{{.}}=scalar(id=1,smax=0x7ffffffe)") check_assert(s64, <, lt_pos, INT_MAX); -__msg(": R0=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))") +__msg("R{{.}}=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))") check_assert(s64, <, lt_zero, 0); -__msg(": R0=scalar(id=1,smax=0xffffffff7fffffff") +__msg("R{{.}}=scalar(id=1,smax=0xffffffff7fffffff") check_assert(s64, <, lt_neg, INT_MIN); -__msg(": R0=scalar(id=1,smax=0x7fffffff)") +__msg("R{{.}}=scalar(id=1,smax=0x7fffffff)") check_assert(s64, <=, le_pos, INT_MAX); -__msg(": R0=scalar(id=1,smax=0)") +__msg("R{{.}}=scalar(id=1,smax=0)") check_assert(s64, <=, le_zero, 0); -__msg(": R0=scalar(id=1,smax=0xffffffff80000000") +__msg("R{{.}}=scalar(id=1,smax=0xffffffff80000000") check_assert(s64, <=, le_neg, INT_MIN); -__msg(": R0=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") +__msg("R{{.}}=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, >, gt_pos, INT_MAX); -__msg(": R0=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") +__msg("R{{.}}=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, >, gt_zero, 0); -__msg(": R0=scalar(id=1,smin=0xffffffff80000001") +__msg("R{{.}}=scalar(id=1,smin=0xffffffff80000001") check_assert(s64, >, gt_neg, INT_MIN); -__msg(": R0=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") +__msg("R{{.}}=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, >=, ge_pos, INT_MAX); -__msg(": R0=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") +__msg("R{{.}}=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, >=, ge_zero, 0); -__msg(": R0=scalar(id=1,smin=0xffffffff80000000") +__msg("R{{.}}=scalar(id=1,smin=0xffffffff80000000") check_assert(s64, >=, ge_neg, INT_MIN); SEC("?tc") diff --git a/tools/testing/selftests/bpf/progs/get_func_args_test.c b/tools/testing/selftests/bpf/progs/get_func_args_test.c index 180ba5098ca1..075a1180ec26 100644 --- a/tools/testing/selftests/bpf/progs/get_func_args_test.c +++ b/tools/testing/selftests/bpf/progs/get_func_args_test.c @@ -167,7 +167,7 @@ int BPF_PROG(tp_test2) } __u64 test7_result = 0; -#if defined(bpf_target_x86) || defined(bpf_target_arm64) +#if defined(bpf_target_x86) || defined(bpf_target_arm64) || defined(bpf_target_riscv) SEC("fsession/bpf_fentry_test1") int BPF_PROG(test7) { diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_test.c index 43ff836a8ed8..45eaa54d1ac7 100644 --- a/tools/testing/selftests/bpf/progs/get_func_ip_test.c +++ b/tools/testing/selftests/bpf/progs/get_func_ip_test.c @@ -106,7 +106,7 @@ int BPF_URETPROBE(test8, int ret) __u64 test9_entry_result = 0; __u64 test9_exit_result = 0; -#if defined(bpf_target_x86) || defined(bpf_target_arm64) +#if defined(bpf_target_x86) || defined(bpf_target_arm64) || defined(bpf_target_riscv) SEC("fsession/bpf_fentry_test1") int BPF_PROG(test9, int a) { diff --git a/tools/testing/selftests/bpf/progs/map_kptr_race.c b/tools/testing/selftests/bpf/progs/map_kptr_race.c new file mode 100644 index 000000000000..f6f136cd8f60 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/map_kptr_race.c @@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "../test_kmods/bpf_testmod_kfunc.h" + +struct map_value { + struct prog_test_ref_kfunc __kptr *ref_ptr; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} race_hash_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} race_percpu_hash_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct map_value); +} race_sk_ls_map SEC(".maps"); + +int num_of_refs; +int sk_ls_leak_done; +int target_map_id; +int map_freed; +const volatile int nr_cpus; + +SEC("tc") +int test_htab_leak(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *p, *old; + struct map_value val = {}; + struct map_value *v; + int key = 0; + + if (bpf_map_update_elem(&race_hash_map, &key, &val, BPF_ANY)) + return 1; + + v = bpf_map_lookup_elem(&race_hash_map, &key); + if (!v) + return 2; + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!p) + return 3; + old = bpf_kptr_xchg(&v->ref_ptr, p); + if (old) + bpf_kfunc_call_test_release(old); + + bpf_map_delete_elem(&race_hash_map, &key); + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!p) + return 4; + old = bpf_kptr_xchg(&v->ref_ptr, p); + if (old) + bpf_kfunc_call_test_release(old); + + return 0; +} + +static int fill_percpu_kptr(struct map_value *v) +{ + struct prog_test_ref_kfunc *p, *old; + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!p) + return 1; + old = bpf_kptr_xchg(&v->ref_ptr, p); + if (old) + bpf_kfunc_call_test_release(old); + return 0; +} + +SEC("tc") +int test_percpu_htab_leak(struct __sk_buff *skb) +{ + struct map_value *v, *arr[16] = {}; + struct map_value val = {}; + int key = 0; + int err = 0; + + if (bpf_map_update_elem(&race_percpu_hash_map, &key, &val, BPF_ANY)) + return 1; + + for (int i = 0; i < nr_cpus; i++) { + v = bpf_map_lookup_percpu_elem(&race_percpu_hash_map, &key, i); + if (!v) + return 2; + arr[i] = v; + } + + bpf_map_delete_elem(&race_percpu_hash_map, &key); + + for (int i = 0; i < nr_cpus; i++) { + v = arr[i]; + err = fill_percpu_kptr(v); + if (err) + return 3; + } + + return 0; +} + +SEC("tp_btf/inet_sock_set_state") +int BPF_PROG(test_sk_ls_leak, struct sock *sk, int oldstate, int newstate) +{ + struct prog_test_ref_kfunc *p, *old; + struct map_value *v; + + if (newstate != BPF_TCP_SYN_SENT) + return 0; + + if (sk_ls_leak_done) + return 0; + + v = bpf_sk_storage_get(&race_sk_ls_map, sk, NULL, + BPF_SK_STORAGE_GET_F_CREATE); + if (!v) + return 0; + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!p) + return 0; + old = bpf_kptr_xchg(&v->ref_ptr, p); + if (old) + bpf_kfunc_call_test_release(old); + + bpf_sk_storage_delete(&race_sk_ls_map, sk); + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!p) + return 0; + old = bpf_kptr_xchg(&v->ref_ptr, p); + if (old) + bpf_kfunc_call_test_release(old); + + sk_ls_leak_done = 1; + return 0; +} + +long target_map_ptr; + +SEC("fentry/bpf_map_put") +int BPF_PROG(map_put, struct bpf_map *map) +{ + if (target_map_id && map->id == (u32)target_map_id) + target_map_ptr = (long)map; + return 0; +} + +SEC("fexit/htab_map_free") +int BPF_PROG(htab_map_free, struct bpf_map *map) +{ + if (target_map_ptr && (long)map == target_map_ptr) + map_freed = 1; + return 0; +} + +SEC("fexit/bpf_sk_storage_map_free") +int BPF_PROG(sk_map_free, struct bpf_map *map) +{ + if (target_map_ptr && (long)map == target_map_ptr) + map_freed = 1; + return 0; +} + +SEC("syscall") +int count_ref(void *ctx) +{ + struct prog_test_ref_kfunc *p; + unsigned long arg = 0; + + p = bpf_kfunc_call_test_acquire(&arg); + if (!p) + return 1; + + num_of_refs = p->cnt.refs.counter; + + bpf_kfunc_call_test_release(p); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/profiler.h b/tools/testing/selftests/bpf/progs/profiler.h index 3bac4fdd4bdf..637fbf2c2652 100644 --- a/tools/testing/selftests/bpf/progs/profiler.h +++ b/tools/testing/selftests/bpf/progs/profiler.h @@ -169,7 +169,7 @@ enum bpf_function_id { profiler_bpf_sched_process_exec, profiler_bpf_sched_process_exit, profiler_bpf_sys_enter_kill, - profiler_bpf_do_filp_open_ret, + profiler_bpf_do_file_open_ret, profiler_bpf_sched_process_fork, profiler_bpf_vfs_link, profiler_bpf_vfs_symlink, diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 813143b4985d..9044dd8aff11 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -751,11 +751,11 @@ out: return 0; } -SEC("kretprobe/do_filp_open") -int kprobe_ret__do_filp_open(struct pt_regs* ctx) +SEC("kretprobe/do_file_open") +int kprobe_ret__do_file_open(struct pt_regs *ctx) { struct bpf_func_stats_ctx stats_ctx; - bpf_stats_enter(&stats_ctx, profiler_bpf_do_filp_open_ret); + bpf_stats_enter(&stats_ctx, profiler_bpf_do_file_open_ret); struct file* filp = (struct file*)PT_REGS_RC_CORE(ctx); diff --git a/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c b/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c index df4873558634..189c05c6abcc 100644 --- a/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c +++ b/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c @@ -1,36 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> -#include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../test_kmods/bpf_testmod_kfunc.h" -struct task_ls_map { - __uint(type, BPF_MAP_TYPE_TASK_STORAGE); - __uint(map_flags, BPF_F_NO_PREALLOC); - __type(key, int); - __type(value, int); -} task_ls_map SEC(".maps"); - -long gp_seq; +int done; SEC("syscall") -int do_call_rcu_tasks_trace(void *ctx) -{ - struct task_struct *current; - int *v; - - current = bpf_get_current_task_btf(); - v = bpf_task_storage_get(&task_ls_map, current, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE); - if (!v) - return 1; - /* Invoke call_rcu_tasks_trace */ - return bpf_task_storage_delete(&task_ls_map, current); -} - -SEC("kprobe/rcu_tasks_trace_postgp") -int rcu_tasks_trace_postgp(void *ctx) +int call_rcu_tasks_trace(void *ctx) { - __sync_add_and_fetch(&gp_seq, 1); - return 0; + return bpf_kfunc_call_test_call_rcu_tasks_trace(&done); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c index 0a0f371a2dec..fa73b17cb999 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c @@ -1,12 +1,12 @@ -#include <stdbool.h> -#include <linux/bpf.h> -#include <linux/errno.h> -#include <linux/if_ether.h> -#include <linux/pkt_cls.h> +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> #include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> +#include <errno.h> + #include "bpf_kfuncs.h" +#include "bpf_tracing_net.h" #define META_SIZE 32 @@ -42,7 +42,7 @@ static bool check_metadata(const char *file, int line, __u8 *meta_have) if (!__builtin_memcmp(meta_have, meta_want, META_SIZE)) return true; - bpf_stream_printk(BPF_STREAM_STDERR, + bpf_stream_printk(BPF_STDERR, "FAIL:%s:%d: metadata mismatch\n" " have:\n %pI6\n %pI6\n" " want:\n %pI6\n %pI6\n", diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index 560531404bce..e526315c718a 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -1148,7 +1148,7 @@ l0_%=: r0 = 0; \ SEC("xdp") __description("bound check with JMP32_JSLT for crossing 32-bit signed boundary") __success __retval(0) -__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */ +__flag(BPF_F_TEST_REG_INVARIANTS) __naked void crossing_32_bit_signed_boundary_2(void) { asm volatile (" \ @@ -1863,4 +1863,178 @@ l1_%=: r0 = 1; \ : __clobber_all); } +/* This test covers the bounds deduction when the u64 range and the tnum + * overlap only at umax. After instruction 3, the ranges look as follows: + * + * 0 umin=0xe01 umax=0xf00 U64_MAX + * | [xxxxxxxxxxxxxx] | + * |----------------------------|------------------------------| + * | x x | tnum values + * + * The verifier can therefore deduce that the R0=0xf0=240. + */ +SEC("socket") +__description("bounds refinement with single-value tnum on umax") +__msg("3: (15) if r0 == 0xe0 {{.*}} R0=240") +__success __log_level(2) +__flag(BPF_F_TEST_REG_INVARIANTS) +__naked void bounds_refinement_tnum_umax(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + r0 |= 0xe0; \ + r0 &= 0xf0; \ + if r0 == 0xe0 goto +2; \ + if r0 == 0xf0 goto +1; \ + r10 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +/* This test covers the bounds deduction when the u64 range and the tnum + * overlap only at umin. After instruction 3, the ranges look as follows: + * + * 0 umin=0xe00 umax=0xeff U64_MAX + * | [xxxxxxxxxxxxxx] | + * |----------------------------|------------------------------| + * | x x | tnum values + * + * The verifier can therefore deduce that the R0=0xe0=224. + */ +SEC("socket") +__description("bounds refinement with single-value tnum on umin") +__msg("3: (15) if r0 == 0xf0 {{.*}} R0=224") +__success __log_level(2) +__flag(BPF_F_TEST_REG_INVARIANTS) +__naked void bounds_refinement_tnum_umin(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + r0 |= 0xe0; \ + r0 &= 0xf0; \ + if r0 == 0xf0 goto +2; \ + if r0 == 0xe0 goto +1; \ + r10 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +/* This test covers the bounds deduction when the only possible tnum value is + * in the middle of the u64 range. After instruction 3, the ranges look as + * follows: + * + * 0 umin=0x7cf umax=0x7df U64_MAX + * | [xxxxxxxxxxxx] | + * |----------------------------|------------------------------| + * | x x x x x | tnum values + * | +--- 0x7e0 + * +--- 0x7d0 + * + * Since the lower four bits are zero, the tnum and the u64 range only overlap + * in R0=0x7d0=2000. Instruction 5 is therefore dead code. + */ +SEC("socket") +__description("bounds refinement with single-value tnum in middle of range") +__msg("3: (a5) if r0 < 0x7cf {{.*}} R0=2000") +__success __log_level(2) +__naked void bounds_refinement_tnum_middle(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + if r0 & 0x0f goto +4; \ + if r0 > 0x7df goto +3; \ + if r0 < 0x7cf goto +2; \ + if r0 == 0x7d0 goto +1; \ + r10 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +/* This test cover the negative case for the tnum/u64 overlap. Since + * they contain the same two values (i.e., {0, 1}), we can't deduce + * anything more. + */ +SEC("socket") +__description("bounds refinement: several overlaps between tnum and u64") +__msg("2: (25) if r0 > 0x1 {{.*}} R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=1,var_off=(0x0; 0x1))") +__failure __log_level(2) +__naked void bounds_refinement_several_overlaps(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + if r0 < 0 goto +3; \ + if r0 > 1 goto +2; \ + if r0 == 1 goto +1; \ + r10 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +/* This test cover the negative case for the tnum/u64 overlap. Since + * they overlap in the two values contained by the u64 range (i.e., + * {0xf, 0x10}), we can't deduce anything more. + */ +SEC("socket") +__description("bounds refinement: multiple overlaps between tnum and u64") +__msg("2: (25) if r0 > 0x10 {{.*}} R0=scalar(smin=umin=smin32=umin32=15,smax=umax=smax32=umax32=16,var_off=(0x0; 0x1f))") +__failure __log_level(2) +__naked void bounds_refinement_multiple_overlaps(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + if r0 < 0xf goto +3; \ + if r0 > 0x10 goto +2; \ + if r0 == 0x10 goto +1; \ + r10 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__success +__flag(BPF_F_TEST_REG_INVARIANTS) +__naked void signed_unsigned_intersection32_case1(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + w0 &= 0xffffffff; \ + if w0 < 0x3 goto 1f; /* on fall-through u32 range [3..U32_MAX] */ \ + if w0 s> 0x1 goto 1f; /* on fall-through s32 range [S32_MIN..1] */ \ + if w0 s< 0x0 goto 1f; /* range can be narrowed to [S32_MIN..-1] */ \ + r10 = 0; /* thus predicting the jump. */ \ +1: exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__success +__flag(BPF_F_TEST_REG_INVARIANTS) +__naked void signed_unsigned_intersection32_case2(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + w0 &= 0xffffffff; \ + if w0 > 0x80000003 goto 1f; /* on fall-through u32 range [0..S32_MIN+3] */ \ + if w0 s< -3 goto 1f; /* on fall-through s32 range [-3..S32_MAX] */ \ + if w0 s> 5 goto 1f; /* on fall-through s32 range [-3..5] */ \ + if w0 <= 5 goto 1f; /* range can be narrowed to [0..5] */ \ + r10 = 0; /* thus predicting the jump */ \ +1: exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c index 2ef346c827c2..7bf7dbfd237d 100644 --- a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c +++ b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c @@ -363,4 +363,68 @@ void alu32_negative_offset(void) __sink(path[0]); } +void dummy_calls(void) +{ + bpf_iter_num_new(0, 0, 0); + bpf_iter_num_next(0); + bpf_iter_num_destroy(0); +} + +SEC("socket") +__success +__flag(BPF_F_TEST_STATE_FREQ) +int spurious_precision_marks(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile( + "r1 = %[iter];" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "1:" + "r1 = %[iter];" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto 4f;" + "r7 = *(u32 *)(r0 + 0);" + "r8 = *(u32 *)(r0 + 0);" + /* This jump can't be predicted and does not change r7 or r8 state. */ + "if r7 > r8 goto 2f;" + /* Branch explored first ties r2 and r7 as having the same id. */ + "r2 = r7;" + "goto 3f;" + "2:" + /* Branch explored second does not tie r2 and r7 but has a function call. */ + "call %[bpf_get_prandom_u32];" + "3:" + /* + * A checkpoint. + * When first branch is explored, this would inject linked registers + * r2 and r7 into the jump history. + * When second branch is explored, this would be a cache hit point, + * triggering propagate_precision(). + */ + "if r7 <= 42 goto +0;" + /* + * Mark r7 as precise using an if condition that is always true. + * When reached via the second branch, this triggered a bug in the backtrack_insn() + * because r2 (tied to r7) was propagated as precise to a call. + */ + "if r7 <= 0xffffFFFF goto +0;" + "goto 1b;" + "4:" + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm(bpf_get_prandom_u32) + : __clobber_common, "r7", "r8" + ); + + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c index 3072fee9a448..58c7704d61cd 100644 --- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -40,6 +40,9 @@ __naked void linked_regs_bpf_k(void) */ "r3 = r10;" "r3 += r0;" + /* Mark r1 and r2 as alive. */ + "r1 = r1;" + "r2 = r2;" "r0 = 0;" "exit;" : @@ -73,6 +76,9 @@ __naked void linked_regs_bpf_x_src(void) */ "r4 = r10;" "r4 += r0;" + /* Mark r1 and r2 as alive. */ + "r1 = r1;" + "r2 = r2;" "r0 = 0;" "exit;" : @@ -106,6 +112,10 @@ __naked void linked_regs_bpf_x_dst(void) */ "r4 = r10;" "r4 += r3;" + /* Mark r1 and r2 as alive. */ + "r0 = r0;" + "r1 = r1;" + "r2 = r2;" "r0 = 0;" "exit;" : @@ -143,6 +153,9 @@ __naked void linked_regs_broken_link(void) */ "r3 = r10;" "r3 += r0;" + /* Mark r1 and r2 as alive. */ + "r1 = r1;" + "r2 = r2;" "r0 = 0;" "exit;" : @@ -156,16 +169,16 @@ __naked void linked_regs_broken_link(void) */ SEC("socket") __success __log_level(2) -__msg("12: (0f) r2 += r1") +__msg("17: (0f) r2 += r1") /* Current state */ -__msg("frame2: last_idx 12 first_idx 11 subseq_idx -1 ") -__msg("frame2: regs=r1 stack= before 11: (bf) r2 = r10") +__msg("frame2: last_idx 17 first_idx 14 subseq_idx -1 ") +__msg("frame2: regs=r1 stack= before 16: (bf) r2 = r10") __msg("frame2: parent state regs=r1 stack=") __msg("frame1: parent state regs= stack=") __msg("frame0: parent state regs= stack=") /* Parent state */ -__msg("frame2: last_idx 10 first_idx 10 subseq_idx 11 ") -__msg("frame2: regs=r1 stack= before 10: (25) if r1 > 0x7 goto pc+0") +__msg("frame2: last_idx 13 first_idx 13 subseq_idx 14 ") +__msg("frame2: regs=r1 stack= before 13: (25) if r1 > 0x7 goto pc+0") __msg("frame2: parent state regs=r1 stack=") /* frame1.r{6,7} are marked because mark_precise_scalar_ids() * looks for all registers with frame2.r1.id in the current state @@ -173,20 +186,20 @@ __msg("frame2: parent state regs=r1 stack=") __msg("frame1: parent state regs=r6,r7 stack=") __msg("frame0: parent state regs=r6 stack=") /* Parent state */ -__msg("frame2: last_idx 8 first_idx 8 subseq_idx 10") -__msg("frame2: regs=r1 stack= before 8: (85) call pc+1") +__msg("frame2: last_idx 9 first_idx 9 subseq_idx 13") +__msg("frame2: regs=r1 stack= before 9: (85) call pc+3") /* frame1.r1 is marked because of backtracking of call instruction */ __msg("frame1: parent state regs=r1,r6,r7 stack=") __msg("frame0: parent state regs=r6 stack=") /* Parent state */ -__msg("frame1: last_idx 7 first_idx 6 subseq_idx 8") -__msg("frame1: regs=r1,r6,r7 stack= before 7: (bf) r7 = r1") -__msg("frame1: regs=r1,r6 stack= before 6: (bf) r6 = r1") +__msg("frame1: last_idx 8 first_idx 7 subseq_idx 9") +__msg("frame1: regs=r1,r6,r7 stack= before 8: (bf) r7 = r1") +__msg("frame1: regs=r1,r6 stack= before 7: (bf) r6 = r1") __msg("frame1: parent state regs=r1 stack=") __msg("frame0: parent state regs=r6 stack=") /* Parent state */ -__msg("frame1: last_idx 4 first_idx 4 subseq_idx 6") -__msg("frame1: regs=r1 stack= before 4: (85) call pc+1") +__msg("frame1: last_idx 4 first_idx 4 subseq_idx 7") +__msg("frame1: regs=r1 stack= before 4: (85) call pc+2") __msg("frame0: parent state regs=r1,r6 stack=") /* Parent state */ __msg("frame0: last_idx 3 first_idx 1 subseq_idx 4") @@ -204,6 +217,7 @@ __naked void precision_many_frames(void) "r1 = r0;" "r6 = r0;" "call precision_many_frames__foo;" + "r6 = r6;" /* mark r6 as live */ "exit;" : : __imm(bpf_ktime_get_ns) @@ -220,6 +234,8 @@ void precision_many_frames__foo(void) "r6 = r1;" "r7 = r1;" "call precision_many_frames__bar;" + "r6 = r6;" /* mark r6 as live */ + "r7 = r7;" /* mark r7 as live */ "exit" ::: __clobber_all); } @@ -229,6 +245,8 @@ void precision_many_frames__bar(void) { asm volatile ( "if r1 > 7 goto +0;" + "r6 = 0;" /* mark r6 as live */ + "r7 = 0;" /* mark r7 as live */ /* force r1 to be precise, this eventually marks: * - bar frame r1 * - foo frame r{1,6,7} @@ -340,6 +358,8 @@ __naked void precision_two_ids(void) "r3 += r7;" /* force r9 to be precise, this also marks r8 */ "r3 += r9;" + "r6 = r6;" /* mark r6 as live */ + "r8 = r8;" /* mark r8 as live */ "exit;" : : __imm(bpf_ktime_get_ns) @@ -353,7 +373,7 @@ __flag(BPF_F_TEST_STATE_FREQ) * collect_linked_regs() can't tie more than 6 registers for a single insn. */ __msg("8: (25) if r0 > 0x7 goto pc+0 ; R0=scalar(id=1") -__msg("9: (bf) r6 = r6 ; R6=scalar(id=2") +__msg("14: (bf) r6 = r6 ; R6=scalar(id=2") /* check that r{0-5} are marked precise after 'if' */ __msg("frame0: regs=r0 stack= before 8: (25) if r0 > 0x7 goto pc+0") __msg("frame0: parent state regs=r0,r1,r2,r3,r4,r5 stack=:") @@ -372,6 +392,12 @@ __naked void linked_regs_too_many_regs(void) "r6 = r0;" /* propagate range for r{0-6} */ "if r0 > 7 goto +0;" + /* keep r{1-5} live */ + "r1 = r1;" + "r2 = r2;" + "r3 = r3;" + "r4 = r4;" + "r5 = r5;" /* make r6 appear in the log */ "r6 = r6;" /* force r0 to be precise, @@ -517,7 +543,7 @@ __naked void check_ids_in_regsafe_2(void) "*(u64*)(r10 - 8) = r1;" /* r9 = pointer to stack */ "r9 = r10;" - "r9 += -8;" + "r9 += -16;" /* r8 = ktime_get_ns() */ "call %[bpf_ktime_get_ns];" "r8 = r0;" @@ -538,6 +564,8 @@ __naked void check_ids_in_regsafe_2(void) "if r7 > 4 goto l2_%=;" /* Access memory at r9[r6] */ "r9 += r6;" + "r9 += r7;" + "r9 += r8;" "r0 = *(u8*)(r9 + 0);" "l2_%=:" "r0 = 0;" diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c index 186a25ab429a..e62c6b78657f 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c @@ -18,6 +18,7 @@ #include <linux/in6.h> #include <linux/un.h> #include <linux/filter.h> +#include <linux/rcupdate_trace.h> #include <net/sock.h> #include <linux/namei.h> #include "bpf_testmod.h" @@ -885,6 +886,32 @@ __bpf_kfunc void bpf_kfunc_call_test_sleepable(void) { } +struct bpf_kfunc_rcu_tasks_trace_data { + struct rcu_head rcu; + int *done; +}; + +static void bpf_kfunc_rcu_tasks_trace_cb(struct rcu_head *rhp) +{ + struct bpf_kfunc_rcu_tasks_trace_data *data; + + data = container_of(rhp, struct bpf_kfunc_rcu_tasks_trace_data, rcu); + WRITE_ONCE(*data->done, 1); + kfree(data); +} + +__bpf_kfunc int bpf_kfunc_call_test_call_rcu_tasks_trace(int *done) +{ + struct bpf_kfunc_rcu_tasks_trace_data *data; + + data = kmalloc(sizeof(*data), GFP_ATOMIC); + if (!data) + return -ENOMEM; + data->done = done; + call_rcu_tasks_trace(&data->rcu, bpf_kfunc_rcu_tasks_trace_cb); + return 0; +} + __bpf_kfunc int bpf_kfunc_init_sock(struct init_sock_args *args) { int proto; @@ -1222,6 +1249,7 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE) BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset) BTF_ID_FLAGS(func, bpf_kfunc_call_test_sleepable, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_call_rcu_tasks_trace) BTF_ID_FLAGS(func, bpf_kfunc_init_sock, KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_kfunc_close_sock, KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_connect, KF_SLEEPABLE) diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h index d5c5454e257e..b393bf771131 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h @@ -118,6 +118,7 @@ void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; void bpf_kfunc_call_test_destructive(void) __ksym; void bpf_kfunc_call_test_sleepable(void) __ksym; +int bpf_kfunc_call_test_call_rcu_tasks_trace(int *done) __ksym; void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p); struct prog_test_member *bpf_kfunc_call_memb_acquire(void); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 02a85dda30e6..0929f4a7bda4 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -1261,14 +1261,8 @@ int get_bpf_max_tramp_links(void) return ret; } -#define MAX_BACKTRACE_SZ 128 -void crash_handler(int signum) +static void dump_crash_log(void) { - void *bt[MAX_BACKTRACE_SZ]; - size_t sz; - - sz = backtrace(bt, ARRAY_SIZE(bt)); - fflush(stdout); stdout = env.stdout_saved; stderr = env.stderr_saved; @@ -1277,12 +1271,32 @@ void crash_handler(int signum) env.test_state->error_cnt++; dump_test_log(env.test, env.test_state, true, false, NULL); } +} + +#define MAX_BACKTRACE_SZ 128 + +void crash_handler(int signum) +{ + void *bt[MAX_BACKTRACE_SZ]; + size_t sz; + + sz = backtrace(bt, ARRAY_SIZE(bt)); + + dump_crash_log(); + if (env.worker_id != -1) fprintf(stderr, "[%d]: ", env.worker_id); fprintf(stderr, "Caught signal #%d!\nStack trace:\n", signum); backtrace_symbols_fd(bt, sz, STDERR_FILENO); } +#ifdef __SANITIZE_ADDRESS__ +void __asan_on_error(void) +{ + dump_crash_log(); +} +#endif + void hexdump(const char *prefix, const void *buf, size_t len) { for (int i = 0; i < len; i++) { @@ -1799,7 +1813,7 @@ static int worker_main_send_subtests(int sock, struct test_state *state) msg.subtest_done.num = i; - strncpy(msg.subtest_done.name, subtest_state->name, MAX_SUBTEST_NAME); + strscpy(msg.subtest_done.name, subtest_state->name, MAX_SUBTEST_NAME); msg.subtest_done.error_cnt = subtest_state->error_cnt; msg.subtest_done.skipped = subtest_state->skipped; @@ -1944,13 +1958,15 @@ int main(int argc, char **argv) .parser = parse_arg, .doc = argp_program_doc, }; + int err, i; + +#ifndef __SANITIZE_ADDRESS__ struct sigaction sigact = { .sa_handler = crash_handler, .sa_flags = SA_RESETHAND, - }; - int err, i; - + }; sigaction(SIGSEGV, &sigact, NULL); +#endif env.stdout_saved = stdout; env.stderr_saved = stderr; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 27db34ecf3f5..a8ae03c57bba 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -1320,7 +1320,7 @@ static bool cmp_str_seq(const char *log, const char *exp) printf("FAIL\nTestcase bug\n"); return false; } - strncpy(needle, exp, len); + memcpy(needle, exp, len); needle[len] = 0; q = strstr(log, needle); if (!q) { diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 16eb37e5bad6..66af0d13751a 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -212,6 +212,7 @@ int parse_test_list_file(const char *path, break; } + free(buf); fclose(f); return err; } diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index eeaab7013ca2..0e63daf83ed5 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -24,12 +24,6 @@ #define TRACEFS_PIPE "/sys/kernel/tracing/trace_pipe" #define DEBUGFS_PIPE "/sys/kernel/debug/tracing/trace_pipe" -struct ksyms { - struct ksym *syms; - size_t sym_cap; - size_t sym_cnt; -}; - static struct ksyms *ksyms; static pthread_mutex_t ksyms_mutex = PTHREAD_MUTEX_INITIALIZER; @@ -54,6 +48,8 @@ void free_kallsyms_local(struct ksyms *ksyms) if (!ksyms) return; + free(ksyms->filtered_syms); + if (!ksyms->syms) { free(ksyms); return; @@ -610,7 +606,7 @@ static int search_kallsyms_compare(const void *p1, const struct ksym *p2) return compare_name(p1, p2->name); } -int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel) +int bpf_get_ksyms(struct ksyms **ksymsp, bool kernel) { size_t cap = 0, cnt = 0; char *name = NULL, *ksym_name, **syms = NULL; @@ -637,8 +633,10 @@ int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel) else f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r"); - if (!f) + if (!f) { + free_kallsyms_local(ksyms); return -EINVAL; + } map = hashmap__new(symbol_hash, symbol_equal, NULL); if (IS_ERR(map)) { @@ -679,15 +677,18 @@ int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel) syms[cnt++] = ksym_name; } - *symsp = syms; - *cntp = cnt; + ksyms->filtered_syms = syms; + ksyms->filtered_cnt = cnt; + *ksymsp = ksyms; error: free(name); fclose(f); hashmap__free(map); - if (err) + if (err) { free(syms); + free_kallsyms_local(ksyms); + } return err; } diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index a5576b2dfc26..d5bf1433675d 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -23,7 +23,14 @@ struct ksym { long addr; char *name; }; -struct ksyms; + +struct ksyms { + struct ksym *syms; + size_t sym_cap; + size_t sym_cnt; + char **filtered_syms; + size_t filtered_cnt; +}; typedef int (*ksym_cmp_t)(const void *p1, const void *p2); typedef int (*ksym_search_cmp_t)(const void *p1, const struct ksym *p2); @@ -53,7 +60,7 @@ ssize_t get_rel_offset(uintptr_t addr); int read_build_id(const char *path, char *build_id, size_t size); -int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel); +int bpf_get_ksyms(struct ksyms **ksymsp, bool kernel); int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel); #endif diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 061d98f6e9bb..a9242103dc47 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -44,9 +44,9 @@ mark_precise: frame0: regs=r2 stack= before 23\ mark_precise: frame0: regs=r2 stack= before 22\ mark_precise: frame0: regs=r2 stack= before 20\ - mark_precise: frame0: parent state regs=r2,r9 stack=:\ + mark_precise: frame0: parent state regs=r2 stack=:\ mark_precise: frame0: last_idx 19 first_idx 10\ - mark_precise: frame0: regs=r2,r9 stack= before 19\ + mark_precise: frame0: regs=r2 stack= before 19\ mark_precise: frame0: regs=r9 stack= before 18\ mark_precise: frame0: regs=r8,r9 stack= before 17\ mark_precise: frame0: regs=r0,r9 stack= before 15\ @@ -107,9 +107,9 @@ mark_precise: frame0: parent state regs=r2 stack=:\ mark_precise: frame0: last_idx 20 first_idx 20\ mark_precise: frame0: regs=r2 stack= before 20\ - mark_precise: frame0: parent state regs=r2,r9 stack=:\ + mark_precise: frame0: parent state regs=r2 stack=:\ mark_precise: frame0: last_idx 19 first_idx 17\ - mark_precise: frame0: regs=r2,r9 stack= before 19\ + mark_precise: frame0: regs=r2 stack= before 19\ mark_precise: frame0: regs=r9 stack= before 18\ mark_precise: frame0: regs=r8,r9 stack= before 17\ mark_precise: frame0: parent state regs= stack=:", diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index 1be1e353d40a..75f85e0362f5 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -3378,6 +3378,8 @@ int main(int argc, char **argv) } } free(env.presets[i].atoms); + if (env.presets[i].value.type == ENUMERATOR) + free(env.presets[i].value.svalue); } free(env.presets); return -err; diff --git a/tools/testing/selftests/bpf/xdp_features.c b/tools/testing/selftests/bpf/xdp_features.c index 595c79141cf3..a27ed663967c 100644 --- a/tools/testing/selftests/bpf/xdp_features.c +++ b/tools/testing/selftests/bpf/xdp_features.c @@ -16,6 +16,7 @@ #include <network_helpers.h> +#include "bpf_util.h" #include "xdp_features.skel.h" #include "xdp_features.h" @@ -212,7 +213,7 @@ static void set_env_default(void) env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT; env.feature.action = -EINVAL; env.ifindex = -ENODEV; - strcpy(env.ifname, "unknown"); + strscpy(env.ifname, "unknown"); make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_CTRL_PORT, &env.dut_ctrl_addr, NULL); make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_ECHO_PORT, diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 3d8de0d4c96a..6db3b5555a22 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -550,7 +550,7 @@ static int rxq_num(const char *ifname) struct ifreq ifr = { .ifr_data = (void *)&ch, }; - strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1); + strscpy(ifr.ifr_name, ifname); int fd, ret; fd = socket(AF_UNIX, SOCK_DGRAM, 0); @@ -571,7 +571,7 @@ static void hwtstamp_ioctl(int op, const char *ifname, struct hwtstamp_config *c struct ifreq ifr = { .ifr_data = (void *)cfg, }; - strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1); + strscpy(ifr.ifr_name, ifname); int fd, ret; fd = socket(AF_UNIX, SOCK_DGRAM, 0); diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 5dff3ad53867..a56f4153c64d 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -196,7 +196,6 @@ test_add_proc() # P<v> = set cpus.partition (0:member, 1:root, 2:isolated) # C<l> = add cpu-list to cpuset.cpus # X<l> = add cpu-list to cpuset.cpus.exclusive -# S<p> = use prefix in subtree_control # T = put a task into cgroup # CX<l> = add cpu-list to both cpuset.cpus and cpuset.cpus.exclusive # O<c>=<v> = Write <v> to CPU online file of <c> @@ -209,44 +208,46 @@ test_add_proc() # sched-debug matching which includes offline CPUs and single-CPU partitions # while the second one is for matching cpuset.cpus.isolated. # -SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1" +SETUP_A123_PARTITIONS="C1-3:P1 C2-3:P1 C3:P1" TEST_MATRIX=( # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- - " C0-1 . . C2-3 S+ C4-5 . . 0 A2:0-1" + " C0-1 . . C2-3 . C4-5 . . 0 A2:0-1" " C0-1 . . C2-3 P1 . . . 0 " - " C0-1 . . C2-3 P1:S+ C0-1:P1 . . 0 " - " C0-1 . . C2-3 P1:S+ C1:P1 . . 0 " - " C0-1:S+ . . C2-3 . . . P1 0 " - " C0-1:P1 . . C2-3 S+ C1 . . 0 " - " C0-1:P1 . . C2-3 S+ C1:P1 . . 0 " - " C0-1:P1 . . C2-3 S+ C1:P1 . P1 0 " + " C0-1 . . C2-3 P1 C0-1:P1 . . 0 " + " C0-1 . . C2-3 P1 C1:P1 . . 0 " + " C0-1 . . C2-3 . . . P1 0 " + " C0-1:P1 . . C2-3 . C1 . . 0 " + " C0-1:P1 . . C2-3 . C1:P1 . . 0 " + " C0-1:P1 . . C2-3 . C1:P1 . P1 0 " " C0-1:P1 . . C2-3 C4-5 . . . 0 A1:4-5" - " C0-1:P1 . . C2-3 S+:C4-5 . . . 0 A1:4-5" " C0-1 . . C2-3:P1 . . . C2 0 " " C0-1 . . C2-3:P1 . . . C4-5 0 B1:4-5" - "C0-3:P1:S+ C2-3:P1 . . . . . . 0 A1:0-1|A2:2-3|XA2:2-3" - "C0-3:P1:S+ C2-3:P1 . . C1-3 . . . 0 A1:1|A2:2-3|XA2:2-3" - "C2-3:P1:S+ C3:P1 . . C3 . . . 0 A1:|A2:3|XA2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P1 . . C3 P0 . . 0 A1:3|A2:3 A1:P1|A2:P0" - "C2-3:P1:S+ C2:P1 . . C2-4 . . . 0 A1:3-4|A2:2" - "C2-3:P1:S+ C3:P1 . . C3 . . C0-2 0 A1:|B1:0-2 A1:P1|A2:P1" + " C0-3:P1 C2-3:P1 . . . . . . 0 A1:0-1|A2:2-3|XA2:2-3" + " C0-3:P1 C2-3:P1 . . C1-3 . . . 0 A1:1|A2:2-3|XA2:2-3" + " C2-3:P1 C3:P1 . . C3 . . . 0 A1:|A2:3|XA2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . C3 P0 . . 0 A1:3|A2:3 A1:P1|A2:P0" + " C2-3:P1 C2:P1 . . C2-4 . . . 0 A1:3-4|A2:2" + " C2-3:P1 C3:P1 . . C3 . . C0-2 0 A1:|B1:0-2 A1:P1|A2:P1" "$SETUP_A123_PARTITIONS . C2-3 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1" # CPU offlining cases: - " C0-1 . . C2-3 S+ C4-5 . O2=0 0 A1:0-1|B1:3" - "C0-3:P1:S+ C2-3:P1 . . O2=0 . . . 0 A1:0-1|A2:3" - "C0-3:P1:S+ C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1|A2:2-3" - "C0-3:P1:S+ C2-3:P1 . . O1=0 . . . 0 A1:0|A2:2-3" - "C0-3:P1:S+ C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1|A2:2-3" - "C2-3:P1:S+ C3:P1 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P2 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" - "C2-3:P1:S+ C3:P1 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P2 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" - "C2-3:P1:S+ C3:P1 . . O2=0 . . . 0 A1:|A2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P1 . . O3=0 . . . 0 A1:2|A2: A1:P1|A2:P1" - "C2-3:P1:S+ C3:P1 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-1" - "C2-3:P1:S+ C3:P1 . . . T:O3=0 . . 0 A1:2|A2:2 A1:P1|A2:P-1" + " C0-1 . . C2-3 . C4-5 . O2=0 0 A1:0-1|B1:3" + " C0-3:P1 C2-3:P1 . . O2=0 . . . 0 A1:0-1|A2:3" + " C0-3:P1 C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1|A2:2-3" + " C0-3:P1 C2-3:P1 . . O1=0 . . . 0 A1:0|A2:2-3" + " C0-3:P1 C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1|A2:2-3" + " C2-3:P1 C3:P1 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P2 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" + " C2-3:P1 C3:P1 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P2 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" + " C2-3:P1 C3:P1 . . O2=0 . . . 0 A1:|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . O3=0 . . . 0 A1:2|A2: A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-1" + " C2-3:P1 C3:P1 . . . T:O3=0 . . 0 A1:2|A2:2 A1:P1|A2:P-1" + " C2-3:P1 C3:P2 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-2" + " C1-3:P1 C3:P2 . . . T:O3=0 . . 0 A1:1-2|A2:1-2 A1:P1|A2:P-2 3|" + " C1-3:P1 C3:P2 . . . T:O3=0 O3=1 . 0 A1:1-2|A2:3 A1:P1|A2:P2 3" "$SETUP_A123_PARTITIONS . O1=0 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1" "$SETUP_A123_PARTITIONS . O2=0 . . . 0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1" "$SETUP_A123_PARTITIONS . O3=0 . . . 0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1" @@ -264,88 +265,87 @@ TEST_MATRIX=( # # Remote partition and cpuset.cpus.exclusive tests # - " C0-3:S+ C1-3:S+ C2-3 . X2-3 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 C2-3 . . . P2 0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2" - " C0-3:S+ C1-3:S+ C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" - " C0-3:S+ C1-3:S+ C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1|A3:2-3 A2:P2|A3:P2 1-3" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5" - " C4:X0-3:S+ X1-3:S+ X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3" - " C4:X0-3:S+ X1-3:S+ X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3" + " C0-3 C1-3 C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C2-3 C2-3 . . . P2 0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2" + " C0-3 C1-3 C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5" + " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" + " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" + " C0-3 C1-3 C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1|A3:2-3 A2:P2|A3:P2 1-3" + " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5" + " C4:X0-3 X1-3 X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3" + " C4:X0-3 X1-3 X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3" # Nested remote/local partition tests - " C0-3:S+ C1-3:S+ C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \ + " C0-3 C1-3 C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \ A1:P0|A2:P1|A3:P2|B1:P1 2-3" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4 \ + " C0-3 C1-3 C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4 \ A1:P0|A2:P1|A3:P2|B1:P1 2-4|2-3" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1|A2:2-3|A3:2-3|B1:4 \ + " C0-3 C1-3 C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1|A2:2-3|A3:2-3|B1:4 \ A1:P0|A2:P1|A3:P0|B1:P1" - " C0-3:S+ C1-3:S+ C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \ + " C0-3 C1-3 C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \ A1:P0|A2:P1|A3:P2|B1:P1 2-4|3" - " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \ + " C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \ A1:P0|A2:P2|A3:P1 2-4|2-3" - " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \ + " C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \ A1:P0|A2:P2|A3:P1 2" - " C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \ + " C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \ . . X5 . . 0 A1:0-4|A2:1-4|A3:2-4 \ A1:P0|A2:P-2|A3:P-1 ." - " C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \ + " C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \ . . . X1 . 0 A1:0-1|A2:2-4|A3:2-4 \ A1:P0|A2:P2|A3:P-1 2-4" # Remote partition offline tests - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3" - " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3" + " C0-3 C1-3 C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|" # An invalidated remote partition cannot self-recover from hotplug - " C0-3:S+ C1-3:S+ C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ." + " C0-3 C1-3 C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ." # cpus.exclusive.effective clearing test - " C0-3:S+ C1-3:S+ C2 . X2-3:X . . . 0 A1:0-3|A2:1-3|A3:2|XA1:" + " C0-3 C1-3 C2 . X2-3:X . . . 0 A1:0-3|A2:1-3|A3:2|XA1:" # Invalid to valid remote partition transition test - " C0-3:S+ C1-3 . . . X3:P2 . . 0 A1:0-3|A2:1-3|XA2: A2:P-2 ." - " C0-3:S+ C1-3:X3:P2 - . . X2-3 P2 . . 0 A1:0-2|A2:3|XA2:3 A2:P2 3" + " C0-3 C1-3 . . . X3:P2 . . 0 A1:0-3|A2:1-3|XA2: A2:P-2 ." + " C0-3 C1-3:X3:P2 . . X2-3 P2 . . 0 A1:0-2|A2:3|XA2:3 A2:P2 3" # Invalid to valid local partition direct transition tests - " C1-3:S+:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3" - " C1-3:S+:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3" - " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:5-6 A1:P2|B1:P0" - " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3" + " C1-3:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3" + " C1-3:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3" + " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:5-6 A1:P2|B1:P0" + " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3" # Local partition invalidation tests - " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ + " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . . . . 0 A1:1|A2:2|A3:3 A1:P2|A2:P2|A3:P2 1-3" - " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ + " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . X4 . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3" - " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ + " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . C4:X . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3" # Local partition CPU change tests - " C0-5:S+:P2 C4-5:S+:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2" - " C0-5:S+:P2 C4-5:S+:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3" + " C0-5:P2 C4-5:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2" + " C0-5:P2 C4-5:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3" # cpus_allowed/exclusive_cpus update tests - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ . X:C4 . P2 . 0 A1:4|A2:4|XA2:|XA3:|A3:4 \ A1:P0|A3:P-2 ." - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ . X1 . P2 . 0 A1:0-3|A2:1-3|XA1:1|XA2:|XA3:|A3:2-3 \ A1:P0|A3:P-2 ." - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ . . X3 P2 . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3 \ A1:P0|A3:P2 3" - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \ . . X3 . . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3|XA3:3 \ A1:P0|A3:P2 3" - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \ . X4 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:4|XA2:|XA3 \ A1:P0|A3:P-2" @@ -356,37 +356,37 @@ TEST_MATRIX=( # # Adding CPUs to partition root that are not in parent's # cpuset.cpus is allowed, but those extra CPUs are ignored. - "C2-3:P1:S+ C3:P1 . . . C2-4 . . 0 A1:|A2:2-3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . . C2-4 . . 0 A1:|A2:2-3 A1:P1|A2:P1" # Taking away all CPUs from parent or itself if there are tasks # will make the partition invalid. - "C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1" - " C3:P1:S+ C3 . . T P1 . . 0 A1:3|A2:3 A1:P1|A2:P-1" + " C2-3:P1 C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1" + " C3:P1 C3 . . T P1 . . 0 A1:3|A2:3 A1:P1|A2:P-1" "$SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1" "$SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1" # Changing a partition root to member makes child partitions invalid - "C2-3:P1:S+ C3:P1 . . P0 . . . 0 A1:2-3|A2:3 A1:P0|A2:P-1" + " C2-3:P1 C3:P1 . . P0 . . . 0 A1:2-3|A2:3 A1:P0|A2:P-1" "$SETUP_A123_PARTITIONS . C2-3 P0 . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P0|A3:P-1" # cpuset.cpus can contains cpus not in parent's cpuset.cpus as long # as they overlap. - "C2-3:P1:S+ . . . . C3-4:P1 . . 0 A1:2|A2:3 A1:P1|A2:P1" + " C2-3:P1 . . . . C3-4:P1 . . 0 A1:2|A2:3 A1:P1|A2:P1" # Deletion of CPUs distributed to child cgroup is allowed. - "C0-1:P1:S+ C1 . C2-3 C4-5 . . . 0 A1:4-5|A2:4-5" + " C0-1:P1 C1 . C2-3 C4-5 . . . 0 A1:4-5|A2:4-5" # To become a valid partition root, cpuset.cpus must overlap parent's # cpuset.cpus. - " C0-1:P1 . . C2-3 S+ C4-5:P1 . . 0 A1:0-1|A2:0-1 A1:P1|A2:P-1" + " C0-1:P1 . . C2-3 . C4-5:P1 . . 0 A1:0-1|A2:0-1 A1:P1|A2:P-1" # Enabling partition with child cpusets is allowed - " C0-1:S+ C1 . C2-3 P1 . . . 0 A1:0-1|A2:1 A1:P1" + " C0-1 C1 . C2-3 P1 . . . 0 A1:0-1|A2:1 A1:P1" # A partition root with non-partition root parent is invalid| but it # can be made valid if its parent becomes a partition root too. - " C0-1:S+ C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2" - " C0-1:S+ C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1" + " C0-1 C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2" + " C0-1 C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1" # A non-exclusive cpuset.cpus change will not invalidate its siblings partition. " C0-1:P1 . . C2-3 C0-2 . . . 0 A1:0-2|B1:3 A1:P1|B1:P0" @@ -398,23 +398,23 @@ TEST_MATRIX=( # Child partition root that try to take all CPUs from parent partition # with tasks will remain invalid. - " C1-4:P1:S+ P1 . . . . . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" - " C1-4:P1:S+ P1 . . . C1-4 . . 0 A1|A2:1-4 A1:P1|A2:P1" - " C1-4:P1:S+ P1 . . T C1-4 . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" + " C1-4:P1 P1 . . . . . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" + " C1-4:P1 P1 . . . C1-4 . . 0 A1|A2:1-4 A1:P1|A2:P1" + " C1-4:P1 P1 . . T C1-4 . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" # Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't # affect cpuset.cpus.exclusive.effective. - " C1-4:X3:S+ C1:X3 . . . C . . 0 A2:1-4|XA2:3" + " C1-4:X3 C1:X3 . . . C . . 0 A2:1-4|XA2:3" # cpuset.cpus can contain CPUs that overlap a sibling cpuset with cpus.exclusive # but creating a local partition out of it is not allowed. Similarly and change # in cpuset.cpus of a local partition that overlaps sibling exclusive CPUs will # invalidate it. - " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1 0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \ + " CX1-4 CX2-4:P2 . C5-6 . . . P1 0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \ A1:P0|A2:P2:B1:P1 2-4" - " CX1-4:S+ CX2-4:P2 . C3-6 . . . P1 0 A1:1|A2:2-4|B1:5-6 \ + " CX1-4 CX2-4:P2 . C3-6 . . . P1 0 A1:1|A2:2-4|B1:5-6 \ A1:P0|A2:P2:B1:P-1 2-4" - " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \ + " CX1-4 CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \ A1:P0|A2:P2:B1:P-1 2-4" # When multiple partitions with conflicting cpuset.cpus are created, the @@ -426,14 +426,14 @@ TEST_MATRIX=( " C1-3:X1-3 . . C4-5 . . . C1-2 0 A1:1-3|B1:1-2" # cpuset.cpus can become empty with task in it as it inherits parent's effective CPUs - " C1-3:S+ C2 . . . T:C . . 0 A1:1-3|A2:1-3" + " C1-3 C2 . . . T:C . . 0 A1:1-3|A2:1-3" # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # Failure cases: # A task cannot be added to a partition with no cpu - "C2-3:P1:S+ C3:P1 . . O2=0:T . . . 1 A1:|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . O2=0:T . . . 1 A1:|A2:3 A1:P1|A2:P1" # Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected " C0-3 . . C4-5 X0-3 . . X3-5 1 A1:0-3|B1:4-5" @@ -465,31 +465,31 @@ REMOTE_TEST_MATRIX=( # old-p1 old-p2 old-c11 old-c12 old-c21 old-c22 # new-p1 new-p2 new-c11 new-c12 new-c21 new-c22 ECPUs Pstate ISOLCPUS # ------ ------ ------- ------- ------- ------- ----- ------ -------- - " X1-3:S+ X4-6:S+ X1-2 X3 X4-5 X6 \ + " X1-3 X4-6 X1-2 X3 X4-5 X6 \ . . P2 P2 P2 P2 c11:1-2|c12:3|c21:4-5|c22:6 \ c11:P2|c12:P2|c21:P2|c22:P2 1-6" - " CX1-4:S+ . X1-2:P2 C3 . . \ + " CX1-4 . X1-2:P2 C3 . . \ . . . C3-4 . . p1:3-4|c11:1-2|c12:3-4 \ p1:P0|c11:P2|c12:P0 1-2" - " CX1-4:S+ . X1-2:P2 . . . \ + " CX1-4 . X1-2:P2 . . . \ X2-4 . . . . . p1:1,3-4|c11:2 \ p1:P0|c11:P2 2" - " CX1-5:S+ . X1-2:P2 X3-5:P1 . . \ + " CX1-5 . X1-2:P2 X3-5:P1 . . \ X2-4 . . . . . p1:1,5|c11:2|c12:3-4 \ p1:P0|c11:P2|c12:P1 2" - " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \ + " CX1-4 . X1-2:P2 X3-4:P1 . . \ . . X2 . . . p1:1|c11:2|c12:3-4 \ p1:P0|c11:P2|c12:P1 2" # p1 as member, will get its effective CPUs from its parent rtest - " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \ + " CX1-4 . X1-2:P2 X3-4:P1 . . \ . . X1 CX2-4 . . p1:5-7|c11:1|c12:2-4 \ p1:P0|c11:P2|c12:P1 1" - " CX1-4:S+ X5-6:P1:S+ . . . . \ - . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \ + " CX1-4 X5-6:P1 . . . . \ + . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \ p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \ 1-2,4-6|1-2,5-6" # c12 whose cpuset.cpus CPUs are all granted to c11 will become invalid partition - " C1-5:P1:S+ . C1-4:P1 C2-3 . . \ + " C1-5:P1 . C1-4:P1 C2-3 . . \ . . . P1 . . p1:5|c11:1-4|c12:5 \ p1:P1|c11:P1|c12:P-1" ) @@ -530,7 +530,6 @@ set_ctrl_state() CGRP=$1 STATE=$2 SHOWERR=${3} - CTRL=${CTRL:=$CONTROLLER} HASERR=0 REDIRECT="2> $TMPMSG" [[ -z "$STATE" || "$STATE" = '.' ]] && return 0 @@ -540,15 +539,16 @@ set_ctrl_state() for CMD in $(echo $STATE | sed -e "s/:/ /g") do TFILE=$CGRP/cgroup.procs - SFILE=$CGRP/cgroup.subtree_control PFILE=$CGRP/cpuset.cpus.partition CFILE=$CGRP/cpuset.cpus XFILE=$CGRP/cpuset.cpus.exclusive - case $CMD in - S*) PREFIX=${CMD#?} - COMM="echo ${PREFIX}${CTRL} > $SFILE" + + # Enable cpuset controller if not enabled yet + [[ -f $CFILE ]] || { + COMM="echo +cpuset > $CGRP/../cgroup.subtree_control" eval $COMM $REDIRECT - ;; + } + case $CMD in X*) CPUS=${CMD#?} COMM="echo $CPUS > $XFILE" @@ -764,7 +764,7 @@ check_cgroup_states() # only CPUs in isolated partitions as well as those that are isolated at # boot time. # -# $1 - expected isolated cpu list(s) <isolcpus1>{,<isolcpus2>} +# $1 - expected isolated cpu list(s) <isolcpus1>{|<isolcpus2>} # <isolcpus1> - expected sched/domains value # <isolcpus2> - cpuset.cpus.isolated value = <isolcpus1> if not defined # @@ -773,6 +773,7 @@ check_isolcpus() EXPECTED_ISOLCPUS=$1 ISCPUS=${CGROUP2}/cpuset.cpus.isolated ISOLCPUS=$(cat $ISCPUS) + HKICPUS=$(cat /sys/devices/system/cpu/isolated) LASTISOLCPU= SCHED_DOMAINS=/sys/kernel/debug/sched/domains if [[ $EXPECTED_ISOLCPUS = . ]] @@ -811,6 +812,11 @@ check_isolcpus() EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN # + # The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS + # + [[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1 + + # # Use the sched domain in debugfs to check isolated CPUs, if available # [[ -d $SCHED_DOMAINS ]] || return 0 @@ -947,7 +953,6 @@ check_test_results() run_state_test() { TEST=$1 - CONTROLLER=cpuset CGROUP_LIST=". A1 A1/A2 A1/A2/A3 B1" RESET_LIST="A1/A2/A3 A1/A2 A1 B1" I=0 @@ -1003,7 +1008,6 @@ run_state_test() run_remote_state_test() { TEST=$1 - CONTROLLER=cpuset [[ -d rtest ]] || mkdir rtest cd rtest echo +cpuset > cgroup.subtree_control diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py index 45c2d49d55b6..ee863e90d1e0 100755 --- a/tools/testing/selftests/drivers/net/hw/devmem.py +++ b/tools/testing/selftests/drivers/net/hw/devmem.py @@ -63,12 +63,29 @@ def check_tx_chunks(cfg) -> None: ksft_eq(socat.stdout.strip(), "hello\nworld") +def check_rx_hds(cfg) -> None: + """Test HDS splitting across payload sizes.""" + require_devmem(cfg) + + for size in [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8192]: + port = rand_port() + listen_cmd = f"{cfg.bin_local} -L -l -f {cfg.ifname} -s {cfg.addr} -p {port}" + + with bkg(listen_cmd, exit_wait=True) as ncdevmem: + wait_port_listen(port) + cmd(f"dd if=/dev/zero bs={size} count=1 2>/dev/null | " + + f"socat -b {size} -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},nodelay", + host=cfg.remote, shell=True) + + ksft_eq(ncdevmem.ret, 0, f"HDS failed for payload size {size}") + + def main() -> None: with NetDrvEpEnv(__file__) as cfg: cfg.bin_local = path.abspath(path.dirname(__file__) + "/ncdevmem") cfg.bin_remote = cfg.remote.deploy(cfg.bin_local) - ksft_run([check_rx, check_tx, check_tx_chunks], + ksft_run([check_rx, check_tx, check_tx_chunks, check_rx_hds], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index 16864c844108..e098d6534c3c 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -98,6 +98,7 @@ static unsigned int ifindex; static unsigned int dmabuf_id; static uint32_t tx_dmabuf_id; static int waittime_ms = 500; +static bool fail_on_linear; /* System state loaded by current_config_load() */ #define MAX_FLOWS 8 @@ -975,6 +976,11 @@ static int do_server(struct memory_buffer *mem) "SCM_DEVMEM_LINEAR. dmabuf_cmsg->frag_size=%u\n", dmabuf_cmsg->frag_size); + if (fail_on_linear) { + pr_err("received SCM_DEVMEM_LINEAR but --fail-on-linear (-L) set"); + goto err_close_client; + } + continue; } @@ -1398,8 +1404,11 @@ int main(int argc, char *argv[]) int is_server = 0, opt; int ret, err = 1; - while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:z:")) != -1) { + while ((opt = getopt(argc, argv, "Lls:c:p:v:q:t:f:z:")) != -1) { switch (opt) { + case 'L': + fail_on_linear = true; + break; case 'l': is_server = 1; break; diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index ed7e405682f0..b9b7527c2c6b 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -4,13 +4,15 @@ import datetime import random import re +import time from lib.py import ksft_run, ksft_pr, ksft_exit from lib.py import ksft_eq, ksft_ne, ksft_ge, ksft_in, ksft_lt, ksft_true, ksft_raises from lib.py import NetDrvEpEnv from lib.py import EthtoolFamily, NetdevFamily from lib.py import KsftSkipEx, KsftFailEx +from lib.py import ksft_disruptive from lib.py import rand_port -from lib.py import ethtool, ip, defer, GenerateTraffic, CmdExitFailure +from lib.py import cmd, ethtool, ip, defer, GenerateTraffic, CmdExitFailure, wait_file def _rss_key_str(key): @@ -809,6 +811,98 @@ def test_rss_default_context_rule(cfg): 'noise' : (0, 1) }) +@ksft_disruptive +def test_rss_context_persist_ifupdown(cfg, pre_down=False): + """ + Test that RSS contexts and their associated ntuple filters persist across + an interface down/up cycle. + + """ + + require_ntuple(cfg) + + qcnt = len(_get_rx_cnts(cfg)) + if qcnt < 6: + try: + ethtool(f"-L {cfg.ifname} combined 6") + defer(ethtool, f"-L {cfg.ifname} combined {qcnt}") + except Exception as exc: + raise KsftSkipEx("Not enough queues for the test") from exc + + ethtool(f"-X {cfg.ifname} equal 2") + defer(ethtool, f"-X {cfg.ifname} default") + + ifup = defer(ip, f"link set dev {cfg.ifname} up") + if pre_down: + ip(f"link set dev {cfg.ifname} down") + + try: + ctx1_id = ethtool_create(cfg, "-X", "context new start 2 equal 2") + defer(ethtool, f"-X {cfg.ifname} context {ctx1_id} delete") + except CmdExitFailure as exc: + raise KsftSkipEx("Create context not supported with interface down") from exc + + ctx2_id = ethtool_create(cfg, "-X", "context new start 4 equal 2") + defer(ethtool, f"-X {cfg.ifname} context {ctx2_id} delete") + + port_ctx2 = rand_port() + flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port_ctx2} context {ctx2_id}" + ntuple_id = ethtool_create(cfg, "-N", flow) + defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}") + + if not pre_down: + ip(f"link set dev {cfg.ifname} down") + ifup.exec() + + wait_file(f"/sys/class/net/{cfg.ifname}/carrier", + lambda x: x.strip() == "1", deadline=20) + + remote_addr = cfg.remote_addr_v[cfg.addr_ipver] + for _ in range(10): + if cmd(f"ping -c 1 -W 1 {remote_addr}", fail=False).ret == 0: + break + time.sleep(1) + else: + raise KsftSkipEx("Cannot reach remote host after interface up") + + ctxs = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}, dump=True) + + data1 = [c for c in ctxs if c.get('context') == ctx1_id] + ksft_eq(len(data1), 1, f"Context {ctx1_id} should persist after ifup") + + data2 = [c for c in ctxs if c.get('context') == ctx2_id] + ksft_eq(len(data2), 1, f"Context {ctx2_id} should persist after ifup") + + _ntuple_rule_check(cfg, ntuple_id, ctx2_id) + + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + + main_traffic = sum(cnts[0:2]) + ksft_ge(main_traffic, 18000, f"Main context traffic distribution: {cnts}") + ksft_lt(sum(cnts[2:6]), 500, f"Other context queues should be mostly empty: {cnts}") + + _send_traffic_check(cfg, port_ctx2, f"context {ctx2_id}", + {'target': (4, 5), + 'noise': (0, 1), + 'empty': (2, 3)}) + + +def test_rss_context_persist_create_and_ifdown(cfg): + """ + Create RSS contexts then cycle the interface down and up. + """ + test_rss_context_persist_ifupdown(cfg, pre_down=False) + + +def test_rss_context_persist_ifdown_and_create(cfg): + """ + Bring interface down first, then create RSS contexts and bring up. + """ + test_rss_context_persist_ifupdown(cfg, pre_down=True) + + def main() -> None: with NetDrvEpEnv(__file__, nsim_test=False) as cfg: cfg.context_cnt = None @@ -823,7 +917,9 @@ def main() -> None: test_rss_context_out_of_order, test_rss_context4_create_with_cfg, test_flow_add_context_missing, test_delete_rss_context_busy, test_rss_ntuple_addition, - test_rss_default_context_rule], + test_rss_default_context_rule, + test_rss_context_persist_create_and_ifdown, + test_rss_context_persist_ifdown_and_create], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.py b/tools/testing/selftests/drivers/net/hw/toeplitz.py index d288c57894f6..cd7e080e6f84 100755 --- a/tools/testing/selftests/drivers/net/hw/toeplitz.py +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.py @@ -19,6 +19,8 @@ from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx, KsftFailEx # "define" for the ID of the Toeplitz hash function ETH_RSS_HASH_TOP = 1 +# Must match RPS_MAX_CPUS in toeplitz.c +RPS_MAX_CPUS = 16 def _check_rps_and_rfs_not_configured(cfg): @@ -67,23 +69,24 @@ def _get_irq_cpus(cfg): return cpus -def _get_unused_cpus(cfg, count=2): +def _get_unused_rps_cpus(cfg, count=2): """ - Get CPUs that are not used by Rx queues. - Returns a list of at least 'count' CPU numbers. + Get CPUs that are not used by Rx queues for RPS. + Returns a list of at least 'count' CPU numbers within + the RPS_MAX_CPUS supported range. """ # Get CPUs used by Rx queues rx_cpus = set(_get_irq_cpus(cfg)) - # Get total number of CPUs - num_cpus = os.cpu_count() + # Get total number of CPUs, capped by RPS_MAX_CPUS + num_cpus = min(os.cpu_count(), RPS_MAX_CPUS) # Find unused CPUs unused_cpus = [cpu for cpu in range(num_cpus) if cpu not in rx_cpus] if len(unused_cpus) < count: - raise KsftSkipEx(f"Need at {count} CPUs not used by Rx queues, found {len(unused_cpus)}") + raise KsftSkipEx(f"Need at least {count} CPUs in range 0..{num_cpus - 1} not used by Rx queues, found {len(unused_cpus)}") return unused_cpus[:count] @@ -181,7 +184,7 @@ def test(cfg, proto_flag, ipver, grp): ksft_pr(f"RSS using CPUs: {irq_cpus}") elif grp == "rps": # Get CPUs not used by Rx queues and configure them for RPS - rps_cpus = _get_unused_cpus(cfg, count=2) + rps_cpus = _get_unused_rps_cpus(cfg, count=2) rps_mask = _configure_rps(cfg, rps_cpus) defer(_configure_rps, cfg, []) rx_cmd += ["-r", rps_mask] diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh index b6093bcf2b06..02dcdeb723be 100644 --- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -249,8 +249,8 @@ function listen_port_and_save_to() { SOCAT_MODE="UDP6-LISTEN" fi - # Just wait for 2 seconds - timeout 2 ip netns exec "${NAMESPACE}" \ + # Just wait for 3 seconds + timeout 3 ip netns exec "${NAMESPACE}" \ socat "${SOCAT_MODE}":"${PORT}",fork "${OUTPUT}" 2> /dev/null } diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh index 0441a18f098b..aac8ef490feb 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh @@ -317,7 +317,7 @@ police_limits_test() tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ flower skip_sw \ - action police rate 0.5kbit burst 1m conform-exceed drop/ok + action police rate 0.5kbit burst 2k conform-exceed drop/ok check_fail $? "Incorrect success to add police action with too low rate" tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ @@ -327,7 +327,7 @@ police_limits_test() tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ flower skip_sw \ - action police rate 1.5kbit burst 1m conform-exceed drop/ok + action police rate 1.5kbit burst 2k conform-exceed drop/ok check_err $? "Failed to add police action with low rate" tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile index 1340b3df9c31..45a3e7ad3dcb 100644 --- a/tools/testing/selftests/drivers/net/team/Makefile +++ b/tools/testing/selftests/drivers/net/team/Makefile @@ -5,6 +5,7 @@ TEST_PROGS := \ dev_addr_lists.sh \ options.sh \ propagation.sh \ + refleak.sh \ # end of TEST_PROGS TEST_INCLUDES := \ diff --git a/tools/testing/selftests/drivers/net/team/refleak.sh b/tools/testing/selftests/drivers/net/team/refleak.sh new file mode 100755 index 000000000000..ef08213ab964 --- /dev/null +++ b/tools/testing/selftests/drivers/net/team/refleak.sh @@ -0,0 +1,17 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# shellcheck disable=SC2154 + +lib_dir=$(dirname "$0") +source "$lib_dir"/../../../net/lib.sh + +trap cleanup_all_ns EXIT + +# Test that there is no reference count leak and that dummy1 can be deleted. +# https://lore.kernel.org/netdev/4d69abe1-ca8d-4f0b-bcf8-13899b211e57@I-love.SAKURA.ne.jp/ +setup_ns ns1 ns2 +ip -n "$ns1" link add name team1 type team +ip -n "$ns1" link add name dummy1 mtu 1499 type dummy +ip -n "$ns1" link set dev dummy1 master team1 +ip -n "$ns1" link set dev dummy1 netns "$ns2" +ip -n "$ns2" link del dev dummy1 diff --git a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c index 61e55dfbf121..e19ff8168baf 100644 --- a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c +++ b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c @@ -37,17 +37,20 @@ FIXTURE(iterate_mount_namespaces) { __u64 mnt_ns_id[MNT_NS_COUNT]; }; +static inline bool mntns_in_list(__u64 *mnt_ns_id, struct mnt_ns_info *info) +{ + for (int i = 0; i < MNT_NS_COUNT; i++) { + if (mnt_ns_id[i] == info->mnt_ns_id) + return true; + } + return false; +} + FIXTURE_SETUP(iterate_mount_namespaces) { for (int i = 0; i < MNT_NS_COUNT; i++) self->fd_mnt_ns[i] = -EBADF; - /* - * Creating a new user namespace let's us guarantee that we only see - * mount namespaces that we did actually create. - */ - ASSERT_EQ(unshare(CLONE_NEWUSER), 0); - for (int i = 0; i < MNT_NS_COUNT; i++) { struct mnt_ns_info info = {}; @@ -75,13 +78,15 @@ TEST_F(iterate_mount_namespaces, iterate_all_forward) fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[0], F_DUPFD_CLOEXEC); ASSERT_GE(fd_mnt_ns_cur, 0); - for (;; count++) { + for (;;) { struct mnt_ns_info info = {}; int fd_mnt_ns_next; fd_mnt_ns_next = ioctl(fd_mnt_ns_cur, NS_MNT_GET_NEXT, &info); if (fd_mnt_ns_next < 0 && errno == ENOENT) break; + if (mntns_in_list(self->mnt_ns_id, &info)) + count++; ASSERT_GE(fd_mnt_ns_next, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_next; @@ -96,13 +101,15 @@ TEST_F(iterate_mount_namespaces, iterate_all_backwards) fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[MNT_NS_LAST_INDEX], F_DUPFD_CLOEXEC); ASSERT_GE(fd_mnt_ns_cur, 0); - for (;; count++) { + for (;;) { struct mnt_ns_info info = {}; int fd_mnt_ns_prev; fd_mnt_ns_prev = ioctl(fd_mnt_ns_cur, NS_MNT_GET_PREV, &info); if (fd_mnt_ns_prev < 0 && errno == ENOENT) break; + if (mntns_in_list(self->mnt_ns_id, &info)) + count++; ASSERT_GE(fd_mnt_ns_prev, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_prev; @@ -125,7 +132,6 @@ TEST_F(iterate_mount_namespaces, iterate_forward) ASSERT_GE(fd_mnt_ns_next, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_next; - ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]); } } @@ -144,7 +150,6 @@ TEST_F(iterate_mount_namespaces, iterate_backward) ASSERT_GE(fd_mnt_ns_prev, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_prev; - ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]); } } diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 16a119a4656c..4afaef01c22e 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -76,6 +76,9 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) memset(s, c, n); } +#define KSELFTEST_PRIO_TEST_F 20000 +#define KSELFTEST_PRIO_XFAIL 20001 + #define TEST_TIMEOUT_DEFAULT 30 /* Utilities exposed to the test definitions */ @@ -465,7 +468,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) fixture_name##_teardown(_metadata, self, variant); \ } \ static struct __test_metadata *_##fixture_name##_##test_name##_object; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST_F))) \ _register_##fixture_name##_##test_name(void) \ { \ struct __test_metadata *object = mmap(NULL, sizeof(*object), \ @@ -880,7 +883,7 @@ struct __test_xfail { .fixture = &_##fixture_name##_fixture_object, \ .variant = &_##fixture_name##_##variant_name##_object, \ }; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_XFAIL))) \ _register_##fixture_name##_##variant_name##_##test_name##_xfail(void) \ { \ _##fixture_name##_##variant_name##_##test_name##_xfail.test = \ diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index fdec90e85467..dc68371f76a3 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -71,6 +71,7 @@ TEST_GEN_PROGS_x86 += x86/cpuid_test TEST_GEN_PROGS_x86 += x86/cr4_cpuid_sync_test TEST_GEN_PROGS_x86 += x86/dirty_log_page_splitting_test TEST_GEN_PROGS_x86 += x86/feature_msrs_test +TEST_GEN_PROGS_x86 += x86/evmcs_smm_controls_test TEST_GEN_PROGS_x86 += x86/exit_on_emulation_failure_test TEST_GEN_PROGS_x86 += x86/fastops_test TEST_GEN_PROGS_x86 += x86/fix_hypercall_test diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 618c937f3c90..cc329b57ce2e 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -80,7 +80,7 @@ static void test_mbind(int fd, size_t total_size) { const unsigned long nodemask_0 = 1; /* nid: 0 */ unsigned long nodemask = 0; - unsigned long maxnode = 8; + unsigned long maxnode = BITS_PER_TYPE(nodemask); int policy; char *mem; int ret; diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index 4ebae4269e68..469a22122157 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -557,6 +557,11 @@ static inline uint64_t get_cr0(void) return cr0; } +static inline void set_cr0(uint64_t val) +{ + __asm__ __volatile__("mov %0, %%cr0" : : "r" (val) : "memory"); +} + static inline uint64_t get_cr3(void) { uint64_t cr3; @@ -566,6 +571,11 @@ static inline uint64_t get_cr3(void) return cr3; } +static inline void set_cr3(uint64_t val) +{ + __asm__ __volatile__("mov %0, %%cr3" : : "r" (val) : "memory"); +} + static inline uint64_t get_cr4(void) { uint64_t cr4; @@ -580,6 +590,19 @@ static inline void set_cr4(uint64_t val) __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } +static inline uint64_t get_cr8(void) +{ + uint64_t cr8; + + __asm__ __volatile__("mov %%cr8, %[cr8]" : [cr8]"=r"(cr8)); + return cr8; +} + +static inline void set_cr8(uint64_t val) +{ + __asm__ __volatile__("mov %0, %%cr8" : : "r" (val) : "memory"); +} + static inline void set_idt(const struct desc_ptr *idt_desc) { __asm__ __volatile__("lidt %0"::"m"(*idt_desc)); diff --git a/tools/testing/selftests/kvm/include/x86/smm.h b/tools/testing/selftests/kvm/include/x86/smm.h new file mode 100644 index 000000000000..19337c34f13e --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86/smm.h @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef SELFTEST_KVM_SMM_H +#define SELFTEST_KVM_SMM_H + +#include "kvm_util.h" + +#define SMRAM_SIZE 65536 +#define SMRAM_MEMSLOT ((1 << 16) | 1) +#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) + +void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, + uint64_t smram_gpa, + const void *smi_handler, size_t handler_size); + +void inject_smi(struct kvm_vcpu *vcpu); + +#endif /* SELFTEST_KVM_SMM_H */ diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c index fab18e9be66c..23a44941e283 100644 --- a/tools/testing/selftests/kvm/lib/x86/processor.c +++ b/tools/testing/selftests/kvm/lib/x86/processor.c @@ -8,6 +8,7 @@ #include "kvm_util.h" #include "pmu.h" #include "processor.h" +#include "smm.h" #include "svm_util.h" #include "sev.h" #include "vmx.h" @@ -1444,3 +1445,28 @@ bool kvm_arch_has_default_irqchip(void) { return true; } + +void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, + uint64_t smram_gpa, + const void *smi_handler, size_t handler_size) +{ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, smram_gpa, + SMRAM_MEMSLOT, SMRAM_PAGES, 0); + TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, smram_gpa, + SMRAM_MEMSLOT) == smram_gpa, + "Could not allocate guest physical addresses for SMRAM"); + + memset(addr_gpa2hva(vm, smram_gpa), 0x0, SMRAM_SIZE); + memcpy(addr_gpa2hva(vm, smram_gpa) + 0x8000, smi_handler, handler_size); + vcpu_set_msr(vcpu, MSR_IA32_SMBASE, smram_gpa); +} + +void inject_smi(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_events events; + + vcpu_events_get(vcpu, &events); + events.smi.pending = 1; + events.flags |= KVM_VCPUEVENT_VALID_SMM; + vcpu_events_set(vcpu, &events); +} diff --git a/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c new file mode 100644 index 000000000000..af7c90103396 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2026, Red Hat, Inc. + * + * Test that vmx_leave_smm() validates vmcs12 controls before re-entering + * nested guest mode on RSM. + */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "smm.h" +#include "hyperv.h" +#include "vmx.h" + +#define SMRAM_GPA 0x1000000 +#define SMRAM_STAGE 0xfe + +#define SYNC_PORT 0xe + +#define STR(x) #x +#define XSTR(s) STR(s) + +/* + * SMI handler: runs in real-address mode. + * Reports SMRAM_STAGE via port IO, then does RSM. + */ +static uint8_t smi_handler[] = { + 0xb0, SMRAM_STAGE, /* mov $SMRAM_STAGE, %al */ + 0xe4, SYNC_PORT, /* in $SYNC_PORT, %al */ + 0x0f, 0xaa, /* rsm */ +}; + +static inline void sync_with_host(uint64_t phase) +{ + asm volatile("in $" XSTR(SYNC_PORT) ", %%al \n" + : "+a" (phase)); +} + +static void l2_guest_code(void) +{ + sync_with_host(1); + + /* After SMI+RSM with invalid controls, we should not reach here. */ + vmcall(); +} + +static void guest_code(struct vmx_pages *vmx_pages, + struct hyperv_test_pages *hv_pages) +{ +#define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + /* Set up Hyper-V enlightenments and eVMCS */ + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); + enable_vp_assist(hv_pages->vp_assist_gpa, hv_pages->vp_assist); + evmcs_enable(); + + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_evmcs(hv_pages)); + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_ASSERT(!vmlaunch()); + + /* L2 exits via vmcall if test fails */ + sync_with_host(2); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t vmx_pages_gva = 0, hv_pages_gva = 0; + struct hyperv_test_pages *hv; + struct hv_enlightened_vmcs *evmcs; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct kvm_regs regs; + int stage_reported; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_SMM)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + setup_smram(vm, vcpu, SMRAM_GPA, smi_handler, sizeof(smi_handler)); + + vcpu_set_hv_cpuid(vcpu); + vcpu_enable_evmcs(vcpu); + vcpu_alloc_vmx(vm, &vmx_pages_gva); + hv = vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva); + vcpu_args_set(vcpu, 2, vmx_pages_gva, hv_pages_gva); + + vcpu_run(vcpu); + + /* L2 is running and syncs with host. */ + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + vcpu_regs_get(vcpu, ®s); + stage_reported = regs.rax & 0xff; + TEST_ASSERT(stage_reported == 1, + "Expected stage 1, got %d", stage_reported); + + /* Inject SMI while L2 is running. */ + inject_smi(vcpu); + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + vcpu_regs_get(vcpu, ®s); + stage_reported = regs.rax & 0xff; + TEST_ASSERT(stage_reported == SMRAM_STAGE, + "Expected SMM handler stage %#x, got %#x", + SMRAM_STAGE, stage_reported); + + /* + * Guest is now paused in the SMI handler, about to execute RSM. + * Hack the eVMCS page to set-up invalid pin-based execution + * control (PIN_BASED_VIRTUAL_NMIS without PIN_BASED_NMI_EXITING). + */ + evmcs = hv->enlightened_vmcs_hva; + evmcs->pin_based_vm_exec_control |= PIN_BASED_VIRTUAL_NMIS; + evmcs->hv_clean_fields = 0; + + /* + * Trigger copy_enlightened_to_vmcs12() via KVM_GET_NESTED_STATE, + * copying the invalid pin_based_vm_exec_control into cached_vmcs12. + */ + union { + struct kvm_nested_state state; + char state_[16384]; + } nested_state_buf; + + memset(&nested_state_buf, 0, sizeof(nested_state_buf)); + nested_state_buf.state.size = sizeof(nested_state_buf); + vcpu_nested_state_get(vcpu, &nested_state_buf.state); + + /* + * Resume the guest. The SMI handler executes RSM, which calls + * vmx_leave_smm(). nested_vmx_check_controls() should detect + * VIRTUAL_NMIS without NMI_EXITING and cause a triple fault. + */ + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c index 86ad1c7d068f..8bd37a476f15 100644 --- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c @@ -13,6 +13,30 @@ #include "linux/psp-sev.h" #include "sev.h" +static void guest_sev_test_msr(uint32_t msr) +{ + uint64_t val = rdmsr(msr); + + wrmsr(msr, val); + GUEST_ASSERT(val == rdmsr(msr)); +} + +#define guest_sev_test_reg(reg) \ +do { \ + uint64_t val = get_##reg(); \ + \ + set_##reg(val); \ + GUEST_ASSERT(val == get_##reg()); \ +} while (0) + +static void guest_sev_test_regs(void) +{ + guest_sev_test_msr(MSR_EFER); + guest_sev_test_reg(cr0); + guest_sev_test_reg(cr3); + guest_sev_test_reg(cr4); + guest_sev_test_reg(cr8); +} #define XFEATURE_MASK_X87_AVX (XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM) @@ -24,6 +48,8 @@ static void guest_snp_code(void) GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_ES_ENABLED); GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_SNP_ENABLED); + guest_sev_test_regs(); + wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ); vmgexit(); } @@ -34,6 +60,8 @@ static void guest_sev_es_code(void) GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED); GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ES_ENABLED); + guest_sev_test_regs(); + /* * TODO: Add GHCB and ucall support for SEV-ES guests. For now, simply * force "termination" to signal "done" via the GHCB MSR protocol. @@ -47,6 +75,8 @@ static void guest_sev_code(void) GUEST_ASSERT(this_cpu_has(X86_FEATURE_SEV)); GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED); + guest_sev_test_regs(); + GUEST_DONE(); } diff --git a/tools/testing/selftests/kvm/x86/smm_test.c b/tools/testing/selftests/kvm/x86/smm_test.c index 55c88d664a94..ade8412bf94a 100644 --- a/tools/testing/selftests/kvm/x86/smm_test.c +++ b/tools/testing/selftests/kvm/x86/smm_test.c @@ -14,13 +14,11 @@ #include "test_util.h" #include "kvm_util.h" +#include "smm.h" #include "vmx.h" #include "svm_util.h" -#define SMRAM_SIZE 65536 -#define SMRAM_MEMSLOT ((1 << 16) | 1) -#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) #define SMRAM_GPA 0x1000000 #define SMRAM_STAGE 0xfe @@ -113,18 +111,6 @@ static void guest_code(void *arg) sync_with_host(DONE); } -void inject_smi(struct kvm_vcpu *vcpu) -{ - struct kvm_vcpu_events events; - - vcpu_events_get(vcpu, &events); - - events.smi.pending = 1; - events.flags |= KVM_VCPUEVENT_VALID_SMM; - - vcpu_events_set(vcpu, &events); -} - int main(int argc, char *argv[]) { vm_vaddr_t nested_gva = 0; @@ -140,16 +126,7 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA, - SMRAM_MEMSLOT, SMRAM_PAGES, 0); - TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT) - == SMRAM_GPA, "could not allocate guest physical addresses?"); - - memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE); - memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler, - sizeof(smi_handler)); - - vcpu_set_msr(vcpu, MSR_IA32_SMBASE, SMRAM_GPA); + setup_smram(vm, vcpu, SMRAM_GPA, smi_handler, sizeof(smi_handler)); if (kvm_has_cap(KVM_CAP_NESTED_STATE)) { if (kvm_cpu_has(X86_FEATURE_SVM)) diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 5b993924cc3f..2ca07ea7202a 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -18,6 +18,9 @@ #include <sys/stat.h> #include <sys/syscall.h> #include <sys/wait.h> +#include <sys/types.h> +#include <sys/ipc.h> +#include <sys/sem.h> #include <unistd.h> #include <ctype.h> @@ -39,6 +42,20 @@ F_SEAL_EXEC) #define MFD_NOEXEC_SEAL 0x0008U +union semun { + int val; + struct semid_ds *buf; + unsigned short int *array; + struct seminfo *__buf; +}; + +/* + * we use semaphores on nested wait tasks due the use of CLONE_NEWPID: the + * child will be PID 1 and can't send SIGSTOP to themselves due special + * treatment of the init task, so the SIGSTOP/SIGCONT synchronization + * approach can't be used here. + */ +#define SEM_KEY 0xdeadbeef /* * Default is not to test hugetlbfs @@ -1333,8 +1350,22 @@ static int sysctl_nested(void *arg) static int sysctl_nested_wait(void *arg) { - /* Wait for a SIGCONT. */ - kill(getpid(), SIGSTOP); + int sem = semget(SEM_KEY, 1, 0600); + struct sembuf sembuf; + + if (sem < 0) { + perror("semget:"); + abort(); + } + sembuf.sem_num = 0; + sembuf.sem_flg = 0; + sembuf.sem_op = 0; + + if (semop(sem, &sembuf, 1) < 0) { + perror("semop:"); + abort(); + } + return sysctl_nested(arg); } @@ -1355,7 +1386,9 @@ static void test_sysctl_sysctl2_failset(void) static int sysctl_nested_child(void *arg) { - int pid; + int pid, sem; + union semun semun; + struct sembuf sembuf; printf("%s nested sysctl 0\n", memfd_str); sysctl_assert_write("0"); @@ -1389,23 +1422,53 @@ static int sysctl_nested_child(void *arg) test_sysctl_sysctl2_failset); join_thread(pid); + sem = semget(SEM_KEY, 1, IPC_CREAT | 0600); + if (sem < 0) { + perror("semget:"); + return 1; + } + semun.val = 1; + sembuf.sem_op = -1; + sembuf.sem_flg = 0; + sembuf.sem_num = 0; + /* Verify that the rules are actually inherited after fork. */ printf("%s nested sysctl 0 -> 1 after fork\n", memfd_str); sysctl_assert_write("0"); + if (semctl(sem, 0, SETVAL, semun) < 0) { + perror("semctl:"); + return 1; + } + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, test_sysctl_sysctl1_failset); sysctl_assert_write("1"); - kill(pid, SIGCONT); + + /* Allow child to continue */ + if (semop(sem, &sembuf, 1) < 0) { + perror("semop:"); + return 1; + } join_thread(pid); printf("%s nested sysctl 0 -> 2 after fork\n", memfd_str); sysctl_assert_write("0"); + if (semctl(sem, 0, SETVAL, semun) < 0) { + perror("semctl:"); + return 1; + } + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, test_sysctl_sysctl2_failset); sysctl_assert_write("2"); - kill(pid, SIGCONT); + + /* Allow child to continue */ + if (semop(sem, &sembuf, 1) < 0) { + perror("semop:"); + return 1; + } join_thread(pid); /* @@ -1415,28 +1478,62 @@ static int sysctl_nested_child(void *arg) */ printf("%s nested sysctl 2 -> 1 after fork\n", memfd_str); sysctl_assert_write("2"); + + if (semctl(sem, 0, SETVAL, semun) < 0) { + perror("semctl:"); + return 1; + } + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, test_sysctl_sysctl2); sysctl_assert_write("1"); - kill(pid, SIGCONT); + + /* Allow child to continue */ + if (semop(sem, &sembuf, 1) < 0) { + perror("semop:"); + return 1; + } join_thread(pid); printf("%s nested sysctl 2 -> 0 after fork\n", memfd_str); sysctl_assert_write("2"); + + if (semctl(sem, 0, SETVAL, semun) < 0) { + perror("semctl:"); + return 1; + } + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, test_sysctl_sysctl2); sysctl_assert_write("0"); - kill(pid, SIGCONT); + + /* Allow child to continue */ + if (semop(sem, &sembuf, 1) < 0) { + perror("semop:"); + return 1; + } join_thread(pid); printf("%s nested sysctl 1 -> 0 after fork\n", memfd_str); sysctl_assert_write("1"); + + if (semctl(sem, 0, SETVAL, semun) < 0) { + perror("semctl:"); + return 1; + } + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, test_sysctl_sysctl1); sysctl_assert_write("0"); - kill(pid, SIGCONT); + /* Allow child to continue */ + if (semop(sem, &sembuf, 1) < 0) { + perror("semop:"); + return 1; + } join_thread(pid); + semctl(sem, 0, IPC_RMID); + return 0; } diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index c2a8586e51a1..83ad9454dd9d 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -12,6 +12,7 @@ map_hugetlb map_populate thuge-gen compaction_test +memory-failure migration mlock2-tests mrelease_test diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 905f1e034963..7a5de4e9bf52 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -72,9 +72,10 @@ TEST_GEN_FILES += madv_populate TEST_GEN_FILES += map_fixed_noreplace TEST_GEN_FILES += map_hugetlb TEST_GEN_FILES += map_populate -ifneq (,$(filter $(ARCH),arm64 riscv riscv64 x86 x86_64)) +ifneq (,$(filter $(ARCH),arm64 riscv riscv64 x86 x86_64 loongarch32 loongarch64)) TEST_GEN_FILES += memfd_secret endif +TEST_GEN_FILES += memory-failure TEST_GEN_FILES += migration TEST_GEN_FILES += mkdirty TEST_GEN_FILES += mlock-random-test @@ -154,6 +155,7 @@ TEST_PROGS += ksft_ksm_numa.sh TEST_PROGS += ksft_madv_guard.sh TEST_PROGS += ksft_madv_populate.sh TEST_PROGS += ksft_memfd_secret.sh +TEST_PROGS += ksft_memory_failure.sh TEST_PROGS += ksft_migration.sh TEST_PROGS += ksft_mkdirty.sh TEST_PROGS += ksft_mlock.sh diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config index deba93379c80..1dbe2b4558ab 100644 --- a/tools/testing/selftests/mm/config +++ b/tools/testing/selftests/mm/config @@ -11,3 +11,5 @@ CONFIG_ANON_VMA_NAME=y CONFIG_FTRACE=y CONFIG_PROFILING=y CONFIG_UPROBES=y +CONFIG_MEMORY_FAILURE=y +CONFIG_HWPOISON_INJECT=m diff --git a/tools/testing/selftests/mm/ksft_memory_failure.sh b/tools/testing/selftests/mm/ksft_memory_failure.sh new file mode 100755 index 000000000000..ae1614d4d49b --- /dev/null +++ b/tools/testing/selftests/mm/ksft_memory_failure.sh @@ -0,0 +1,4 @@ +#!/bin/sh -e +# SPDX-License-Identifier: GPL-2.0 + +./run_vmtests.sh -t memory-failure diff --git a/tools/testing/selftests/mm/memory-failure.c b/tools/testing/selftests/mm/memory-failure.c new file mode 100644 index 000000000000..3d9e0b9ffb41 --- /dev/null +++ b/tools/testing/selftests/mm/memory-failure.c @@ -0,0 +1,359 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Memory-failure functional tests. + * + * Author(s): Miaohe Lin <linmiaohe@huawei.com> + */ + +#include "../kselftest_harness.h" + +#include <sys/mman.h> +#include <linux/mman.h> +#include <linux/string.h> +#include <unistd.h> +#include <signal.h> +#include <setjmp.h> +#include <unistd.h> +#include <fcntl.h> +#include <sys/vfs.h> +#include <linux/magic.h> +#include <errno.h> + +#include "vm_util.h" + +enum inject_type { + MADV_HARD, + MADV_SOFT, +}; + +enum result_type { + MADV_HARD_ANON, + MADV_HARD_CLEAN_PAGECACHE, + MADV_HARD_DIRTY_PAGECACHE, + MADV_SOFT_ANON, + MADV_SOFT_CLEAN_PAGECACHE, + MADV_SOFT_DIRTY_PAGECACHE, +}; + +static jmp_buf signal_jmp_buf; +static siginfo_t siginfo; +const char *pagemap_proc = "/proc/self/pagemap"; +const char *kpageflags_proc = "/proc/kpageflags"; + +FIXTURE(memory_failure) +{ + unsigned long page_size; + unsigned long corrupted_size; + unsigned long pfn; + int pagemap_fd; + int kpageflags_fd; + bool triggered; +}; + +FIXTURE_VARIANT(memory_failure) +{ + enum inject_type type; + int (*inject)(FIXTURE_DATA(memory_failure) * self, void *vaddr); +}; + +static int madv_hard_inject(FIXTURE_DATA(memory_failure) * self, void *vaddr) +{ + return madvise(vaddr, self->page_size, MADV_HWPOISON); +} + +FIXTURE_VARIANT_ADD(memory_failure, madv_hard) +{ + .type = MADV_HARD, + .inject = madv_hard_inject, +}; + +static int madv_soft_inject(FIXTURE_DATA(memory_failure) * self, void *vaddr) +{ + return madvise(vaddr, self->page_size, MADV_SOFT_OFFLINE); +} + +FIXTURE_VARIANT_ADD(memory_failure, madv_soft) +{ + .type = MADV_SOFT, + .inject = madv_soft_inject, +}; + +static void sigbus_action(int signo, siginfo_t *si, void *args) +{ + memcpy(&siginfo, si, sizeof(siginfo_t)); + siglongjmp(signal_jmp_buf, 1); +} + +static int setup_sighandler(void) +{ + struct sigaction sa = { + .sa_sigaction = sigbus_action, + .sa_flags = SA_SIGINFO, + }; + + return sigaction(SIGBUS, &sa, NULL); +} + +FIXTURE_SETUP(memory_failure) +{ + memset(self, 0, sizeof(*self)); + + self->page_size = (unsigned long)sysconf(_SC_PAGESIZE); + + memset(&siginfo, 0, sizeof(siginfo)); + if (setup_sighandler()) + SKIP(return, "setup sighandler failed.\n"); + + self->pagemap_fd = open(pagemap_proc, O_RDONLY); + if (self->pagemap_fd == -1) + SKIP(return, "open %s failed.\n", pagemap_proc); + + self->kpageflags_fd = open(kpageflags_proc, O_RDONLY); + if (self->kpageflags_fd == -1) + SKIP(return, "open %s failed.\n", kpageflags_proc); +} + +static void teardown_sighandler(void) +{ + struct sigaction sa = { + .sa_handler = SIG_DFL, + .sa_flags = SA_SIGINFO, + }; + + sigaction(SIGBUS, &sa, NULL); +} + +FIXTURE_TEARDOWN(memory_failure) +{ + close(self->kpageflags_fd); + close(self->pagemap_fd); + teardown_sighandler(); +} + +static void prepare(struct __test_metadata *_metadata, FIXTURE_DATA(memory_failure) * self, + void *vaddr) +{ + self->pfn = pagemap_get_pfn(self->pagemap_fd, vaddr); + ASSERT_NE(self->pfn, -1UL); + + ASSERT_EQ(get_hardware_corrupted_size(&self->corrupted_size), 0); +} + +static bool check_memory(void *vaddr, unsigned long size) +{ + char buf[64]; + + memset(buf, 0xce, sizeof(buf)); + while (size >= sizeof(buf)) { + if (memcmp(vaddr, buf, sizeof(buf))) + return false; + size -= sizeof(buf); + vaddr += sizeof(buf); + } + + return true; +} + +static void check(struct __test_metadata *_metadata, FIXTURE_DATA(memory_failure) * self, + void *vaddr, enum result_type type, int setjmp) +{ + unsigned long size; + uint64_t pfn_flags; + + switch (type) { + case MADV_SOFT_ANON: + case MADV_HARD_CLEAN_PAGECACHE: + case MADV_SOFT_CLEAN_PAGECACHE: + case MADV_SOFT_DIRTY_PAGECACHE: + /* It is not expected to receive a SIGBUS signal. */ + ASSERT_EQ(setjmp, 0); + + /* The page content should remain unchanged. */ + ASSERT_TRUE(check_memory(vaddr, self->page_size)); + + /* The backing pfn of addr should have changed. */ + ASSERT_NE(pagemap_get_pfn(self->pagemap_fd, vaddr), self->pfn); + break; + case MADV_HARD_ANON: + case MADV_HARD_DIRTY_PAGECACHE: + /* The SIGBUS signal should have been received. */ + ASSERT_EQ(setjmp, 1); + + /* Check if siginfo contains correct SIGBUS context. */ + ASSERT_EQ(siginfo.si_signo, SIGBUS); + ASSERT_EQ(siginfo.si_code, BUS_MCEERR_AR); + ASSERT_EQ(1UL << siginfo.si_addr_lsb, self->page_size); + ASSERT_EQ(siginfo.si_addr, vaddr); + + /* XXX Check backing pte is hwpoison entry when supported. */ + ASSERT_TRUE(pagemap_is_swapped(self->pagemap_fd, vaddr)); + break; + default: + SKIP(return, "unexpected inject type %d.\n", type); + } + + /* Check if the value of HardwareCorrupted has increased. */ + ASSERT_EQ(get_hardware_corrupted_size(&size), 0); + ASSERT_EQ(size, self->corrupted_size + self->page_size / 1024); + + /* Check if HWPoison flag is set. */ + ASSERT_EQ(pageflags_get(self->pfn, self->kpageflags_fd, &pfn_flags), 0); + ASSERT_EQ(pfn_flags & KPF_HWPOISON, KPF_HWPOISON); +} + +static void cleanup(struct __test_metadata *_metadata, FIXTURE_DATA(memory_failure) * self, + void *vaddr) +{ + unsigned long size; + uint64_t pfn_flags; + + ASSERT_EQ(unpoison_memory(self->pfn), 0); + + /* Check if HWPoison flag is cleared. */ + ASSERT_EQ(pageflags_get(self->pfn, self->kpageflags_fd, &pfn_flags), 0); + ASSERT_NE(pfn_flags & KPF_HWPOISON, KPF_HWPOISON); + + /* Check if the value of HardwareCorrupted has decreased. */ + ASSERT_EQ(get_hardware_corrupted_size(&size), 0); + ASSERT_EQ(size, self->corrupted_size); +} + +TEST_F(memory_failure, anon) +{ + char *addr; + int ret; + + addr = mmap(0, self->page_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (addr == MAP_FAILED) + SKIP(return, "mmap failed, not enough memory.\n"); + memset(addr, 0xce, self->page_size); + + prepare(_metadata, self, addr); + + ret = sigsetjmp(signal_jmp_buf, 1); + if (!self->triggered) { + self->triggered = true; + ASSERT_EQ(variant->inject(self, addr), 0); + FORCE_READ(*addr); + } + + if (variant->type == MADV_HARD) + check(_metadata, self, addr, MADV_HARD_ANON, ret); + else + check(_metadata, self, addr, MADV_SOFT_ANON, ret); + + cleanup(_metadata, self, addr); + + ASSERT_EQ(munmap(addr, self->page_size), 0); +} + +static int prepare_file(const char *fname, unsigned long size) +{ + int fd; + + fd = open(fname, O_RDWR | O_CREAT, 0664); + if (fd >= 0) { + unlink(fname); + ftruncate(fd, size); + } + return fd; +} + +/* Borrowed from mm/gup_longterm.c. */ +static int get_fs_type(int fd) +{ + struct statfs fs; + int ret; + + do { + ret = fstatfs(fd, &fs); + } while (ret && errno == EINTR); + + return ret ? 0 : (int)fs.f_type; +} + +TEST_F(memory_failure, clean_pagecache) +{ + int fd; + char *addr; + int ret; + int fs_type; + + fd = prepare_file("./clean-page-cache-test-file", self->page_size); + if (fd < 0) + SKIP(return, "failed to open test file.\n"); + fs_type = get_fs_type(fd); + if (!fs_type || fs_type == TMPFS_MAGIC) + SKIP(return, "unsupported filesystem :%x\n", fs_type); + + addr = mmap(0, self->page_size, PROT_READ | PROT_WRITE, + MAP_SHARED, fd, 0); + if (addr == MAP_FAILED) + SKIP(return, "mmap failed, not enough memory.\n"); + memset(addr, 0xce, self->page_size); + fsync(fd); + + prepare(_metadata, self, addr); + + ret = sigsetjmp(signal_jmp_buf, 1); + if (!self->triggered) { + self->triggered = true; + ASSERT_EQ(variant->inject(self, addr), 0); + FORCE_READ(*addr); + } + + if (variant->type == MADV_HARD) + check(_metadata, self, addr, MADV_HARD_CLEAN_PAGECACHE, ret); + else + check(_metadata, self, addr, MADV_SOFT_CLEAN_PAGECACHE, ret); + + cleanup(_metadata, self, addr); + + ASSERT_EQ(munmap(addr, self->page_size), 0); + + ASSERT_EQ(close(fd), 0); +} + +TEST_F(memory_failure, dirty_pagecache) +{ + int fd; + char *addr; + int ret; + int fs_type; + + fd = prepare_file("./dirty-page-cache-test-file", self->page_size); + if (fd < 0) + SKIP(return, "failed to open test file.\n"); + fs_type = get_fs_type(fd); + if (!fs_type || fs_type == TMPFS_MAGIC) + SKIP(return, "unsupported filesystem :%x\n", fs_type); + + addr = mmap(0, self->page_size, PROT_READ | PROT_WRITE, + MAP_SHARED, fd, 0); + if (addr == MAP_FAILED) + SKIP(return, "mmap failed, not enough memory.\n"); + memset(addr, 0xce, self->page_size); + + prepare(_metadata, self, addr); + + ret = sigsetjmp(signal_jmp_buf, 1); + if (!self->triggered) { + self->triggered = true; + ASSERT_EQ(variant->inject(self, addr), 0); + FORCE_READ(*addr); + } + + if (variant->type == MADV_HARD) + check(_metadata, self, addr, MADV_HARD_DIRTY_PAGECACHE, ret); + else + check(_metadata, self, addr, MADV_SOFT_DIRTY_PAGECACHE, ret); + + cleanup(_metadata, self, addr); + + ASSERT_EQ(munmap(addr, self->page_size), 0); + + ASSERT_EQ(close(fd), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 29be9038bfb0..afdcfd0d7cef 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -91,6 +91,8 @@ separated by spaces: test VMA merge cases behave as expected - rmap test rmap behaves as expected +- memory-failure + test memory-failure behaves as expected example: ./run_vmtests.sh -t "hmm mmap ksm" EOF @@ -527,6 +529,25 @@ CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned CATEGORY="rmap" run_test ./rmap +# Try to load hwpoison_inject if not present. +HWPOISON_DIR=/sys/kernel/debug/hwpoison/ +if [ ! -d "$HWPOISON_DIR" ]; then + if ! modprobe -q -R hwpoison_inject; then + echo "Module hwpoison_inject not found, skipping..." + else + modprobe hwpoison_inject > /dev/null 2>&1 + LOADED_MOD=1 + fi +fi + +if [ -d "$HWPOISON_DIR" ]; then + CATEGORY="memory-failure" run_test ./memory-failure +fi + +if [ -n "${LOADED_MOD}" ]; then + modprobe -r hwpoison_inject > /dev/null 2>&1 +fi + if [ "${HAVE_HUGEPAGES}" = 1 ]; then echo "$orig_nr_hugepgs" > /proc/sys/vm/nr_hugepages fi diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index d954bf91afd5..a6d4ff7dfdc0 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -723,3 +723,44 @@ int ksm_stop(void) close(ksm_fd); return ret == 1 ? 0 : -errno; } + +int get_hardware_corrupted_size(unsigned long *val) +{ + unsigned long size; + char *line = NULL; + size_t linelen = 0; + FILE *f = fopen("/proc/meminfo", "r"); + int ret = -1; + + if (!f) + return ret; + + while (getline(&line, &linelen, f) > 0) { + if (sscanf(line, "HardwareCorrupted: %12lu kB", &size) == 1) { + *val = size; + ret = 0; + break; + } + } + + free(line); + fclose(f); + return ret; +} + +int unpoison_memory(unsigned long pfn) +{ + int unpoison_fd, len; + char buf[32]; + ssize_t ret; + + unpoison_fd = open("/sys/kernel/debug/hwpoison/unpoison-pfn", O_WRONLY); + if (unpoison_fd < 0) + return -errno; + + len = sprintf(buf, "0x%lx\n", pfn); + ret = write(unpoison_fd, buf, len); + close(unpoison_fd); + + return ret > 0 ? 0 : -errno; +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 522f7f9050f5..e9c4e24769c1 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -20,6 +20,7 @@ #define KPF_COMPOUND_HEAD BIT_ULL(15) #define KPF_COMPOUND_TAIL BIT_ULL(16) +#define KPF_HWPOISON BIT_ULL(19) #define KPF_THP BIT_ULL(22) /* * Ignore the checkpatch warning, we must read from x but don't want to do @@ -154,6 +155,8 @@ long ksm_get_full_scans(void); int ksm_use_zero_pages(void); int ksm_start(void); int ksm_stop(void); +int get_hardware_corrupted_size(unsigned long *val); +int unpoison_memory(unsigned long pfn); /* * On ppc64 this will only work with radix 2M hugepage size diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index afdea6d95bde..605c54c0e8a3 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -15,6 +15,7 @@ TEST_PROGS := \ big_tcp.sh \ bind_bhash.sh \ bpf_offload.py \ + bridge_vlan_dump.sh \ broadcast_ether_dst.sh \ broadcast_pmtu.sh \ busy_poll_test.sh \ diff --git a/tools/testing/selftests/net/bridge_vlan_dump.sh b/tools/testing/selftests/net/bridge_vlan_dump.sh new file mode 100755 index 000000000000..ad66731d2a6f --- /dev/null +++ b/tools/testing/selftests/net/bridge_vlan_dump.sh @@ -0,0 +1,204 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bridge VLAN range grouping. VLANs are collapsed into a range entry in +# the dump if they have the same per-VLAN options. These tests verify that +# VLANs with different per-VLAN option values are not grouped together. + +# shellcheck disable=SC1091,SC2034,SC2154,SC2317 +source lib.sh + +ALL_TESTS=" + vlan_range_neigh_suppress + vlan_range_mcast_max_groups + vlan_range_mcast_n_groups + vlan_range_mcast_enabled +" + +setup_prepare() +{ + setup_ns NS + defer cleanup_all_ns + + ip -n "$NS" link add name br0 type bridge vlan_filtering 1 \ + vlan_default_pvid 0 mcast_snooping 1 mcast_vlan_snooping 1 + ip -n "$NS" link set dev br0 up + + ip -n "$NS" link add name dummy0 type dummy + ip -n "$NS" link set dev dummy0 master br0 + ip -n "$NS" link set dev dummy0 up +} + +vlan_range_neigh_suppress() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Configure different neigh_suppress values and verify no range grouping + bridge -n "$NS" vlan set vid 10 dev dummy0 neigh_suppress on + check_err $? "Failed to set neigh_suppress for VLAN 10" + + bridge -n "$NS" vlan set vid 11 dev dummy0 neigh_suppress off + check_err $? "Failed to set neigh_suppress for VLAN 11" + + # Verify VLANs are not shown as a range, but individual entries exist + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different neigh_suppress incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Configure same neigh_suppress value and verify range grouping + bridge -n "$NS" vlan set vid 11 dev dummy0 neigh_suppress on + check_err $? "Failed to set neigh_suppress for VLAN 11" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same neigh_suppress not grouped" + + log_test "VLAN range grouping with neigh_suppress" +} + +vlan_range_mcast_max_groups() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Configure different mcast_max_groups values and verify no range grouping + bridge -n "$NS" vlan set vid 10 dev dummy0 mcast_max_groups 100 + check_err $? "Failed to set mcast_max_groups for VLAN 10" + + bridge -n "$NS" vlan set vid 11 dev dummy0 mcast_max_groups 200 + check_err $? "Failed to set mcast_max_groups for VLAN 11" + + # Verify VLANs are not shown as a range, but individual entries exist + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different mcast_max_groups incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Configure same mcast_max_groups value and verify range grouping + bridge -n "$NS" vlan set vid 11 dev dummy0 mcast_max_groups 100 + check_err $? "Failed to set mcast_max_groups for VLAN 11" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same mcast_max_groups not grouped" + + log_test "VLAN range grouping with mcast_max_groups" +} + +vlan_range_mcast_n_groups() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Add different numbers of multicast groups to each VLAN + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.1 vid 10 + check_err $? "Failed to add mdb entry to VLAN 10" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.1 vid 10 + + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.2 vid 10 + check_err $? "Failed to add second mdb entry to VLAN 10" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.2 vid 10 + + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.1 vid 11 + check_err $? "Failed to add mdb entry to VLAN 11" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.1 vid 11 + + # Verify VLANs are not shown as a range due to different mcast_n_groups + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different mcast_n_groups incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Add another group to VLAN 11 to match VLAN 10's count + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.2 vid 11 + check_err $? "Failed to add second mdb entry to VLAN 11" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.2 vid 11 + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same mcast_n_groups not grouped" + + log_test "VLAN range grouping with mcast_n_groups" +} + +vlan_range_mcast_enabled() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev br0 self + defer bridge -n "$NS" vlan del vid 10 dev br0 self + + bridge -n "$NS" vlan add vid 11 dev br0 self + defer bridge -n "$NS" vlan del vid 11 dev br0 self + + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Configure different mcast_snooping for bridge VLANs + # Port VLANs inherit BR_VLFLAG_MCAST_ENABLED from bridge VLANs + bridge -n "$NS" vlan global set dev br0 vid 10 mcast_snooping 1 + bridge -n "$NS" vlan global set dev br0 vid 11 mcast_snooping 0 + + # Verify port VLANs are not grouped due to different mcast_enabled + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different mcast_enabled incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Configure same mcast_snooping and verify range grouping + bridge -n "$NS" vlan global set dev br0 vid 11 mcast_snooping 1 + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same mcast_enabled not grouped" + + log_test "VLAN range grouping with mcast_enabled" +} + +# Verify the newest tested option is supported +if ! bridge vlan help 2>&1 | grep -q "neigh_suppress"; then + echo "SKIP: iproute2 too old, missing per-VLAN neighbor suppression support" + exit "$ksft_skip" +fi + +trap defer_scopes_cleanup EXIT +setup_prepare +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 21026b667667..6eb7f95e70e1 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1672,6 +1672,17 @@ ipv4_withv6_fcnal() run_cmd "$IP ro replace 172.16.101.1/32 via inet6 2001:db8:50::1 dev veth1" log_test $? 2 "IPv4 route with invalid IPv6 gateway" + + # Test IPv4 route with loopback IPv6 nexthop + # Regression test: loopback IPv6 nexthop was misclassified as reject + # route, skipping nhc_pcpu_rth_output allocation, causing panic when + # an IPv4 route references it and triggers __mkroute_output(). + run_cmd "$IP -6 nexthop add id 20 dev lo" + run_cmd "$IP ro add 172.20.20.0/24 nhid 20" + run_cmd "ip netns exec $me ping -c1 -W1 172.20.20.1" + log_test $? 1 "IPv4 route with loopback IPv6 nexthop (no crash)" + run_cmd "$IP ro del 172.20.20.0/24" + run_cmd "$IP nexthop del id 20" } ipv4_fcnal_runtime() diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh index 3da9d93ab36f..625162fd7e8b 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh @@ -28,6 +28,7 @@ ALL_TESTS=" test_8021d test_8021q test_8021qvs + test_mdb_count_warning " NUM_NETIFS=4 @@ -83,8 +84,6 @@ switch_create_8021q() { local br_flags=$1; shift - log_info "802.1q $br_flags${br_flags:+ }tests" - ip link add name br0 type bridge vlan_filtering 1 vlan_default_pvid 0 \ mcast_snooping 1 $br_flags \ mcast_igmp_version 3 mcast_mld_version 2 @@ -106,6 +105,7 @@ switch_create_8021q() switch_create_8021qvs() { + log_info "802.1q mcast_vlan_snooping 1 tests" switch_create_8021q "mcast_vlan_snooping 1" bridge vlan global set dev br0 vid 10 mcast_igmp_version 3 bridge vlan global set dev br0 vid 10 mcast_mld_version 2 @@ -1272,6 +1272,76 @@ test_8021qvs_toggle_vlan_snooping() test_toggle_vlan_snooping_permanent } +mdb_count_check_warn() +{ + local msg=$1; shift + + dmesg | grep -q "WARNING:.*br_multicast_port_ngroups_dec.*" + check_fail $? "$msg" +} + +test_mdb_count_mcast_vlan_snooping_flush() +{ + RET=0 + + # check if we already have a warning + mdb_count_check_warn "Check MDB entries count warning before test" + + bridge mdb add dev br0 port "$swp1" grp 239.0.0.1 permanent vid 10 + ip link set dev br0 down + ip link set dev br0 type bridge mcast_vlan_snooping 1 + bridge mdb flush dev br0 + + mdb_count_check_warn "Check MDB entries count warning after test" + + ip link set dev br0 type bridge mcast_vlan_snooping 0 + ip link set dev br0 up + + log_test "MDB count warning: mcast_vlan_snooping and MDB flush" +} + +test_mdb_count_mcast_snooping_flush() +{ + RET=0 + + # check if we already have a warning + mdb_count_check_warn "Check MDB entries count warning before test" + + bridge mdb add dev br0 port "$swp1" grp 239.0.0.1 permanent vid 10 + ip link set dev br0 type bridge mcast_snooping 0 + ip link set dev br0 type bridge mcast_vlan_snooping 1 + bridge mdb flush dev br0 + + mdb_count_check_warn "Check MDB entries count warning after test" + + ip link set dev br0 type bridge mcast_vlan_snooping 0 + ip link set dev br0 type bridge mcast_snooping 1 + + log_test "MDB count warning: mcast_snooping and MDB flush" +} + +test_mdb_count_vlan_state_flush() +{ + RET=0 + + # check if we already have a warning + mdb_count_check_warn "Check MDB entries count warning before test" + + bridge mdb add dev br0 port "$swp1" grp 239.0.0.1 permanent vid 10 + ip link set dev br0 down + bridge vlan set vid 10 dev "$swp1" state blocking + ip link set dev br0 type bridge mcast_vlan_snooping 1 + ip link set dev br0 up + bridge mdb flush dev br0 + + mdb_count_check_warn "Check MDB entries count warning after test" + + bridge vlan set vid 10 dev "$swp1" state forwarding + ip link set dev br0 type bridge mcast_vlan_snooping 0 + + log_test "MDB count warning: disabled vlan state and MDB flush" +} + # test groups test_8021d() @@ -1297,6 +1367,7 @@ test_8021q() { # Tests for vlan_filtering 1 mcast_vlan_snooping 0. + log_info "802.1q tests" switch_create_8021q setup_wait @@ -1334,6 +1405,21 @@ test_8021qvs() switch_destroy } +test_mdb_count_warning() +{ + # Tests for mdb_n_entries warning + + log_info "MDB count warning tests" + switch_create_8021q + setup_wait + + test_mdb_count_mcast_vlan_snooping_flush + test_mdb_count_mcast_snooping_flush + test_mdb_count_vlan_state_flush + + switch_destroy +} + if ! bridge link help 2>&1 | grep -q "mcast_max_groups"; then echo "SKIP: iproute2 too old, missing bridge \"mcast_max_groups\" support" exit $ksft_skip diff --git a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh index af008fbf2725..eb2d8034de9c 100755 --- a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh +++ b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh @@ -98,12 +98,20 @@ setup_prepare() h1_create h2_create switch_create + + if [ -f /proc/sys/net/bridge/bridge-nf-call-iptables ]; then + sysctl_set net.bridge.bridge-nf-call-iptables 0 + fi } cleanup() { pre_cleanup + if [ -f /proc/sys/net/bridge/bridge-nf-call-iptables ]; then + sysctl_restore net.bridge.bridge-nf-call-iptables + fi + switch_destroy h2_destroy h1_destroy diff --git a/tools/testing/selftests/net/forwarding/pedit_ip.sh b/tools/testing/selftests/net/forwarding/pedit_ip.sh index d14efb2d23b2..9235674627ab 100755 --- a/tools/testing/selftests/net/forwarding/pedit_ip.sh +++ b/tools/testing/selftests/net/forwarding/pedit_ip.sh @@ -91,12 +91,20 @@ setup_prepare() h1_create h2_create switch_create + + if [ -f /proc/sys/net/bridge/bridge-nf-call-iptables ]; then + sysctl_set net.bridge.bridge-nf-call-iptables 0 + fi } cleanup() { pre_cleanup + if [ -f /proc/sys/net/bridge/bridge-nf-call-iptables ]; then + sysctl_restore net.bridge.bridge-nf-call-iptables + fi + switch_destroy h2_destroy h1_destroy diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index ea89e558672d..86edbc7e2489 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -223,7 +223,7 @@ mirred_egress_to_ingress_tcp_test() ip_proto icmp \ action drop - ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & + ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 > $mirred_e2i_tf2 & local rpid=$! ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 wait -n $rpid diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh index b43816dd998c..457f41d5e584 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh @@ -567,6 +567,21 @@ vxlan_encapped_ping_do() local inner_tos=$1; shift local outer_tos=$1; shift + local ipv4hdr=$(: + )"45:"$( : IP version + IHL + )"$inner_tos:"$( : IP TOS + )"00:54:"$( : IP total length + )"99:83:"$( : IP identification + )"40:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"01:"$( : IP proto + )"CHECKSUM:"$( : IP header csum + )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 + )"c0:00:02:01"$( : IP daddr: 192.0.2.1 + ) + local checksum=$(payload_template_calc_checksum "$ipv4hdr") + ipv4hdr=$(payload_template_expand_checksum "$ipv4hdr" $checksum) + $MZ $dev -c $count -d 100msec -q \ -b $next_hop_mac -B $dest_ip \ -t udp tos=$outer_tos,sp=23456,dp=$VXPORT,p=$(: @@ -577,16 +592,7 @@ vxlan_encapped_ping_do() )"$dest_mac:"$( : ETH daddr )"$(mac_get w2):"$( : ETH saddr )"08:00:"$( : ETH type - )"45:"$( : IP version + IHL - )"$inner_tos:"$( : IP TOS - )"00:54:"$( : IP total length - )"99:83:"$( : IP identification - )"40:00:"$( : IP flags + frag off - )"40:"$( : IP TTL - )"01:"$( : IP proto - )"00:00:"$( : IP header csum - )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 - )"c0:00:02:01:"$( : IP daddr: 192.0.2.1 + )"$ipv4hdr:"$( : IPv4 header )"08:"$( : ICMP type )"00:"$( : ICMP code )"8b:f2:"$( : ICMP csum diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh index a603f7b0a08f..e642feeada0e 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh @@ -695,7 +695,7 @@ vxlan_encapped_ping_do() )"6"$( : IP version )"$inner_tos"$( : Traffic class )"0:00:00:"$( : Flow label - )"00:08:"$( : Payload length + )"00:03:"$( : Payload length )"3a:"$( : Next header )"04:"$( : Hop limit )"$saddr:"$( : IP saddr diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 0ec131b339bc..b40694573f4c 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -577,7 +577,7 @@ ip_link_has_flag() local flag=$1; shift local state=$(ip -j link show "$name" | - jq --arg flag "$flag" 'any(.[].flags.[]; . == $flag)') + jq --arg flag "$flag" 'any(.[].flags[]; . == $flag)') [[ $state == true ]] } diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index dc1f200aaa81..a3144d7298a5 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -104,6 +104,24 @@ CBPF_MPTCP_SUBOPTION_ADD_ADDR="14, 6 0 0 65535, 6 0 0 0" +# IPv4: TCP hdr of 48B, a first suboption of 12B (DACK8), the RM_ADDR suboption +# generated using "nfbpf_compile '(ip[32] & 0xf0) == 0xc0 && ip[53] == 0x0c && +# (ip[66] & 0xf0) == 0x40'" +CBPF_MPTCP_SUBOPTION_RM_ADDR="13, + 48 0 0 0, + 84 0 0 240, + 21 0 9 64, + 48 0 0 32, + 84 0 0 240, + 21 0 6 192, + 48 0 0 53, + 21 0 4 12, + 48 0 0 66, + 84 0 0 240, + 21 0 1 64, + 6 0 0 65535, + 6 0 0 0" + init_partial() { capout=$(mktemp) @@ -2608,6 +2626,19 @@ remove_tests() chk_rst_nr 0 0 fi + # signal+subflow with limits, remove + if reset "remove signal+subflow with limits"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,subflow + pm_nl_set_limits $ns2 0 0 + addr_nr_ns1=-1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 1 1 + chk_rm_nr 1 0 invert + chk_rst_nr 0 0 + fi + # addresses remove if reset "remove addresses"; then pm_nl_set_limits $ns1 3 3 @@ -4217,6 +4248,14 @@ endpoint_tests() chk_subflow_nr "after no reject" 3 chk_mptcp_info subflows 2 subflows 2 + # To make sure RM_ADDR are sent over a different subflow, but + # allow the rest to quickly and cleanly close the subflow + local ipt=1 + ip netns exec "${ns2}" ${iptables} -I OUTPUT -s "10.0.1.2" \ + -p tcp -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_RM_ADDR" \ + -j DROP || ipt=0 local i for i in $(seq 3); do pm_nl_del_endpoint $ns2 1 10.0.1.2 @@ -4229,6 +4268,7 @@ endpoint_tests() chk_subflow_nr "after re-add id 0 ($i)" 3 chk_mptcp_info subflows 3 subflows 3 done + [ ${ipt} = 1 ] && ip netns exec "${ns2}" ${iptables} -D OUTPUT 1 mptcp_lib_kill_group_wait $tests_pid @@ -4288,11 +4328,20 @@ endpoint_tests() chk_mptcp_info subflows 2 subflows 2 chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 + # To make sure RM_ADDR are sent over a different subflow, but + # allow the rest to quickly and cleanly close the subflow + local ipt=1 + ip netns exec "${ns1}" ${iptables} -I OUTPUT -s "10.0.1.1" \ + -p tcp -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_RM_ADDR" \ + -j DROP || ipt=0 pm_nl_del_endpoint $ns1 42 10.0.1.1 sleep 0.5 chk_subflow_nr "after delete ID 0" 2 chk_mptcp_info subflows 2 subflows 2 chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 + [ ${ipt} = 1 ] && ip netns exec "${ns1}" ${iptables} -D OUTPUT 1 pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal wait_mpj 4 diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 806aaa7d2d61..d11a8b949aab 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -237,10 +237,13 @@ run_test() for dev in ns2eth1 ns2eth2; do tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1 done - tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 - tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 - tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 - tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 + + # keep the queued pkts number low, or the RTT estimator will see + # increasing latency over time. + tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 limit 50 + tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 limit 50 + tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 limit 50 + tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 limit 50 # time is measured in ms, account for transfer size, aggregated link speed # and header overhead (10%) diff --git a/tools/testing/selftests/net/netfilter/nf_queue.c b/tools/testing/selftests/net/netfilter/nf_queue.c index 9e56b9d47037..116c0ca0eabb 100644 --- a/tools/testing/selftests/net/netfilter/nf_queue.c +++ b/tools/testing/selftests/net/netfilter/nf_queue.c @@ -18,6 +18,7 @@ struct options { bool count_packets; bool gso_enabled; + bool failopen; int verbose; unsigned int queue_num; unsigned int timeout; @@ -30,7 +31,7 @@ static struct options opts; static void help(const char *p) { - printf("Usage: %s [-c|-v [-vv] ] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p); + printf("Usage: %s [-c|-v [-vv] ] [-o] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p); } static int parse_attr_cb(const struct nlattr *attr, void *data) @@ -236,6 +237,8 @@ struct mnl_socket *open_queue(void) flags = opts.gso_enabled ? NFQA_CFG_F_GSO : 0; flags |= NFQA_CFG_F_UID_GID; + if (opts.failopen) + flags |= NFQA_CFG_F_FAIL_OPEN; mnl_attr_put_u32(nlh, NFQA_CFG_FLAGS, htonl(flags)); mnl_attr_put_u32(nlh, NFQA_CFG_MASK, htonl(flags)); @@ -329,7 +332,7 @@ static void parse_opts(int argc, char **argv) { int c; - while ((c = getopt(argc, argv, "chvt:q:Q:d:G")) != -1) { + while ((c = getopt(argc, argv, "chvot:q:Q:d:G")) != -1) { switch (c) { case 'c': opts.count_packets = true; @@ -366,6 +369,9 @@ static void parse_opts(int argc, char **argv) case 'G': opts.gso_enabled = false; break; + case 'o': + opts.failopen = true; + break; case 'v': opts.verbose++; break; diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh index 139bc1211878..ea766bdc5d04 100755 --- a/tools/testing/selftests/net/netfilter/nft_queue.sh +++ b/tools/testing/selftests/net/netfilter/nft_queue.sh @@ -591,6 +591,7 @@ EOF test_udp_gro_ct() { local errprefix="FAIL: test_udp_gro_ct:" + local timeout=5 ip netns exec "$nsrouter" conntrack -F 2>/dev/null @@ -630,10 +631,10 @@ table inet udpq { } } EOF - timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc & + timeout "$timeout" ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc & local rpid=$! - ip netns exec "$nsrouter" ./nf_queue -G -c -q 1 -t 2 > "$TMPFILE2" & + ip netns exec "$nsrouter" nice -n -19 ./nf_queue -G -c -q 1 -o -t 2 > "$TMPFILE2" & local nfqpid=$! ip netns exec "$nsrouter" ethtool -K "veth0" rx-udp-gro-forwarding on rx-gro-list on generic-receive-offload on @@ -643,8 +644,12 @@ EOF local bs=512 local count=$(((32 * 1024 * 1024) / bs)) - dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 16); do - timeout 5 ip netns exec "$ns1" \ + + local nprocs=$(nproc) + [ $nprocs -gt 1 ] && nprocs=$((nprocs - 1)) + + dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 $nprocs); do + timeout "$timeout" nice -n 19 ip netns exec "$ns1" \ socat -u -b 512 STDIN UDP-DATAGRAM:10.0.2.99:12346,reuseport,bind=0.0.0.0:55221 & done diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh index b34e5cf0112e..0a97d5ae3469 100755 --- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh +++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh @@ -13,6 +13,15 @@ declare -A ip_args=( -D TFO_COOKIE_ZERO=b7c12350a90dc8f5 -D CMSG_LEVEL_IP=SOL_IP -D CMSG_TYPE_RECVERR=IP_RECVERR" + [ipv4-mapped-ipv6]="--ip_version=ipv4-mapped-ipv6 + --local_ip=192.168.0.1 + --gateway_ip=192.168.0.1 + --netmask_ip=255.255.0.0 + --remote_ip=192.0.2.1 + -D TFO_COOKIE=3021b9d889017eeb + -D TFO_COOKIE_ZERO=b7c12350a90dc8f5 + -D CMSG_LEVEL_IP=SOL_IPV6 + -D CMSG_TYPE_RECVERR=IPV6_RECVERR" [ipv6]="--ip_version=ipv6 --mtu=1520 --local_ip=fd3d:0a0b:17d6::1 @@ -45,7 +54,7 @@ fi ip_versions=$(grep -E '^--ip_version=' $script | cut -d '=' -f 2) if [[ -z $ip_versions ]]; then - ip_versions="ipv4 ipv6" + ip_versions="ipv4 ipv6 ipv4-mapped-ipv6" elif [[ ! "$ip_versions" =~ ^ipv[46]$ ]]; then ktap_exit_fail_msg "Too many or unsupported --ip_version: $ip_versions" exit "$KSFT_FAIL" diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt index 3848b419e68c..6c0f32c40f19 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt @@ -38,7 +38,7 @@ // If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd +0 < P. 4001:54001(50000) ack 1 win 257 - +0 > . 1:1(0) ack 54001 win 0 + * > . 1:1(0) ack 54001 win 0 // Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times. +0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "` diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt deleted file mode 100644 index f575c0ff89da..000000000000 --- a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt +++ /dev/null @@ -1,33 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - ---mss=1000 - -`./defaults.sh` - - 0 `nstat -n` - -// Establish a connection. - +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 - +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 - +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0 - +0 bind(3, ..., ...) = 0 - +0 listen(3, 1) = 0 - - +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> - +0 > S. 0:0(0) ack 1 win 18980 <mss 1460,nop,wscale 0> - +.1 < . 1:1(0) ack 1 win 257 - - +0 accept(3, ..., ...) = 4 - - +0 < P. 1:20001(20000) ack 1 win 257 - +.04 > . 1:1(0) ack 20001 win 18000 - - +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [12000], 4) = 0 - +0 < P. 20001:80001(60000) ack 1 win 257 - +0 > . 1:1(0) ack 20001 win 18000 - - +0 read(4, ..., 20000) = 20000 -// A too big packet is accepted if the receive queue is empty - +0 < P. 20001:80001(60000) ack 1 win 257 - +0 > . 1:1(0) ack 80001 win 0 - diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt new file mode 100644 index 000000000000..e245359a1a91 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Some TCP stacks send FINs even though the window is closed. We break +// a possible FIN/ACK loop by accepting the FIN. + +--mss=1000 + +`./defaults.sh` + +// Establish a connection. + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0> + +0 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < P. 1:60001(60000) ack 1 win 257 + * > . 1:1(0) ack 60001 win 0 + + +0 < F. 60001:60001(0) ack 1 win 257 + +0 > . 1:1(0) ack 60002 win 0 diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 248c2b91fe42..5a5ff88321d5 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -28,6 +28,7 @@ ALL_TESTS=" kci_test_fdb_get kci_test_fdb_del kci_test_neigh_get + kci_test_neigh_update kci_test_bridge_parent_id kci_test_address_proto kci_test_enslave_bonding @@ -1160,6 +1161,60 @@ kci_test_neigh_get() end_test "PASS: neigh get" } +kci_test_neigh_update() +{ + dstip=10.0.2.4 + dstmac=de:ad:be:ef:13:37 + local ret=0 + + for proxy in "" "proxy" ; do + # add a neighbour entry without any flags + run_cmd ip neigh add $proxy $dstip dev "$devdummy" lladdr $dstmac nud permanent + run_cmd_grep $dstip ip neigh show $proxy + run_cmd_grep_fail "$dstip dev $devdummy .*\(managed\|use\|router\|extern\)" ip neigh show $proxy + + # set the extern_learn flag, but no other + run_cmd ip neigh change $proxy $dstip dev "$devdummy" extern_learn + run_cmd_grep "$dstip dev $devdummy .* extern_learn" ip neigh show $proxy + run_cmd_grep_fail "$dstip dev $devdummy .* \(managed\|use\|router\)" ip neigh show $proxy + + # flags are reset when not provided + run_cmd ip neigh change $proxy $dstip dev "$devdummy" + run_cmd_grep $dstip ip neigh show $proxy + run_cmd_grep_fail "$dstip dev $devdummy .* extern_learn" ip neigh show $proxy + + # add a protocol + run_cmd ip neigh change $proxy $dstip dev "$devdummy" protocol boot + run_cmd_grep "$dstip dev $devdummy .* proto boot" ip neigh show $proxy + + # protocol is retained when not provided + run_cmd ip neigh change $proxy $dstip dev "$devdummy" + run_cmd_grep "$dstip dev $devdummy .* proto boot" ip neigh show $proxy + + # change protocol + run_cmd ip neigh change $proxy $dstip dev "$devdummy" protocol static + run_cmd_grep "$dstip dev $devdummy .* proto static" ip neigh show $proxy + + # also check an extended flag for non-proxy neighs + if [ "$proxy" = "" ]; then + run_cmd ip neigh change $proxy $dstip dev "$devdummy" managed + run_cmd_grep "$dstip dev $devdummy managed" ip neigh show $proxy + + run_cmd ip neigh change $proxy $dstip dev "$devdummy" lladdr $dstmac + run_cmd_grep_fail "$dstip dev $devdummy managed" ip neigh show $proxy + fi + + run_cmd ip neigh del $proxy $dstip dev "$devdummy" + done + + if [ $ret -ne 0 ];then + end_test "FAIL: neigh update" + return 1 + fi + + end_test "PASS: neigh update" +} + kci_test_bridge_parent_id() { local ret=0 diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c index 8a5cd5cb5472..cf106a49b55e 100644 --- a/tools/testing/selftests/net/tun.c +++ b/tools/testing/selftests/net/tun.c @@ -944,8 +944,8 @@ TEST_F(tun_vnet_udptnl, send_gso_packet) ASSERT_EQ(ret, off); ret = receive_gso_packet_from_tunnel(self, variant, &r_num_mss); - ASSERT_EQ(ret, variant->data_size); - ASSERT_EQ(r_num_mss, variant->r_num_mss); + EXPECT_EQ(ret, variant->data_size); + EXPECT_EQ(r_num_mss, variant->r_num_mss); } TEST_F(tun_vnet_udptnl, recv_gso_packet) @@ -955,18 +955,18 @@ TEST_F(tun_vnet_udptnl, recv_gso_packet) int ret, gso_type = VIRTIO_NET_HDR_GSO_UDP_L4; ret = send_gso_packet_into_tunnel(self, variant); - ASSERT_EQ(ret, variant->data_size); + EXPECT_EQ(ret, variant->data_size); memset(&vnet_hdr, 0, sizeof(vnet_hdr)); ret = receive_gso_packet_from_tun(self, variant, &vnet_hdr); - ASSERT_EQ(ret, variant->data_size); + EXPECT_EQ(ret, variant->data_size); if (!variant->no_gso) { - ASSERT_EQ(vh->gso_size, variant->gso_size); + EXPECT_EQ(vh->gso_size, variant->gso_size); gso_type |= (variant->tunnel_type & UDP_TUNNEL_OUTER_IPV4) ? (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4) : (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6); - ASSERT_EQ(vh->gso_type, gso_type); + EXPECT_EQ(vh->gso_type, gso_type); } } diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore index 7283e8b07b75..80d4270a71ac 100644 --- a/tools/testing/selftests/powerpc/copyloops/.gitignore +++ b/tools/testing/selftests/powerpc/copyloops/.gitignore @@ -2,8 +2,8 @@ copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 -copyuser_p7_t0 -copyuser_p7_t1 +copyuser_p7 +copyuser_p7_vmx memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile index 42940f92d832..0c8efb0bddeb 100644 --- a/tools/testing/selftests/powerpc/copyloops/Makefile +++ b/tools/testing/selftests/powerpc/copyloops/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \ - copyuser_p7_t0 copyuser_p7_t1 \ + copyuser_p7 copyuser_p7_vmx \ memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 \ memcpy_p7_t0 memcpy_p7_t1 copy_mc_64 \ copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2 \ @@ -28,10 +28,15 @@ $(OUTPUT)/copyuser_64_t%: copyuser_64.S $(EXTRA_SOURCES) -D SELFTEST_CASE=$(subst copyuser_64_t,,$(notdir $@)) \ -o $@ $^ -$(OUTPUT)/copyuser_p7_t%: copyuser_power7.S $(EXTRA_SOURCES) +$(OUTPUT)/copyuser_p7: copyuser_power7.S $(EXTRA_SOURCES) $(CC) $(CPPFLAGS) $(CFLAGS) \ -D COPY_LOOP=test___copy_tofrom_user_power7 \ - -D SELFTEST_CASE=$(subst copyuser_p7_t,,$(notdir $@)) \ + -o $@ $^ + +$(OUTPUT)/copyuser_p7_vmx: copyuser_power7.S $(EXTRA_SOURCES) ../utils.c + $(CC) $(CPPFLAGS) $(CFLAGS) \ + -D COPY_LOOP=test___copy_tofrom_user_power7_vmx \ + -D VMX_TEST \ -o $@ $^ # Strictly speaking, we only need the memcpy_64 test cases for big-endian diff --git a/tools/testing/selftests/powerpc/copyloops/stubs.S b/tools/testing/selftests/powerpc/copyloops/stubs.S index ec8bcf2bf1c2..3a9cb8c9a3ee 100644 --- a/tools/testing/selftests/powerpc/copyloops/stubs.S +++ b/tools/testing/selftests/powerpc/copyloops/stubs.S @@ -1,13 +1,5 @@ #include <asm/ppc_asm.h> -FUNC_START(enter_vmx_usercopy) - li r3,1 - blr - -FUNC_START(exit_vmx_usercopy) - li r3,0 - blr - FUNC_START(enter_vmx_ops) li r3,1 blr diff --git a/tools/testing/selftests/powerpc/copyloops/validate.c b/tools/testing/selftests/powerpc/copyloops/validate.c index 0f6873618552..fb822534fbe9 100644 --- a/tools/testing/selftests/powerpc/copyloops/validate.c +++ b/tools/testing/selftests/powerpc/copyloops/validate.c @@ -12,6 +12,10 @@ #define BUFLEN (MAX_LEN+MAX_OFFSET+2*MIN_REDZONE) #define POISON 0xa5 +#ifdef VMX_TEST +#define VMX_COPY_THRESHOLD 3328 +#endif + unsigned long COPY_LOOP(void *to, const void *from, unsigned long size); static void do_one(char *src, char *dst, unsigned long src_off, @@ -81,8 +85,12 @@ int test_copy_loop(void) /* Fill with sequential bytes */ for (i = 0; i < BUFLEN; i++) fill[i] = i & 0xff; - +#ifdef VMX_TEST + /* Force sizes above kernel VMX threshold (3328) */ + for (len = VMX_COPY_THRESHOLD + 1; len < MAX_LEN; len++) { +#else for (len = 1; len < MAX_LEN; len++) { +#endif for (src_off = 0; src_off < MAX_OFFSET; src_off++) { for (dst_off = 0; dst_off < MAX_OFFSET; dst_off++) { do_one(src, dst, src_off, dst_off, len, @@ -96,5 +104,10 @@ int test_copy_loop(void) int main(void) { +#ifdef VMX_TEST + /* Skip if Altivec not present */ + SKIP_IF_MSG(!have_hwcap(PPC_FEATURE_HAS_ALTIVEC), "ALTIVEC not supported"); +#endif + return test_harness(test_copy_loop, str(COPY_LOOP)); } diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N index 07f5e0a70ae7..f943cdfb0a74 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N @@ -2,7 +2,9 @@ CONFIG_RCU_TRACE=n CONFIG_SMP=y CONFIG_NR_CPUS=4 CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_DYNAMIC=n +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n #CHECK#CONFIG_RCU_EXPERT=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T index c70cf0405f24..06e4d1030279 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U index bc9eeabaa1b1..71da6e3e9488 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n @@ -7,4 +8,3 @@ CONFIG_PREEMPT_DYNAMIC=n CONFIG_RCU_TRACE=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PREEMPT_COUNT=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 index 2f9fcffff5ae..dd2bd4e08da4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 b/tools/testing/selftests/rcutorture/configs/rcu/TINY01 index 0953c52fcfd7..2be53bf60d65 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY01 @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n @@ -11,4 +12,3 @@ CONFIG_RCU_TRACE=n #CHECK#CONFIG_RCU_STALL_COMMON=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PREEMPT_COUNT=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 index 30439f6fc20e..be8860342ef7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 index 18efab346381..8fb124c28f28 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 @@ -1,7 +1,8 @@ CONFIG_SMP=y CONFIG_NR_CPUS=5 CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 67caf4276bb0..ac857d5bcb22 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -1,10 +1,12 @@ CONFIG_SMP=y CONFIG_NR_CPUS=8 +CONFIG_PREEMPT_LAZY=y CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=y +CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TREE_RCU=y +#CHECK#CONFIG_PREEMPT_RCU=n CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 index 9f48c73709ec..61d15b1b54d1 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 @@ -1,6 +1,8 @@ CONFIG_SMP=y CONFIG_NR_CPUS=8 -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_DYNAMIC=n +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n #CHECK#CONFIG_TREE_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 index db27651de04b..0e090bb68a0f 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 @@ -1,9 +1,12 @@ CONFIG_SMP=y CONFIG_NR_CPUS=8 -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_DYNAMIC=n +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n #CHECK#CONFIG_TREE_RCU=y +#CHECK#CONFIG_PREEMPT_RCU=n CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 b/tools/testing/selftests/rcutorture/configs/rcu/TREE10 index 420632b030dc..b2ce37861e71 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10 @@ -6,6 +6,7 @@ CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TREE_RCU=y +CONFIG_PREEMPT_RCU=n CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL b/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL index 5d546efa68e8..696fba9968c6 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL +++ b/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL @@ -1,6 +1,8 @@ CONFIG_SMP=y CONFIG_NR_CPUS=8 -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_DYNAMIC=n +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_HZ_PERIODIC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY index 0fa2dc086e10..c1a7d38823fb 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 index 0059592c7408..f3f1368b8386 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 @@ -1,5 +1,6 @@ CONFIG_SMP=y -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT index 67f9d2998afd..1f215e17cbae 100644 --- a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT +++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT @@ -1,5 +1,6 @@ CONFIG_SMP=y -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/refscale/TINY b/tools/testing/selftests/rcutorture/configs/refscale/TINY index 759343980b80..9a11b578ff34 100644 --- a/tools/testing/selftests/rcutorture/configs/refscale/TINY +++ b/tools/testing/selftests/rcutorture/configs/refscale/TINY @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT index 6133f54ce2a7..f9621e2770a4 100644 --- a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT +++ b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT @@ -1,5 +1,6 @@ CONFIG_SMP=y -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 2c601a7eaff5..006300ac6dff 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -93,6 +93,8 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) \ $(CLANG_SYS_INCLUDES) \ -Wall -Wno-compare-distinct-pointer-types \ -Wno-incompatible-function-pointer-types \ + -Wno-microsoft-anon-tag \ + -fms-extensions \ -O2 -mcpu=v3 # sort removes libbpf duplicates when not cross-building diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c index 82c71653977b..44577e30e764 100644 --- a/tools/testing/selftests/sched_ext/init_enable_count.c +++ b/tools/testing/selftests/sched_ext/init_enable_count.c @@ -57,7 +57,8 @@ static enum scx_test_status run_test(bool global) char buf; close(pipe_fds[1]); - read(pipe_fds[0], &buf, 1); + if (read(pipe_fds[0], &buf, 1) < 0) + exit(1); close(pipe_fds[0]); exit(0); } diff --git a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c index a3faf5bb49d6..784f2f6c1af9 100644 --- a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c @@ -58,14 +58,14 @@ static void record_peek_result(long pid) { u32 slot_key; long *slot_pid_ptr; - int ix; + u32 ix; if (pid <= 0) return; /* Find an empty slot or one with the same PID */ bpf_for(ix, 0, 10) { - slot_key = (pid + ix) % MAX_SAMPLES; + slot_key = ((u64)pid + ix) % MAX_SAMPLES; slot_pid_ptr = bpf_map_lookup_elem(&peek_results, &slot_key); if (!slot_pid_ptr) continue; diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c index 015200f80f6e..81ea9b4883e5 100644 --- a/tools/testing/selftests/sched_ext/rt_stall.c +++ b/tools/testing/selftests/sched_ext/rt_stall.c @@ -15,7 +15,6 @@ #include <signal.h> #include <bpf/bpf.h> #include <scx/common.h> -#include <unistd.h> #include "rt_stall.bpf.skel.h" #include "scx_test.h" #include "../kselftest.h" @@ -23,6 +22,30 @@ #define CORE_ID 0 /* CPU to pin tasks to */ #define RUN_TIME 5 /* How long to run the test in seconds */ +/* Signal the parent that setup is complete by writing to a pipe */ +static void signal_ready(int fd) +{ + char c = 1; + + if (write(fd, &c, 1) != 1) { + perror("write to ready pipe"); + exit(EXIT_FAILURE); + } + close(fd); +} + +/* Wait for a child to signal readiness via a pipe */ +static void wait_ready(int fd) +{ + char c; + + if (read(fd, &c, 1) != 1) { + perror("read from ready pipe"); + exit(EXIT_FAILURE); + } + close(fd); +} + /* Simple busy-wait function for test tasks */ static void process_func(void) { @@ -122,14 +145,24 @@ static bool sched_stress_test(bool is_ext) float ext_runtime, rt_runtime, actual_ratio; int ext_pid, rt_pid; + int ext_ready[2], rt_ready[2]; ksft_print_header(); ksft_set_plan(1); + if (pipe(ext_ready) || pipe(rt_ready)) { + perror("pipe"); + ksft_exit_fail(); + } + /* Create and set up a EXT task */ ext_pid = fork(); if (ext_pid == 0) { + close(ext_ready[0]); + close(rt_ready[0]); + close(rt_ready[1]); set_affinity(CORE_ID); + signal_ready(ext_ready[1]); process_func(); exit(0); } else if (ext_pid < 0) { @@ -140,8 +173,12 @@ static bool sched_stress_test(bool is_ext) /* Create an RT task */ rt_pid = fork(); if (rt_pid == 0) { + close(ext_ready[0]); + close(ext_ready[1]); + close(rt_ready[0]); set_affinity(CORE_ID); set_sched(SCHED_FIFO, 50); + signal_ready(rt_ready[1]); process_func(); exit(0); } else if (rt_pid < 0) { @@ -149,6 +186,17 @@ static bool sched_stress_test(bool is_ext) ksft_exit_fail(); } + /* + * Wait for both children to complete their setup (affinity and + * scheduling policy) before starting the measurement window. + * This prevents flaky failures caused by the RT child's setup + * time eating into the measurement period. + */ + close(ext_ready[1]); + close(rt_ready[1]); + wait_ready(ext_ready[0]); + wait_ready(rt_ready[0]); + /* Let the processes run for the specified time */ sleep(RUN_TIME); diff --git a/tools/testing/selftests/sched_ext/runner.c b/tools/testing/selftests/sched_ext/runner.c index 5748d2c69903..761c21f96404 100644 --- a/tools/testing/selftests/sched_ext/runner.c +++ b/tools/testing/selftests/sched_ext/runner.c @@ -166,6 +166,9 @@ int main(int argc, char **argv) enum scx_test_status status; struct scx_test *test = &__scx_tests[i]; + if (exit_req) + break; + if (list) { printf("%s\n", test->name); if (i == (__scx_num_tests - 1)) diff --git a/tools/testing/selftests/sched_ext/util.c b/tools/testing/selftests/sched_ext/util.c index e47769c91918..2111329ed289 100644 --- a/tools/testing/selftests/sched_ext/util.c +++ b/tools/testing/selftests/sched_ext/util.c @@ -60,11 +60,11 @@ int file_write_long(const char *path, long val) char buf[64]; int ret; - ret = sprintf(buf, "%lu", val); + ret = sprintf(buf, "%ld", val); if (ret < 0) return ret; - if (write_text(path, buf, sizeof(buf)) <= 0) + if (write_text(path, buf, ret) <= 0) return -1; return 0; diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json index 7d07c55bb668..33bb8f3ff8ed 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json @@ -505,5 +505,164 @@ "teardown": [ "$TC qdisc del dev $DEV1 ingress" ] + }, + { + "id": "8883", + "name": "Try to attach act_ct to an ets qdisc", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 root handle 1: ets bands 2" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: prio 1 protocol ip matchall action ct index 42", + "expExitCode": "2", + "verifyCmd": "$TC -j filter ls dev $DEV1 parent 1: prio 1 protocol ip", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DEV1 root" + ] + }, + { + "id": "3b10", + "name": "Attach act_ct to an ingress qdisc", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress prio 1 protocol ip matchall action ct index 42", + "expExitCode": "0", + "verifyCmd": "$TC -j filter ls dev $DEV1 ingress prio 1 protocol ip", + "matchJSON": [ + { + "kind": "matchall" + }, + { + "options": { + "actions": [ + { + "order": 1, + "kind": "ct", + "index": 42, + "ref": 1, + "bind": 1 + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "0337", + "name": "Attach act_ct to a clsact/egress qdisc", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 clsact" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 egress prio 1 protocol ip matchall action ct index 42", + "expExitCode": "0", + "verifyCmd": "$TC -j filter ls dev $DEV1 egress prio 1 protocol ip", + "matchJSON": [ + { + "kind": "matchall" + }, + { + "options": { + "actions": [ + { + "order": 1, + "kind": "ct", + "index": 42, + "ref": 1, + "bind": 1 + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] + }, + { + "id": "4f60", + "name": "Attach act_ct to a shared block", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 ingress_block 21 clsact" + ], + "cmdUnderTest": "$TC filter add block 21 prio 1 protocol ip matchall action ct index 42", + "expExitCode": "0", + "verifyCmd": "$TC -j filter ls block 21 prio 1 protocol ip", + "matchJSON": [ + { + "kind": "matchall" + }, + { + "options": { + "actions": [ + { + "order": 1, + "kind": "ct", + "index": 42, + "ref": 1, + "bind": 1 + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 ingress_block 21 clsact" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json index f587a32e44c4..808aef4afe22 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json @@ -1279,5 +1279,104 @@ "teardown": [ "$TC actions flush action ife" ] + }, + { + "id": "f2a0", + "name": "Update decode ife action with encode metadata", + "category": [ + "actions", + "ife" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife decode index 10" + ], + "cmdUnderTest": "$TC actions replace action ife encode use tcindex 1 index 10", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action ife index 10", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "ife", + "mode": "encode", + "control_action": { + "type": "pipe" + }, + "type": "0xed3e", + "tcindex": 1, + "index": 10, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "d352", + "name": "Update decode ife action into encode with multiple metadata", + "category": [ + "actions", + "ife" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife decode index 10" + ], + "cmdUnderTest": "$TC actions replace action ife encode use tcindex 1 use mark 22 index 10", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action ife index 10", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "ife", + "mode": "encode", + "control_action": { + "type": "pipe" + }, + "type": "0xed3e", + "tcindex": 1, + "mark": 22, + "index": 10, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC actions flush action ife" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py index 0440d252c4c5..bc447ca57333 100644 --- a/tools/testing/selftests/tc-testing/tdc_helper.py +++ b/tools/testing/selftests/tc-testing/tdc_helper.py @@ -38,10 +38,14 @@ def list_test_cases(testlist): def list_categories(testlist): - """ Show all categories that are present in a test case file. """ - categories = set(map(lambda x: x['category'], testlist)) + """Show all unique categories present in the test cases.""" + categories = set() + for t in testlist: + if 'category' in t: + categories.update(t['category']) + print("Available categories:") - print(", ".join(str(s) for s in categories)) + print(", ".join(sorted(categories))) print("") diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index dc8dbe74a6d0..86e338886b33 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -210,16 +210,21 @@ check_result() { } add_namespaces() { - local orig_mode - orig_mode=$(cat /proc/sys/net/vsock/child_ns_mode) - - for mode in "${NS_MODES[@]}"; do - echo "${mode}" > /proc/sys/net/vsock/child_ns_mode - ip netns add "${mode}0" 2>/dev/null - ip netns add "${mode}1" 2>/dev/null - done - - echo "${orig_mode}" > /proc/sys/net/vsock/child_ns_mode + ip netns add "global-parent" 2>/dev/null + echo "global" | ip netns exec "global-parent" \ + tee /proc/sys/net/vsock/child_ns_mode &>/dev/null + ip netns add "local-parent" 2>/dev/null + echo "local" | ip netns exec "local-parent" \ + tee /proc/sys/net/vsock/child_ns_mode &>/dev/null + + nsenter --net=/var/run/netns/global-parent \ + ip netns add "global0" 2>/dev/null + nsenter --net=/var/run/netns/global-parent \ + ip netns add "global1" 2>/dev/null + nsenter --net=/var/run/netns/local-parent \ + ip netns add "local0" 2>/dev/null + nsenter --net=/var/run/netns/local-parent \ + ip netns add "local1" 2>/dev/null } init_namespaces() { @@ -237,6 +242,8 @@ del_namespaces() { log_host "removed ns ${mode}0" log_host "removed ns ${mode}1" done + ip netns del "global-parent" &>/dev/null + ip netns del "local-parent" &>/dev/null } vm_ssh() { @@ -287,7 +294,7 @@ check_args() { } check_deps() { - for dep in vng ${QEMU} busybox pkill ssh ss socat; do + for dep in vng ${QEMU} busybox pkill ssh ss socat nsenter; do if [[ ! -x $(command -v "${dep}") ]]; then echo -e "skip: dependency ${dep} not found!\n" exit "${KSFT_SKIP}" @@ -1231,12 +1238,8 @@ test_ns_local_same_cid_ok() { } test_ns_host_vsock_child_ns_mode_ok() { - local orig_mode - local rc - - orig_mode=$(cat /proc/sys/net/vsock/child_ns_mode) + local rc="${KSFT_PASS}" - rc="${KSFT_PASS}" for mode in "${NS_MODES[@]}"; do local ns="${mode}0" @@ -1246,15 +1249,13 @@ test_ns_host_vsock_child_ns_mode_ok() { continue fi - if ! echo "${mode}" > /proc/sys/net/vsock/child_ns_mode; then - log_host "child_ns_mode should be writable to ${mode}" + if ! echo "${mode}" | ip netns exec "${ns}" \ + tee /proc/sys/net/vsock/child_ns_mode &>/dev/null; then rc="${KSFT_FAIL}" continue fi done - echo "${orig_mode}" > /proc/sys/net/vsock/child_ns_mode - return "${rc}" } diff --git a/tools/testing/vma/Makefile b/tools/testing/vma/Makefile index 66f3831a668f..e72b45dedda5 100644 --- a/tools/testing/vma/Makefile +++ b/tools/testing/vma/Makefile @@ -6,10 +6,13 @@ default: vma include ../shared/shared.mk -OFILES = $(SHARED_OFILES) vma.o maple-shim.o +OFILES = $(SHARED_OFILES) main.o shared.o maple-shim.o TARGETS = vma -vma.o: vma.c vma_internal.h ../../../mm/vma.c ../../../mm/vma_init.c ../../../mm/vma_exec.c ../../../mm/vma.h +# These can be varied to test different sizes. +CFLAGS += -DNUM_VMA_FLAG_BITS=128 -DNUM_MM_FLAG_BITS=128 + +main.o: main.c shared.c shared.h vma_internal.h tests/merge.c tests/mmap.c tests/vma.c ../../../mm/vma.c ../../../mm/vma_init.c ../../../mm/vma_exec.c ../../../mm/vma.h include/custom.h include/dup.h include/stubs.h vma: $(OFILES) $(CC) $(CFLAGS) -o $@ $(OFILES) $(LDLIBS) diff --git a/tools/testing/vma/include/custom.h b/tools/testing/vma/include/custom.h new file mode 100644 index 000000000000..802a76317245 --- /dev/null +++ b/tools/testing/vma/include/custom.h @@ -0,0 +1,119 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#pragma once + +/* + * Contains declarations that exist in the kernel which have been CUSTOMISED for + * testing purposes to faciliate userland VMA testing. + */ + +#ifdef CONFIG_MMU +extern unsigned long mmap_min_addr; +extern unsigned long dac_mmap_min_addr; +#else +#define mmap_min_addr 0UL +#define dac_mmap_min_addr 0UL +#endif + +#define VM_WARN_ON(_expr) (WARN_ON(_expr)) +#define VM_WARN_ON_ONCE(_expr) (WARN_ON_ONCE(_expr)) +#define VM_WARN_ON_VMG(_expr, _vmg) (WARN_ON(_expr)) +#define VM_BUG_ON(_expr) (BUG_ON(_expr)) +#define VM_BUG_ON_VMA(_expr, _vma) (BUG_ON(_expr)) + +/* We hardcode this for now. */ +#define sysctl_max_map_count 0x1000000UL + +#define TASK_SIZE ((1ul << 47)-PAGE_SIZE) + +/* + * The shared stubs do not implement this, it amounts to an fprintf(STDERR,...) + * either way :) + */ +#define pr_warn_once pr_err + +#define pgtable_supports_soft_dirty() 1 + +struct anon_vma { + struct anon_vma *root; + struct rb_root_cached rb_root; + + /* Test fields. */ + bool was_cloned; + bool was_unlinked; +}; + +static inline void unlink_anon_vmas(struct vm_area_struct *vma) +{ + /* For testing purposes, indicate that the anon_vma was unlinked. */ + vma->anon_vma->was_unlinked = true; +} + +static inline void vma_start_write(struct vm_area_struct *vma) +{ + /* Used to indicate to tests that a write operation has begun. */ + vma->vm_lock_seq++; +} + +static inline __must_check +int vma_start_write_killable(struct vm_area_struct *vma) +{ + /* Used to indicate to tests that a write operation has begun. */ + vma->vm_lock_seq++; + return 0; +} + +static inline int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src, + enum vma_operation operation) +{ + /* For testing purposes. We indicate that an anon_vma has been cloned. */ + if (src->anon_vma != NULL) { + dst->anon_vma = src->anon_vma; + dst->anon_vma->was_cloned = true; + } + + return 0; +} + +static inline int __anon_vma_prepare(struct vm_area_struct *vma) +{ + struct anon_vma *anon_vma = calloc(1, sizeof(struct anon_vma)); + + if (!anon_vma) + return -ENOMEM; + + anon_vma->root = anon_vma; + vma->anon_vma = anon_vma; + + return 0; +} + +static inline int anon_vma_prepare(struct vm_area_struct *vma) +{ + if (likely(vma->anon_vma)) + return 0; + + return __anon_vma_prepare(vma); +} + +static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) +{ + if (reset_refcnt) + refcount_set(&vma->vm_refcnt, 0); +} + +static inline vma_flags_t __mk_vma_flags(size_t count, const vma_flag_t *bits) +{ + vma_flags_t flags; + int i; + + /* + * For testing purposes: allow invalid bit specification so we can + * easily test. + */ + vma_flags_clear_all(&flags); + for (i = 0; i < count; i++) + if (bits[i] < NUM_VMA_FLAG_BITS) + vma_flag_set(&flags, bits[i]); + return flags; +} diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h new file mode 100644 index 000000000000..3078ff1487d3 --- /dev/null +++ b/tools/testing/vma/include/dup.h @@ -0,0 +1,1320 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#pragma once + +/* Forward declarations to avoid header cycle. */ +struct vm_area_struct; +static inline void vma_start_write(struct vm_area_struct *vma); + +extern const struct vm_operations_struct vma_dummy_vm_ops; +extern unsigned long stack_guard_gap; +extern const struct vm_operations_struct vma_dummy_vm_ops; +extern unsigned long rlimit(unsigned int limit); +struct task_struct *get_current(void); + +#define MMF_HAS_MDWE 28 +#define current get_current() + +/* + * Define the task command name length as enum, then it can be visible to + * BPF programs. + */ +enum { + TASK_COMM_LEN = 16, +}; + +/* PARTIALLY implemented types. */ +struct mm_struct { + struct maple_tree mm_mt; + int map_count; /* number of VMAs */ + unsigned long total_vm; /* Total pages mapped */ + unsigned long locked_vm; /* Pages that have PG_mlocked set */ + unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ + unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ + unsigned long stack_vm; /* VM_STACK */ + + unsigned long def_flags; + + mm_flags_t flags; /* Must use mm_flags_* helpers to access */ +}; +struct address_space { + struct rb_root_cached i_mmap; + unsigned long flags; + atomic_t i_mmap_writable; +}; +struct file_operations { + int (*mmap)(struct file *, struct vm_area_struct *); + int (*mmap_prepare)(struct vm_area_desc *); +}; +struct file { + struct address_space *f_mapping; + const struct file_operations *f_op; +}; +struct anon_vma_chain { + struct anon_vma *anon_vma; + struct list_head same_vma; +}; +struct task_struct { + char comm[TASK_COMM_LEN]; + pid_t pid; + struct mm_struct *mm; + + /* Used for emulating ABI behavior of previous Linux versions: */ + unsigned int personality; +}; + +struct kref { + refcount_t refcount; +}; + +struct anon_vma_name { + struct kref kref; + /* The name needs to be at the end because it is dynamically sized. */ + char name[]; +}; + +/* + * Contains declarations that are DUPLICATED from kernel source in order to + * faciliate userland VMA testing. + * + * These must be kept in sync with kernel source. + */ + +#define VMA_LOCK_OFFSET 0x40000000 + +typedef struct { unsigned long v; } freeptr_t; + +#define VM_NONE 0x00000000 + +typedef int __bitwise vma_flag_t; + +#define ACCESS_PRIVATE(p, member) ((p)->member) + +#define DECLARE_VMA_BIT(name, bitnum) \ + VMA_ ## name ## _BIT = ((__force vma_flag_t)bitnum) +#define DECLARE_VMA_BIT_ALIAS(name, aliased) \ + VMA_ ## name ## _BIT = VMA_ ## aliased ## _BIT +enum { + DECLARE_VMA_BIT(READ, 0), + DECLARE_VMA_BIT(WRITE, 1), + DECLARE_VMA_BIT(EXEC, 2), + DECLARE_VMA_BIT(SHARED, 3), + /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ + DECLARE_VMA_BIT(MAYREAD, 4), /* limits for mprotect() etc. */ + DECLARE_VMA_BIT(MAYWRITE, 5), + DECLARE_VMA_BIT(MAYEXEC, 6), + DECLARE_VMA_BIT(MAYSHARE, 7), + DECLARE_VMA_BIT(GROWSDOWN, 8), /* general info on the segment */ +#ifdef CONFIG_MMU + DECLARE_VMA_BIT(UFFD_MISSING, 9),/* missing pages tracking */ +#else + /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */ + DECLARE_VMA_BIT(MAYOVERLAY, 9), +#endif /* CONFIG_MMU */ + /* Page-ranges managed without "struct page", just pure PFN */ + DECLARE_VMA_BIT(PFNMAP, 10), + DECLARE_VMA_BIT(MAYBE_GUARD, 11), + DECLARE_VMA_BIT(UFFD_WP, 12), /* wrprotect pages tracking */ + DECLARE_VMA_BIT(LOCKED, 13), + DECLARE_VMA_BIT(IO, 14), /* Memory mapped I/O or similar */ + DECLARE_VMA_BIT(SEQ_READ, 15), /* App will access data sequentially */ + DECLARE_VMA_BIT(RAND_READ, 16), /* App will not benefit from clustered reads */ + DECLARE_VMA_BIT(DONTCOPY, 17), /* Do not copy this vma on fork */ + DECLARE_VMA_BIT(DONTEXPAND, 18),/* Cannot expand with mremap() */ + DECLARE_VMA_BIT(LOCKONFAULT, 19),/* Lock pages covered when faulted in */ + DECLARE_VMA_BIT(ACCOUNT, 20), /* Is a VM accounted object */ + DECLARE_VMA_BIT(NORESERVE, 21), /* should the VM suppress accounting */ + DECLARE_VMA_BIT(HUGETLB, 22), /* Huge TLB Page VM */ + DECLARE_VMA_BIT(SYNC, 23), /* Synchronous page faults */ + DECLARE_VMA_BIT(ARCH_1, 24), /* Architecture-specific flag */ + DECLARE_VMA_BIT(WIPEONFORK, 25),/* Wipe VMA contents in child. */ + DECLARE_VMA_BIT(DONTDUMP, 26), /* Do not include in the core dump */ + DECLARE_VMA_BIT(SOFTDIRTY, 27), /* NOT soft dirty clean area */ + DECLARE_VMA_BIT(MIXEDMAP, 28), /* Can contain struct page and pure PFN pages */ + DECLARE_VMA_BIT(HUGEPAGE, 29), /* MADV_HUGEPAGE marked this vma */ + DECLARE_VMA_BIT(NOHUGEPAGE, 30),/* MADV_NOHUGEPAGE marked this vma */ + DECLARE_VMA_BIT(MERGEABLE, 31), /* KSM may merge identical pages */ + /* These bits are reused, we define specific uses below. */ + DECLARE_VMA_BIT(HIGH_ARCH_0, 32), + DECLARE_VMA_BIT(HIGH_ARCH_1, 33), + DECLARE_VMA_BIT(HIGH_ARCH_2, 34), + DECLARE_VMA_BIT(HIGH_ARCH_3, 35), + DECLARE_VMA_BIT(HIGH_ARCH_4, 36), + DECLARE_VMA_BIT(HIGH_ARCH_5, 37), + DECLARE_VMA_BIT(HIGH_ARCH_6, 38), + /* + * This flag is used to connect VFIO to arch specific KVM code. It + * indicates that the memory under this VMA is safe for use with any + * non-cachable memory type inside KVM. Some VFIO devices, on some + * platforms, are thought to be unsafe and can cause machine crashes + * if KVM does not lock down the memory type. + */ + DECLARE_VMA_BIT(ALLOW_ANY_UNCACHED, 39), +#ifdef CONFIG_PPC32 + DECLARE_VMA_BIT_ALIAS(DROPPABLE, ARCH_1), +#else + DECLARE_VMA_BIT(DROPPABLE, 40), +#endif + DECLARE_VMA_BIT(UFFD_MINOR, 41), + DECLARE_VMA_BIT(SEALED, 42), + /* Flags that reuse flags above. */ + DECLARE_VMA_BIT_ALIAS(PKEY_BIT0, HIGH_ARCH_0), + DECLARE_VMA_BIT_ALIAS(PKEY_BIT1, HIGH_ARCH_1), + DECLARE_VMA_BIT_ALIAS(PKEY_BIT2, HIGH_ARCH_2), + DECLARE_VMA_BIT_ALIAS(PKEY_BIT3, HIGH_ARCH_3), + DECLARE_VMA_BIT_ALIAS(PKEY_BIT4, HIGH_ARCH_4), +#if defined(CONFIG_X86_USER_SHADOW_STACK) + /* + * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of + * support core mm. + * + * These VMAs will get a single end guard page. This helps userspace + * protect itself from attacks. A single page is enough for current + * shadow stack archs (x86). See the comments near alloc_shstk() in + * arch/x86/kernel/shstk.c for more details on the guard size. + */ + DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_5), +#elif defined(CONFIG_ARM64_GCS) + /* + * arm64's Guarded Control Stack implements similar functionality and + * has similar constraints to shadow stacks. + */ + DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_6), +#endif + DECLARE_VMA_BIT_ALIAS(SAO, ARCH_1), /* Strong Access Ordering (powerpc) */ + DECLARE_VMA_BIT_ALIAS(GROWSUP, ARCH_1), /* parisc */ + DECLARE_VMA_BIT_ALIAS(SPARC_ADI, ARCH_1), /* sparc64 */ + DECLARE_VMA_BIT_ALIAS(ARM64_BTI, ARCH_1), /* arm64 */ + DECLARE_VMA_BIT_ALIAS(ARCH_CLEAR, ARCH_1), /* sparc64, arm64 */ + DECLARE_VMA_BIT_ALIAS(MAPPED_COPY, ARCH_1), /* !CONFIG_MMU */ + DECLARE_VMA_BIT_ALIAS(MTE, HIGH_ARCH_4), /* arm64 */ + DECLARE_VMA_BIT_ALIAS(MTE_ALLOWED, HIGH_ARCH_5),/* arm64 */ +#ifdef CONFIG_STACK_GROWSUP + DECLARE_VMA_BIT_ALIAS(STACK, GROWSUP), + DECLARE_VMA_BIT_ALIAS(STACK_EARLY, GROWSDOWN), +#else + DECLARE_VMA_BIT_ALIAS(STACK, GROWSDOWN), +#endif +}; + +#define INIT_VM_FLAG(name) BIT((__force int) VMA_ ## name ## _BIT) +#define VM_READ INIT_VM_FLAG(READ) +#define VM_WRITE INIT_VM_FLAG(WRITE) +#define VM_EXEC INIT_VM_FLAG(EXEC) +#define VM_SHARED INIT_VM_FLAG(SHARED) +#define VM_MAYREAD INIT_VM_FLAG(MAYREAD) +#define VM_MAYWRITE INIT_VM_FLAG(MAYWRITE) +#define VM_MAYEXEC INIT_VM_FLAG(MAYEXEC) +#define VM_MAYSHARE INIT_VM_FLAG(MAYSHARE) +#define VM_GROWSDOWN INIT_VM_FLAG(GROWSDOWN) +#ifdef CONFIG_MMU +#define VM_UFFD_MISSING INIT_VM_FLAG(UFFD_MISSING) +#else +#define VM_UFFD_MISSING VM_NONE +#define VM_MAYOVERLAY INIT_VM_FLAG(MAYOVERLAY) +#endif +#define VM_PFNMAP INIT_VM_FLAG(PFNMAP) +#define VM_MAYBE_GUARD INIT_VM_FLAG(MAYBE_GUARD) +#define VM_UFFD_WP INIT_VM_FLAG(UFFD_WP) +#define VM_LOCKED INIT_VM_FLAG(LOCKED) +#define VM_IO INIT_VM_FLAG(IO) +#define VM_SEQ_READ INIT_VM_FLAG(SEQ_READ) +#define VM_RAND_READ INIT_VM_FLAG(RAND_READ) +#define VM_DONTCOPY INIT_VM_FLAG(DONTCOPY) +#define VM_DONTEXPAND INIT_VM_FLAG(DONTEXPAND) +#define VM_LOCKONFAULT INIT_VM_FLAG(LOCKONFAULT) +#define VM_ACCOUNT INIT_VM_FLAG(ACCOUNT) +#define VM_NORESERVE INIT_VM_FLAG(NORESERVE) +#define VM_HUGETLB INIT_VM_FLAG(HUGETLB) +#define VM_SYNC INIT_VM_FLAG(SYNC) +#define VM_ARCH_1 INIT_VM_FLAG(ARCH_1) +#define VM_WIPEONFORK INIT_VM_FLAG(WIPEONFORK) +#define VM_DONTDUMP INIT_VM_FLAG(DONTDUMP) +#ifdef CONFIG_MEM_SOFT_DIRTY +#define VM_SOFTDIRTY INIT_VM_FLAG(SOFTDIRTY) +#else +#define VM_SOFTDIRTY VM_NONE +#endif +#define VM_MIXEDMAP INIT_VM_FLAG(MIXEDMAP) +#define VM_HUGEPAGE INIT_VM_FLAG(HUGEPAGE) +#define VM_NOHUGEPAGE INIT_VM_FLAG(NOHUGEPAGE) +#define VM_MERGEABLE INIT_VM_FLAG(MERGEABLE) +#define VM_STACK INIT_VM_FLAG(STACK) +#ifdef CONFIG_STACK_GROWS_UP +#define VM_STACK_EARLY INIT_VM_FLAG(STACK_EARLY) +#else +#define VM_STACK_EARLY VM_NONE +#endif +#ifdef CONFIG_ARCH_HAS_PKEYS +#define VM_PKEY_SHIFT ((__force int)VMA_HIGH_ARCH_0_BIT) +/* Despite the naming, these are FLAGS not bits. */ +#define VM_PKEY_BIT0 INIT_VM_FLAG(PKEY_BIT0) +#define VM_PKEY_BIT1 INIT_VM_FLAG(PKEY_BIT1) +#define VM_PKEY_BIT2 INIT_VM_FLAG(PKEY_BIT2) +#if CONFIG_ARCH_PKEY_BITS > 3 +#define VM_PKEY_BIT3 INIT_VM_FLAG(PKEY_BIT3) +#else +#define VM_PKEY_BIT3 VM_NONE +#endif /* CONFIG_ARCH_PKEY_BITS > 3 */ +#if CONFIG_ARCH_PKEY_BITS > 4 +#define VM_PKEY_BIT4 INIT_VM_FLAG(PKEY_BIT4) +#else +#define VM_PKEY_BIT4 VM_NONE +#endif /* CONFIG_ARCH_PKEY_BITS > 4 */ +#endif /* CONFIG_ARCH_HAS_PKEYS */ +#if defined(CONFIG_X86_USER_SHADOW_STACK) || defined(CONFIG_ARM64_GCS) +#define VM_SHADOW_STACK INIT_VM_FLAG(SHADOW_STACK) +#else +#define VM_SHADOW_STACK VM_NONE +#endif +#if defined(CONFIG_PPC64) +#define VM_SAO INIT_VM_FLAG(SAO) +#elif defined(CONFIG_PARISC) +#define VM_GROWSUP INIT_VM_FLAG(GROWSUP) +#elif defined(CONFIG_SPARC64) +#define VM_SPARC_ADI INIT_VM_FLAG(SPARC_ADI) +#define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR) +#elif defined(CONFIG_ARM64) +#define VM_ARM64_BTI INIT_VM_FLAG(ARM64_BTI) +#define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR) +#elif !defined(CONFIG_MMU) +#define VM_MAPPED_COPY INIT_VM_FLAG(MAPPED_COPY) +#endif +#ifndef VM_GROWSUP +#define VM_GROWSUP VM_NONE +#endif +#ifdef CONFIG_ARM64_MTE +#define VM_MTE INIT_VM_FLAG(MTE) +#define VM_MTE_ALLOWED INIT_VM_FLAG(MTE_ALLOWED) +#else +#define VM_MTE VM_NONE +#define VM_MTE_ALLOWED VM_NONE +#endif +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR +#define VM_UFFD_MINOR INIT_VM_FLAG(UFFD_MINOR) +#else +#define VM_UFFD_MINOR VM_NONE +#endif +#ifdef CONFIG_64BIT +#define VM_ALLOW_ANY_UNCACHED INIT_VM_FLAG(ALLOW_ANY_UNCACHED) +#define VM_SEALED INIT_VM_FLAG(SEALED) +#else +#define VM_ALLOW_ANY_UNCACHED VM_NONE +#define VM_SEALED VM_NONE +#endif +#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32) +#define VM_DROPPABLE INIT_VM_FLAG(DROPPABLE) +#else +#define VM_DROPPABLE VM_NONE +#endif + +/* Bits set in the VMA until the stack is in its final location */ +#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY) + +#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) + +/* Common data flag combinations */ +#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_DATA_FLAGS_NON_EXEC (VM_READ | VM_WRITE | VM_MAYREAD | \ + VM_MAYWRITE | VM_MAYEXEC) +#define VM_DATA_FLAGS_EXEC (VM_READ | VM_WRITE | VM_EXEC | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) + +#ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */ +#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_EXEC +#endif + +#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ +#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS +#endif + +#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK) + +#define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) + +/* VMA basic access permission flags */ +#define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) + +/* + * Special vmas that are non-mergable, non-mlock()able. + */ +#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) + +#define DEFAULT_MAP_WINDOW ((1UL << 47) - PAGE_SIZE) +#define TASK_SIZE_LOW DEFAULT_MAP_WINDOW +#define TASK_SIZE_MAX DEFAULT_MAP_WINDOW +#define STACK_TOP TASK_SIZE_LOW +#define STACK_TOP_MAX TASK_SIZE_MAX + +/* This mask represents all the VMA flag bits used by mlock */ +#define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) + +#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) + +#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) + +#define RLIMIT_STACK 3 /* max stack size */ +#define RLIMIT_MEMLOCK 8 /* max locked-in-memory address space */ + +#define CAP_IPC_LOCK 14 + +#define VM_STICKY (VM_SOFTDIRTY | VM_MAYBE_GUARD) + +#define VM_IGNORE_MERGE VM_STICKY + +#define VM_COPY_ON_FORK (VM_PFNMAP | VM_MIXEDMAP | VM_UFFD_WP | VM_MAYBE_GUARD) + +#define pgprot_val(x) ((x).pgprot) +#define __pgprot(x) ((pgprot_t) { (x) } ) + +#define for_each_vma(__vmi, __vma) \ + while (((__vma) = vma_next(&(__vmi))) != NULL) + +/* The MM code likes to work with exclusive end addresses */ +#define for_each_vma_range(__vmi, __vma, __end) \ + while (((__vma) = vma_find(&(__vmi), (__end))) != NULL) + +#define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) + +#define PHYS_PFN(x) ((unsigned long)((x) >> PAGE_SHIFT)) + +#define test_and_set_bit(nr, addr) __test_and_set_bit(nr, addr) +#define test_and_clear_bit(nr, addr) __test_and_clear_bit(nr, addr) + +#define AS_MM_ALL_LOCKS 2 + +#define swap(a, b) \ + do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) + +/* + * Flags for bug emulation. + * + * These occupy the top three bytes. + */ +enum { + READ_IMPLIES_EXEC = 0x0400000, +}; + +struct vma_iterator { + struct ma_state mas; +}; + +#define VMA_ITERATOR(name, __mm, __addr) \ + struct vma_iterator name = { \ + .mas = { \ + .tree = &(__mm)->mm_mt, \ + .index = __addr, \ + .node = NULL, \ + .status = ma_start, \ + }, \ + } + +#define DEFINE_MUTEX(mutexname) \ + struct mutex mutexname = {} + +#define DECLARE_BITMAP(name, bits) \ + unsigned long name[BITS_TO_LONGS(bits)] + +#define EMPTY_VMA_FLAGS ((vma_flags_t){ }) + +/* What action should be taken after an .mmap_prepare call is complete? */ +enum mmap_action_type { + MMAP_NOTHING, /* Mapping is complete, no further action. */ + MMAP_REMAP_PFN, /* Remap PFN range. */ + MMAP_IO_REMAP_PFN, /* I/O remap PFN range. */ +}; + +/* + * Describes an action an mmap_prepare hook can instruct to be taken to complete + * the mapping of a VMA. Specified in vm_area_desc. + */ +struct mmap_action { + union { + /* Remap range. */ + struct { + unsigned long start; + unsigned long start_pfn; + unsigned long size; + pgprot_t pgprot; + } remap; + }; + enum mmap_action_type type; + + /* + * If specified, this hook is invoked after the selected action has been + * successfully completed. Note that the VMA write lock still held. + * + * The absolute minimum ought to be done here. + * + * Returns 0 on success, or an error code. + */ + int (*success_hook)(const struct vm_area_struct *vma); + + /* + * If specified, this hook is invoked when an error occurred when + * attempting the selection action. + * + * The hook can return an error code in order to filter the error, but + * it is not valid to clear the error here. + */ + int (*error_hook)(int err); + + /* + * This should be set in rare instances where the operation required + * that the rmap should not be able to access the VMA until + * completely set up. + */ + bool hide_from_rmap_until_complete :1; +}; + +/* Operations which modify VMAs. */ +enum vma_operation { + VMA_OP_SPLIT, + VMA_OP_MERGE_UNFAULTED, + VMA_OP_REMAP, + VMA_OP_FORK, +}; + +/* + * Describes a VMA that is about to be mmap()'ed. Drivers may choose to + * manipulate mutable fields which will cause those fields to be updated in the + * resultant VMA. + * + * Helper functions are not required for manipulating any field. + */ +struct vm_area_desc { + /* Immutable state. */ + const struct mm_struct *const mm; + struct file *const file; /* May vary from vm_file in stacked callers. */ + unsigned long start; + unsigned long end; + + /* Mutable fields. Populated with initial state. */ + pgoff_t pgoff; + struct file *vm_file; + union { + vm_flags_t vm_flags; + vma_flags_t vma_flags; + }; + pgprot_t page_prot; + + /* Write-only fields. */ + const struct vm_operations_struct *vm_ops; + void *private_data; + + /* Take further action? */ + struct mmap_action action; +}; + +struct vm_area_struct { + /* The first cache line has the info for VMA tree walking. */ + + union { + struct { + /* VMA covers [vm_start; vm_end) addresses within mm */ + unsigned long vm_start; + unsigned long vm_end; + }; + freeptr_t vm_freeptr; /* Pointer used by SLAB_TYPESAFE_BY_RCU */ + }; + + struct mm_struct *vm_mm; /* The address space we belong to. */ + pgprot_t vm_page_prot; /* Access permissions of this VMA. */ + + /* + * Flags, see mm.h. + * To modify use vm_flags_{init|reset|set|clear|mod} functions. + */ + union { + const vm_flags_t vm_flags; + vma_flags_t flags; + }; + +#ifdef CONFIG_PER_VMA_LOCK + /* + * Can only be written (using WRITE_ONCE()) while holding both: + * - mmap_lock (in write mode) + * - vm_refcnt bit at VMA_LOCK_OFFSET is set + * Can be read reliably while holding one of: + * - mmap_lock (in read or write mode) + * - vm_refcnt bit at VMA_LOCK_OFFSET is set or vm_refcnt > 1 + * Can be read unreliably (using READ_ONCE()) for pessimistic bailout + * while holding nothing (except RCU to keep the VMA struct allocated). + * + * This sequence counter is explicitly allowed to overflow; sequence + * counter reuse can only lead to occasional unnecessary use of the + * slowpath. + */ + unsigned int vm_lock_seq; +#endif + + /* + * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma + * list, after a COW of one of the file pages. A MAP_SHARED vma + * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack + * or brk vma (with NULL file) can only be in an anon_vma list. + */ + struct list_head anon_vma_chain; /* Serialized by mmap_lock & + * page_table_lock */ + struct anon_vma *anon_vma; /* Serialized by page_table_lock */ + + /* Function pointers to deal with this struct. */ + const struct vm_operations_struct *vm_ops; + + /* Information about our backing store: */ + unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE + units */ + struct file * vm_file; /* File we map to (can be NULL). */ + void * vm_private_data; /* was vm_pte (shared mem) */ + +#ifdef CONFIG_SWAP + atomic_long_t swap_readahead_info; +#endif +#ifndef CONFIG_MMU + struct vm_region *vm_region; /* NOMMU mapping region */ +#endif +#ifdef CONFIG_NUMA + struct mempolicy *vm_policy; /* NUMA policy for the VMA */ +#endif +#ifdef CONFIG_NUMA_BALANCING + struct vma_numab_state *numab_state; /* NUMA Balancing state */ +#endif +#ifdef CONFIG_PER_VMA_LOCK + /* Unstable RCU readers are allowed to read this. */ + refcount_t vm_refcnt; +#endif + /* + * For areas with an address space and backing store, + * linkage into the address_space->i_mmap interval tree. + * + */ + struct { + struct rb_node rb; + unsigned long rb_subtree_last; + } shared; +#ifdef CONFIG_ANON_VMA_NAME + /* + * For private and shared anonymous mappings, a pointer to a null + * terminated string containing the name given to the vma, or NULL if + * unnamed. Serialized by mmap_lock. Use anon_vma_name to access. + */ + struct anon_vma_name *anon_name; +#endif + struct vm_userfaultfd_ctx vm_userfaultfd_ctx; +} __randomize_layout; + +struct vm_operations_struct { + void (*open)(struct vm_area_struct * area); + /** + * @close: Called when the VMA is being removed from the MM. + * Context: User context. May sleep. Caller holds mmap_lock. + */ + void (*close)(struct vm_area_struct * area); + /* Called any time before splitting to check if it's allowed */ + int (*may_split)(struct vm_area_struct *area, unsigned long addr); + int (*mremap)(struct vm_area_struct *area); + /* + * Called by mprotect() to make driver-specific permission + * checks before mprotect() is finalised. The VMA must not + * be modified. Returns 0 if mprotect() can proceed. + */ + int (*mprotect)(struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned long newflags); + vm_fault_t (*fault)(struct vm_fault *vmf); + vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order); + vm_fault_t (*map_pages)(struct vm_fault *vmf, + pgoff_t start_pgoff, pgoff_t end_pgoff); + unsigned long (*pagesize)(struct vm_area_struct * area); + + /* notification that a previously read-only page is about to become + * writable, if an error is returned it will cause a SIGBUS */ + vm_fault_t (*page_mkwrite)(struct vm_fault *vmf); + + /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */ + vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf); + + /* called by access_process_vm when get_user_pages() fails, typically + * for use by special VMAs. See also generic_access_phys() for a generic + * implementation useful for any iomem mapping. + */ + int (*access)(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); + + /* Called by the /proc/PID/maps code to ask the vma whether it + * has a special name. Returning non-NULL will also cause this + * vma to be dumped unconditionally. */ + const char *(*name)(struct vm_area_struct *vma); + +#ifdef CONFIG_NUMA + /* + * set_policy() op must add a reference to any non-NULL @new mempolicy + * to hold the policy upon return. Caller should pass NULL @new to + * remove a policy and fall back to surrounding context--i.e. do not + * install a MPOL_DEFAULT policy, nor the task or system default + * mempolicy. + */ + int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); + + /* + * get_policy() op must add reference [mpol_get()] to any policy at + * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure + * in mm/mempolicy.c will do this automatically. + * get_policy() must NOT add a ref if the policy at (vma,addr) is not + * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. + * If no [shared/vma] mempolicy exists at the addr, get_policy() op + * must return NULL--i.e., do not "fallback" to task or system default + * policy. + */ + struct mempolicy *(*get_policy)(struct vm_area_struct *vma, + unsigned long addr, pgoff_t *ilx); +#endif +#ifdef CONFIG_FIND_NORMAL_PAGE + /* + * Called by vm_normal_page() for special PTEs in @vma at @addr. This + * allows for returning a "normal" page from vm_normal_page() even + * though the PTE indicates that the "struct page" either does not exist + * or should not be touched: "special". + * + * Do not add new users: this really only works when a "normal" page + * was mapped, but then the PTE got changed to something weird (+ + * marked special) that would not make pte_pfn() identify the originally + * inserted page. + */ + struct page *(*find_normal_page)(struct vm_area_struct *vma, + unsigned long addr); +#endif /* CONFIG_FIND_NORMAL_PAGE */ +}; + +struct vm_unmapped_area_info { +#define VM_UNMAPPED_AREA_TOPDOWN 1 + unsigned long flags; + unsigned long length; + unsigned long low_limit; + unsigned long high_limit; + unsigned long align_mask; + unsigned long align_offset; + unsigned long start_gap; +}; + +struct pagetable_move_control { + struct vm_area_struct *old; /* Source VMA. */ + struct vm_area_struct *new; /* Destination VMA. */ + unsigned long old_addr; /* Address from which the move begins. */ + unsigned long old_end; /* Exclusive address at which old range ends. */ + unsigned long new_addr; /* Address to move page tables to. */ + unsigned long len_in; /* Bytes to remap specified by user. */ + + bool need_rmap_locks; /* Do rmap locks need to be taken? */ + bool for_stack; /* Is this an early temp stack being moved? */ +}; + +#define PAGETABLE_MOVE(name, old_, new_, old_addr_, new_addr_, len_) \ + struct pagetable_move_control name = { \ + .old = old_, \ + .new = new_, \ + .old_addr = old_addr_, \ + .old_end = (old_addr_) + (len_), \ + .new_addr = new_addr_, \ + .len_in = len_, \ + } + +static inline void vma_iter_invalidate(struct vma_iterator *vmi) +{ + mas_pause(&vmi->mas); +} + +static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) +{ + return __pgprot(pgprot_val(oldprot) | pgprot_val(newprot)); +} + +static inline pgprot_t vm_get_page_prot(vm_flags_t vm_flags) +{ + return __pgprot(vm_flags); +} + +static inline bool mm_flags_test(int flag, const struct mm_struct *mm) +{ + return test_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); +} + +/* + * Copy value to the first system word of VMA flags, non-atomically. + * + * IMPORTANT: This does not overwrite bytes past the first system word. The + * caller must account for this. + */ +static inline void vma_flags_overwrite_word(vma_flags_t *flags, unsigned long value) +{ + *ACCESS_PRIVATE(flags, __vma_flags) = value; +} + +/* + * Copy value to the first system word of VMA flags ONCE, non-atomically. + * + * IMPORTANT: This does not overwrite bytes past the first system word. The + * caller must account for this. + */ +static inline void vma_flags_overwrite_word_once(vma_flags_t *flags, unsigned long value) +{ + unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags); + + WRITE_ONCE(*bitmap, value); +} + +/* Update the first system word of VMA flags setting bits, non-atomically. */ +static inline void vma_flags_set_word(vma_flags_t *flags, unsigned long value) +{ + unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags); + + *bitmap |= value; +} + +/* Update the first system word of VMA flags clearing bits, non-atomically. */ +static inline void vma_flags_clear_word(vma_flags_t *flags, unsigned long value) +{ + unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags); + + *bitmap &= ~value; +} + +static inline void vma_flags_clear_all(vma_flags_t *flags) +{ + bitmap_zero(ACCESS_PRIVATE(flags, __vma_flags), NUM_VMA_FLAG_BITS); +} + +static inline void vma_flag_set(vma_flags_t *flags, vma_flag_t bit) +{ + unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags); + + __set_bit((__force int)bit, bitmap); +} + +/* Use when VMA is not part of the VMA tree and needs no locking */ +static inline void vm_flags_init(struct vm_area_struct *vma, + vm_flags_t flags) +{ + vma_flags_clear_all(&vma->flags); + vma_flags_overwrite_word(&vma->flags, flags); +} + +/* + * Use when VMA is part of the VMA tree and modifications need coordination + * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and + * it should be locked explicitly beforehand. + */ +static inline void vm_flags_reset(struct vm_area_struct *vma, + vm_flags_t flags) +{ + vma_assert_write_locked(vma); + vm_flags_init(vma, flags); +} + +static inline void vm_flags_reset_once(struct vm_area_struct *vma, + vm_flags_t flags) +{ + vma_assert_write_locked(vma); + /* + * The user should only be interested in avoiding reordering of + * assignment to the first word. + */ + vma_flags_clear_all(&vma->flags); + vma_flags_overwrite_word_once(&vma->flags, flags); +} + +static inline void vm_flags_set(struct vm_area_struct *vma, + vm_flags_t flags) +{ + vma_start_write(vma); + vma_flags_set_word(&vma->flags, flags); +} + +static inline void vm_flags_clear(struct vm_area_struct *vma, + vm_flags_t flags) +{ + vma_start_write(vma); + vma_flags_clear_word(&vma->flags, flags); +} + +static inline vma_flags_t __mk_vma_flags(size_t count, const vma_flag_t *bits); + +#define mk_vma_flags(...) __mk_vma_flags(COUNT_ARGS(__VA_ARGS__), \ + (const vma_flag_t []){__VA_ARGS__}) + +static __always_inline bool vma_flags_test_mask(const vma_flags_t *flags, + vma_flags_t to_test) +{ + const unsigned long *bitmap = flags->__vma_flags; + const unsigned long *bitmap_to_test = to_test.__vma_flags; + + return bitmap_intersects(bitmap_to_test, bitmap, NUM_VMA_FLAG_BITS); +} + +#define vma_flags_test(flags, ...) \ + vma_flags_test_mask(flags, mk_vma_flags(__VA_ARGS__)) + +static __always_inline bool vma_flags_test_all_mask(const vma_flags_t *flags, + vma_flags_t to_test) +{ + const unsigned long *bitmap = flags->__vma_flags; + const unsigned long *bitmap_to_test = to_test.__vma_flags; + + return bitmap_subset(bitmap_to_test, bitmap, NUM_VMA_FLAG_BITS); +} + +#define vma_flags_test_all(flags, ...) \ + vma_flags_test_all_mask(flags, mk_vma_flags(__VA_ARGS__)) + +static __always_inline void vma_flags_set_mask(vma_flags_t *flags, vma_flags_t to_set) +{ + unsigned long *bitmap = flags->__vma_flags; + const unsigned long *bitmap_to_set = to_set.__vma_flags; + + bitmap_or(bitmap, bitmap, bitmap_to_set, NUM_VMA_FLAG_BITS); +} + +#define vma_flags_set(flags, ...) \ + vma_flags_set_mask(flags, mk_vma_flags(__VA_ARGS__)) + +static __always_inline void vma_flags_clear_mask(vma_flags_t *flags, vma_flags_t to_clear) +{ + unsigned long *bitmap = flags->__vma_flags; + const unsigned long *bitmap_to_clear = to_clear.__vma_flags; + + bitmap_andnot(bitmap, bitmap, bitmap_to_clear, NUM_VMA_FLAG_BITS); +} + +#define vma_flags_clear(flags, ...) \ + vma_flags_clear_mask(flags, mk_vma_flags(__VA_ARGS__)) + +static inline bool vma_test_all_flags_mask(const struct vm_area_struct *vma, + vma_flags_t flags) +{ + return vma_flags_test_all_mask(&vma->flags, flags); +} + +#define vma_test_all_flags(vma, ...) \ + vma_test_all_flags_mask(vma, mk_vma_flags(__VA_ARGS__)) + +static inline bool is_shared_maywrite_vm_flags(vm_flags_t vm_flags) +{ + return (vm_flags & (VM_SHARED | VM_MAYWRITE)) == + (VM_SHARED | VM_MAYWRITE); +} + +static inline void vma_set_flags_mask(struct vm_area_struct *vma, + vma_flags_t flags) +{ + vma_flags_set_mask(&vma->flags, flags); +} + +#define vma_set_flags(vma, ...) \ + vma_set_flags_mask(vma, mk_vma_flags(__VA_ARGS__)) + +static inline bool vma_desc_test_flags_mask(const struct vm_area_desc *desc, + vma_flags_t flags) +{ + return vma_flags_test_mask(&desc->vma_flags, flags); +} + +#define vma_desc_test_flags(desc, ...) \ + vma_desc_test_flags_mask(desc, mk_vma_flags(__VA_ARGS__)) + +static inline void vma_desc_set_flags_mask(struct vm_area_desc *desc, + vma_flags_t flags) +{ + vma_flags_set_mask(&desc->vma_flags, flags); +} + +#define vma_desc_set_flags(desc, ...) \ + vma_desc_set_flags_mask(desc, mk_vma_flags(__VA_ARGS__)) + +static inline void vma_desc_clear_flags_mask(struct vm_area_desc *desc, + vma_flags_t flags) +{ + vma_flags_clear_mask(&desc->vma_flags, flags); +} + +#define vma_desc_clear_flags(desc, ...) \ + vma_desc_clear_flags_mask(desc, mk_vma_flags(__VA_ARGS__)) + +static inline bool is_shared_maywrite(const vma_flags_t *flags) +{ + return vma_flags_test_all(flags, VMA_SHARED_BIT, VMA_MAYWRITE_BIT); +} + +static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma) +{ + return is_shared_maywrite(&vma->flags); +} + +static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) +{ + /* + * Uses mas_find() to get the first VMA when the iterator starts. + * Calling mas_next() could skip the first entry. + */ + return mas_find(&vmi->mas, ULONG_MAX); +} + +/* + * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these + * assertions should be made either under mmap_write_lock or when the object + * has been isolated under mmap_write_lock, ensuring no competing writers. + */ +static inline void vma_assert_attached(struct vm_area_struct *vma) +{ + WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt)); +} + +static inline void vma_assert_detached(struct vm_area_struct *vma) +{ + WARN_ON_ONCE(refcount_read(&vma->vm_refcnt)); +} + +static inline void vma_assert_write_locked(struct vm_area_struct *); +static inline void vma_mark_attached(struct vm_area_struct *vma) +{ + vma_assert_write_locked(vma); + vma_assert_detached(vma); + refcount_set_release(&vma->vm_refcnt, 1); +} + +static inline void vma_mark_detached(struct vm_area_struct *vma) +{ + vma_assert_write_locked(vma); + vma_assert_attached(vma); + /* We are the only writer, so no need to use vma_refcount_put(). */ + if (unlikely(!refcount_dec_and_test(&vma->vm_refcnt))) { + /* + * Reader must have temporarily raised vm_refcnt but it will + * drop it without using the vma since vma is write-locked. + */ + } +} + +static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) +{ + memset(vma, 0, sizeof(*vma)); + vma->vm_mm = mm; + vma->vm_ops = &vma_dummy_vm_ops; + INIT_LIST_HEAD(&vma->anon_vma_chain); + vma->vm_lock_seq = UINT_MAX; +} + +/* + * These are defined in vma.h, but sadly vm_stat_account() is referenced by + * kernel/fork.c, so we have to these broadly available there, and temporarily + * define them here to resolve the dependency cycle. + */ +#define is_exec_mapping(flags) \ + ((flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC) + +#define is_stack_mapping(flags) \ + (((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK)) + +#define is_data_mapping(flags) \ + ((flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE) + +static inline void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, + long npages) +{ + WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages); + + if (is_exec_mapping(flags)) + mm->exec_vm += npages; + else if (is_stack_mapping(flags)) + mm->stack_vm += npages; + else if (is_data_mapping(flags)) + mm->data_vm += npages; +} + +#undef is_exec_mapping +#undef is_stack_mapping +#undef is_data_mapping + +static inline void vm_unacct_memory(long pages) +{ + vm_acct_memory(-pages); +} + +static inline void mapping_allow_writable(struct address_space *mapping) +{ + atomic_inc(&mapping->i_mmap_writable); +} + +static inline +struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) +{ + return mas_find(&vmi->mas, max - 1); +} + +static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, + unsigned long start, unsigned long end, gfp_t gfp) +{ + __mas_set_range(&vmi->mas, start, end - 1); + mas_store_gfp(&vmi->mas, NULL, gfp); + if (unlikely(mas_is_err(&vmi->mas))) + return -ENOMEM; + + return 0; +} + +static inline void vma_set_anonymous(struct vm_area_struct *vma) +{ + vma->vm_ops = NULL; +} + +/* Declared in vma.h. */ +static inline void set_vma_from_desc(struct vm_area_struct *vma, + struct vm_area_desc *desc); + +static inline int __compat_vma_mmap(const struct file_operations *f_op, + struct file *file, struct vm_area_struct *vma) +{ + struct vm_area_desc desc = { + .mm = vma->vm_mm, + .file = file, + .start = vma->vm_start, + .end = vma->vm_end, + + .pgoff = vma->vm_pgoff, + .vm_file = vma->vm_file, + .vm_flags = vma->vm_flags, + .page_prot = vma->vm_page_prot, + + .action.type = MMAP_NOTHING, /* Default */ + }; + int err; + + err = f_op->mmap_prepare(&desc); + if (err) + return err; + + mmap_action_prepare(&desc.action, &desc); + set_vma_from_desc(vma, &desc); + return mmap_action_complete(&desc.action, vma); +} + +static inline int compat_vma_mmap(struct file *file, + struct vm_area_struct *vma) +{ + return __compat_vma_mmap(file->f_op, file, vma); +} + + +static inline void vma_iter_init(struct vma_iterator *vmi, + struct mm_struct *mm, unsigned long addr) +{ + mas_init(&vmi->mas, &mm->mm_mt, addr); +} + +static inline unsigned long vma_pages(struct vm_area_struct *vma) +{ + return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; +} + +static inline void mmap_assert_locked(struct mm_struct *); +static inline struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, + unsigned long start_addr, + unsigned long end_addr) +{ + unsigned long index = start_addr; + + mmap_assert_locked(mm); + return mt_find(&mm->mm_mt, &index, end_addr - 1); +} + +static inline +struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) +{ + return mtree_load(&mm->mm_mt, addr); +} + +static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) +{ + return mas_prev(&vmi->mas, 0); +} + +static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr) +{ + mas_set(&vmi->mas, addr); +} + +static inline bool vma_is_anonymous(struct vm_area_struct *vma) +{ + return !vma->vm_ops; +} + +/* Defined in vma.h, so temporarily define here to avoid circular dependency. */ +#define vma_iter_load(vmi) \ + mas_walk(&(vmi)->mas) + +static inline struct vm_area_struct * +find_vma_prev(struct mm_struct *mm, unsigned long addr, + struct vm_area_struct **pprev) +{ + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, addr); + + vma = vma_iter_load(&vmi); + *pprev = vma_prev(&vmi); + if (!vma) + vma = vma_next(&vmi); + return vma; +} + +#undef vma_iter_load + +static inline void vma_iter_free(struct vma_iterator *vmi) +{ + mas_destroy(&vmi->mas); +} + +static inline +struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi) +{ + return mas_next_range(&vmi->mas, ULONG_MAX); +} + +bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); + +/* Update vma->vm_page_prot to reflect vma->vm_flags. */ +static inline void vma_set_page_prot(struct vm_area_struct *vma) +{ + vm_flags_t vm_flags = vma->vm_flags; + pgprot_t vm_page_prot; + + /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */ + vm_page_prot = pgprot_modify(vma->vm_page_prot, vm_get_page_prot(vm_flags)); + + if (vma_wants_writenotify(vma, vm_page_prot)) { + vm_flags &= ~VM_SHARED; + /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */ + vm_page_prot = pgprot_modify(vm_page_prot, vm_get_page_prot(vm_flags)); + } + /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */ + WRITE_ONCE(vma->vm_page_prot, vm_page_prot); +} + +static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_GROWSDOWN) + return stack_guard_gap; + + /* See reasoning around the VM_SHADOW_STACK definition */ + if (vma->vm_flags & VM_SHADOW_STACK) + return PAGE_SIZE; + + return 0; +} + +static inline unsigned long vm_start_gap(struct vm_area_struct *vma) +{ + unsigned long gap = stack_guard_start_gap(vma); + unsigned long vm_start = vma->vm_start; + + vm_start -= gap; + if (vm_start > vma->vm_start) + vm_start = 0; + return vm_start; +} + +static inline unsigned long vm_end_gap(struct vm_area_struct *vma) +{ + unsigned long vm_end = vma->vm_end; + + if (vma->vm_flags & VM_GROWSUP) { + vm_end += stack_guard_gap; + if (vm_end < vma->vm_end) + vm_end = -PAGE_SIZE; + } + return vm_end; +} + +static inline bool vma_is_accessible(struct vm_area_struct *vma) +{ + return vma->vm_flags & VM_ACCESS_FLAGS; +} + +static inline bool mlock_future_ok(const struct mm_struct *mm, + vm_flags_t vm_flags, unsigned long bytes) +{ + unsigned long locked_pages, limit_pages; + + if (!(vm_flags & VM_LOCKED) || capable(CAP_IPC_LOCK)) + return true; + + locked_pages = bytes >> PAGE_SHIFT; + locked_pages += mm->locked_vm; + + limit_pages = rlimit(RLIMIT_MEMLOCK); + limit_pages >>= PAGE_SHIFT; + + return locked_pages <= limit_pages; +} + +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) +{ + /* If MDWE is disabled, we have nothing to deny. */ + if (mm_flags_test(MMF_HAS_MDWE, current->mm)) + return false; + + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) + return true; + + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) + return true; + + return false; +} + +static inline int mapping_map_writable(struct address_space *mapping) +{ + return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? + 0 : -EPERM; +} + +/* Did the driver provide valid mmap hook configuration? */ +static inline bool can_mmap_file(struct file *file) +{ + bool has_mmap = file->f_op->mmap; + bool has_mmap_prepare = file->f_op->mmap_prepare; + + /* Hooks are mutually exclusive. */ + if (WARN_ON_ONCE(has_mmap && has_mmap_prepare)) + return false; + if (!has_mmap && !has_mmap_prepare) + return false; + + return true; +} + +static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma) +{ + if (file->f_op->mmap_prepare) + return compat_vma_mmap(file, vma); + + return file->f_op->mmap(file, vma); +} + +static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc) +{ + return file->f_op->mmap_prepare(desc); +} + +static inline void vma_set_file(struct vm_area_struct *vma, struct file *file) +{ + /* Changing an anonymous vma with this is illegal */ + get_file(file); + swap(vma->vm_file, file); + fput(file); +} diff --git a/tools/testing/vma/include/stubs.h b/tools/testing/vma/include/stubs.h new file mode 100644 index 000000000000..947a3a0c2566 --- /dev/null +++ b/tools/testing/vma/include/stubs.h @@ -0,0 +1,428 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#pragma once + +/* + * Contains declarations that are STUBBED, that is that are rendered no-ops, in + * order to faciliate userland VMA testing. + */ + +/* Forward declarations. */ +struct mm_struct; +struct vm_area_struct; +struct vm_area_desc; +struct pagetable_move_control; +struct mmap_action; +struct file; +struct anon_vma; +struct anon_vma_chain; +struct address_space; +struct unmap_desc; + +#define __bitwise +#define __randomize_layout + +#define FIRST_USER_ADDRESS 0UL +#define USER_PGTABLES_CEILING 0UL + +#define vma_policy(vma) NULL + +#define down_write_nest_lock(sem, nest_lock) + +#define data_race(expr) expr + +#define ASSERT_EXCLUSIVE_WRITER(x) + +struct vm_userfaultfd_ctx {}; +struct mempolicy {}; +struct mmu_gather {}; +struct mutex {}; +struct vm_fault {}; + +static inline void userfaultfd_unmap_complete(struct mm_struct *mm, + struct list_head *uf) +{ +} + +static inline unsigned long move_page_tables(struct pagetable_move_control *pmc) +{ + return 0; +} + +static inline void free_pgd_range(struct mmu_gather *tlb, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ +} + +static inline int ksm_execve(struct mm_struct *mm) +{ + return 0; +} + +static inline void ksm_exit(struct mm_struct *mm) +{ +} + +static inline void vma_numab_state_init(struct vm_area_struct *vma) +{ +} + +static inline void vma_numab_state_free(struct vm_area_struct *vma) +{ +} + +static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) +{ +} + +static inline void free_anon_vma_name(struct vm_area_struct *vma) +{ +} + +static inline void mmap_action_prepare(struct mmap_action *action, + struct vm_area_desc *desc) +{ +} + +static inline int mmap_action_complete(struct mmap_action *action, + struct vm_area_struct *vma) +{ + return 0; +} + +static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ +} + +static inline bool shmem_file(struct file *file) +{ + return false; +} + +static inline vm_flags_t ksm_vma_flags(const struct mm_struct *mm, + const struct file *file, vm_flags_t vm_flags) +{ + return vm_flags; +} + +static inline void remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long pfn) +{ +} + +static inline int remap_pfn_range_complete(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t pgprot) +{ + return 0; +} + +static inline int do_munmap(struct mm_struct *, unsigned long, size_t, + struct list_head *uf) +{ + return 0; +} + +/* Currently stubbed but we may later wish to un-stub. */ +static inline void vm_acct_memory(long pages); + +static inline void mmap_assert_locked(struct mm_struct *mm) +{ +} + + +static inline void anon_vma_unlock_write(struct anon_vma *anon_vma) +{ +} + +static inline void i_mmap_unlock_write(struct address_space *mapping) +{ +} + +static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + struct list_head *unmaps) +{ + return 0; +} + +static inline void mmap_write_downgrade(struct mm_struct *mm) +{ +} + +static inline void mmap_read_unlock(struct mm_struct *mm) +{ +} + +static inline void mmap_write_unlock(struct mm_struct *mm) +{ +} + +static inline int mmap_write_lock_killable(struct mm_struct *mm) +{ + return 0; +} + +static inline bool can_modify_mm(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + return true; +} + +static inline void arch_unmap(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ +} + +static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) +{ + return true; +} + +static inline void khugepaged_enter_vma(struct vm_area_struct *vma, + vm_flags_t vm_flags) +{ +} + +static inline bool mapping_can_writeback(struct address_space *mapping) +{ + return true; +} + +static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma) +{ + return false; +} + +static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) +{ + return false; +} + +static inline bool userfaultfd_wp(struct vm_area_struct *vma) +{ + return false; +} + +static inline void mmap_assert_write_locked(struct mm_struct *mm) +{ +} + +static inline void mutex_lock(struct mutex *lock) +{ +} + +static inline void mutex_unlock(struct mutex *lock) +{ +} + +static inline bool mutex_is_locked(struct mutex *lock) +{ + return true; +} + +static inline bool signal_pending(void *p) +{ + return false; +} + +static inline bool is_file_hugepages(struct file *file) +{ + return false; +} + +static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) +{ + return 0; +} + +static inline bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, + unsigned long npages) +{ + return true; +} + +static inline int shmem_zero_setup(struct vm_area_struct *vma) +{ + return 0; +} + + +static inline void vm_acct_memory(long pages) +{ +} + +static inline void vma_interval_tree_insert(struct vm_area_struct *vma, + struct rb_root_cached *rb) +{ +} + +static inline void vma_interval_tree_remove(struct vm_area_struct *vma, + struct rb_root_cached *rb) +{ +} + +static inline void flush_dcache_mmap_unlock(struct address_space *mapping) +{ +} + +static inline void anon_vma_interval_tree_insert(struct anon_vma_chain *avc, + struct rb_root_cached *rb) +{ +} + +static inline void anon_vma_interval_tree_remove(struct anon_vma_chain *avc, + struct rb_root_cached *rb) +{ +} + +static inline void uprobe_mmap(struct vm_area_struct *vma) +{ +} + +static inline void uprobe_munmap(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ +} + +static inline void i_mmap_lock_write(struct address_space *mapping) +{ +} + +static inline void anon_vma_lock_write(struct anon_vma *anon_vma) +{ +} + +static inline void vma_assert_write_locked(struct vm_area_struct *vma) +{ +} + +static inline void ksm_add_vma(struct vm_area_struct *vma) +{ +} + +static inline void perf_event_mmap(struct vm_area_struct *vma) +{ +} + +static inline bool vma_is_dax(struct vm_area_struct *vma) +{ + return false; +} + +static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm) +{ + return NULL; +} + +static inline bool arch_validate_flags(vm_flags_t flags) +{ + return true; +} + +static inline void vma_close(struct vm_area_struct *vma) +{ +} + +static inline int mmap_file(struct file *file, struct vm_area_struct *vma) +{ + return 0; +} + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, unsigned long len) +{ + return 0; +} + +static inline bool capable(int cap) +{ + return true; +} + +static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) +{ + return NULL; +} + +static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, + struct vm_userfaultfd_ctx vm_ctx) +{ + return true; +} + +static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, + struct anon_vma_name *anon_name2) +{ + return true; +} + +static inline void might_sleep(void) +{ +} + +static inline void fput(struct file *file) +{ +} + +static inline void mpol_put(struct mempolicy *pol) +{ +} + +static inline void lru_add_drain(void) +{ +} + +static inline void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm) +{ +} + +static inline void update_hiwater_rss(struct mm_struct *mm) +{ +} + +static inline void update_hiwater_vm(struct mm_struct *mm) +{ +} + +static inline void unmap_vmas(struct mmu_gather *tlb, struct unmap_desc *unmap) +{ +} + +static inline void free_pgtables(struct mmu_gather *tlb, struct unmap_desc *unmap) +{ +} + +static inline void mapping_unmap_writable(struct address_space *mapping) +{ +} + +static inline void flush_dcache_mmap_lock(struct address_space *mapping) +{ +} + +static inline void tlb_finish_mmu(struct mmu_gather *tlb) +{ +} + +static inline struct file *get_file(struct file *f) +{ + return f; +} + +static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) +{ + return 0; +} + +static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + struct vm_area_struct *next) +{ +} + +static inline void hugetlb_split(struct vm_area_struct *, unsigned long) {} diff --git a/tools/testing/vma/main.c b/tools/testing/vma/main.c new file mode 100644 index 000000000000..49b09e97a51f --- /dev/null +++ b/tools/testing/vma/main.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include "shared.h" +/* + * Directly import the VMA implementation here. Our vma_internal.h wrapper + * provides userland-equivalent functionality for everything vma.c uses. + */ +#include "../../../mm/vma_init.c" +#include "../../../mm/vma_exec.c" +#include "../../../mm/vma.c" + +/* Tests are included directly so they can test static functions in mm/vma.c. */ +#include "tests/merge.c" +#include "tests/mmap.c" +#include "tests/vma.c" + +/* Helper functions which utilise static kernel functions. */ + +struct vm_area_struct *merge_existing(struct vma_merge_struct *vmg) +{ + struct vm_area_struct *vma; + + vma = vma_merge_existing_range(vmg); + if (vma) + vma_assert_attached(vma); + return vma; +} + +int attach_vma(struct mm_struct *mm, struct vm_area_struct *vma) +{ + int res; + + res = vma_link(mm, vma); + if (!res) + vma_assert_attached(vma); + return res; +} + +/* Main test running which invokes tests/ *.c runners. */ +int main(void) +{ + int num_tests = 0, num_fail = 0; + + maple_tree_init(); + vma_state_init(); + + run_merge_tests(&num_tests, &num_fail); + run_mmap_tests(&num_tests, &num_fail); + run_vma_tests(&num_tests, &num_fail); + + printf("%d tests run, %d passed, %d failed.\n", + num_tests, num_tests - num_fail, num_fail); + + return num_fail == 0 ? EXIT_SUCCESS : EXIT_FAILURE; +} diff --git a/tools/testing/vma/shared.c b/tools/testing/vma/shared.c new file mode 100644 index 000000000000..bda578cc3304 --- /dev/null +++ b/tools/testing/vma/shared.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include "shared.h" + + +bool fail_prealloc; +unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; +unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; +unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT; + +const struct vm_operations_struct vma_dummy_vm_ops; +struct anon_vma dummy_anon_vma; +struct task_struct __current; + +struct vm_area_struct *alloc_vma(struct mm_struct *mm, + unsigned long start, unsigned long end, + pgoff_t pgoff, vm_flags_t vm_flags) +{ + struct vm_area_struct *vma = vm_area_alloc(mm); + + if (vma == NULL) + return NULL; + + vma->vm_start = start; + vma->vm_end = end; + vma->vm_pgoff = pgoff; + vm_flags_reset(vma, vm_flags); + vma_assert_detached(vma); + + return vma; +} + +void detach_free_vma(struct vm_area_struct *vma) +{ + vma_mark_detached(vma); + vm_area_free(vma); +} + +struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm, + unsigned long start, unsigned long end, + pgoff_t pgoff, vm_flags_t vm_flags) +{ + struct vm_area_struct *vma = alloc_vma(mm, start, end, pgoff, vm_flags); + + if (vma == NULL) + return NULL; + + if (attach_vma(mm, vma)) { + detach_free_vma(vma); + return NULL; + } + + /* + * Reset this counter which we use to track whether writes have + * begun. Linking to the tree will have caused this to be incremented, + * which means we will get a false positive otherwise. + */ + vma->vm_lock_seq = UINT_MAX; + + return vma; +} + +void reset_dummy_anon_vma(void) +{ + dummy_anon_vma.was_cloned = false; + dummy_anon_vma.was_unlinked = false; +} + +int cleanup_mm(struct mm_struct *mm, struct vma_iterator *vmi) +{ + struct vm_area_struct *vma; + int count = 0; + + fail_prealloc = false; + reset_dummy_anon_vma(); + + vma_iter_set(vmi, 0); + for_each_vma(*vmi, vma) { + detach_free_vma(vma); + count++; + } + + mtree_destroy(&mm->mm_mt); + mm->map_count = 0; + return count; +} + +bool vma_write_started(struct vm_area_struct *vma) +{ + int seq = vma->vm_lock_seq; + + /* We reset after each check. */ + vma->vm_lock_seq = UINT_MAX; + + /* The vma_start_write() stub simply increments this value. */ + return seq > -1; +} + +void __vma_set_dummy_anon_vma(struct vm_area_struct *vma, + struct anon_vma_chain *avc, struct anon_vma *anon_vma) +{ + vma->anon_vma = anon_vma; + INIT_LIST_HEAD(&vma->anon_vma_chain); + list_add(&avc->same_vma, &vma->anon_vma_chain); + avc->anon_vma = vma->anon_vma; +} + +void vma_set_dummy_anon_vma(struct vm_area_struct *vma, + struct anon_vma_chain *avc) +{ + __vma_set_dummy_anon_vma(vma, avc, &dummy_anon_vma); +} + +struct task_struct *get_current(void) +{ + return &__current; +} + +unsigned long rlimit(unsigned int limit) +{ + return (unsigned long)-1; +} + +void vma_set_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + pgoff_t pgoff) +{ + vma->vm_start = start; + vma->vm_end = end; + vma->vm_pgoff = pgoff; +} diff --git a/tools/testing/vma/shared.h b/tools/testing/vma/shared.h new file mode 100644 index 000000000000..6c64211cfa22 --- /dev/null +++ b/tools/testing/vma/shared.h @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#pragma once + +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> + +#include "generated/bit-length.h" +#include "maple-shared.h" +#include "vma_internal.h" +#include "../../../mm/vma.h" + +/* Simple test runner. Assumes local num_[fail, tests] counters. */ +#define TEST(name) \ + do { \ + (*num_tests)++; \ + if (!test_##name()) { \ + (*num_fail)++; \ + fprintf(stderr, "Test " #name " FAILED\n"); \ + } \ + } while (0) + +#define ASSERT_TRUE(_expr) \ + do { \ + if (!(_expr)) { \ + fprintf(stderr, \ + "Assert FAILED at %s:%d:%s(): %s is FALSE.\n", \ + __FILE__, __LINE__, __FUNCTION__, #_expr); \ + return false; \ + } \ + } while (0) + +#define ASSERT_FALSE(_expr) ASSERT_TRUE(!(_expr)) +#define ASSERT_EQ(_val1, _val2) ASSERT_TRUE((_val1) == (_val2)) +#define ASSERT_NE(_val1, _val2) ASSERT_TRUE((_val1) != (_val2)) + +#define IS_SET(_val, _flags) ((_val & _flags) == _flags) + +extern bool fail_prealloc; + +/* Override vma_iter_prealloc() so we can choose to fail it. */ +#define vma_iter_prealloc(vmi, vma) \ + (fail_prealloc ? -ENOMEM : mas_preallocate(&(vmi)->mas, (vma), GFP_KERNEL)) + +#define CONFIG_DEFAULT_MMAP_MIN_ADDR 65536 + +extern unsigned long mmap_min_addr; +extern unsigned long dac_mmap_min_addr; +extern unsigned long stack_guard_gap; + +extern const struct vm_operations_struct vma_dummy_vm_ops; +extern struct anon_vma dummy_anon_vma; +extern struct task_struct __current; + +/* + * Helper function which provides a wrapper around a merge existing VMA + * operation. + * + * Declared in main.c as uses static VMA function. + */ +struct vm_area_struct *merge_existing(struct vma_merge_struct *vmg); + +/* + * Helper function to allocate a VMA and link it to the tree. + * + * Declared in main.c as uses static VMA function. + */ +int attach_vma(struct mm_struct *mm, struct vm_area_struct *vma); + +/* Helper function providing a dummy vm_ops->close() method.*/ +static inline void dummy_close(struct vm_area_struct *) +{ +} + +/* Helper function to simply allocate a VMA. */ +struct vm_area_struct *alloc_vma(struct mm_struct *mm, + unsigned long start, unsigned long end, + pgoff_t pgoff, vm_flags_t vm_flags); + +/* Helper function to detach and free a VMA. */ +void detach_free_vma(struct vm_area_struct *vma); + +/* Helper function to allocate a VMA and link it to the tree. */ +struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm, + unsigned long start, unsigned long end, + pgoff_t pgoff, vm_flags_t vm_flags); + +/* + * Helper function to reset the dummy anon_vma to indicate it has not been + * duplicated. + */ +void reset_dummy_anon_vma(void); + +/* + * Helper function to remove all VMAs and destroy the maple tree associated with + * a virtual address space. Returns a count of VMAs in the tree. + */ +int cleanup_mm(struct mm_struct *mm, struct vma_iterator *vmi); + +/* Helper function to determine if VMA has had vma_start_write() performed. */ +bool vma_write_started(struct vm_area_struct *vma); + +void __vma_set_dummy_anon_vma(struct vm_area_struct *vma, + struct anon_vma_chain *avc, struct anon_vma *anon_vma); + +/* Provide a simple dummy VMA/anon_vma dummy setup for testing. */ +void vma_set_dummy_anon_vma(struct vm_area_struct *vma, + struct anon_vma_chain *avc); + +/* Helper function to specify a VMA's range. */ +void vma_set_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + pgoff_t pgoff); diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/tests/merge.c index 93d21bc7e112..3708dc6945b0 100644 --- a/tools/testing/vma/vma.c +++ b/tools/testing/vma/tests/merge.c @@ -1,132 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -#include <stdbool.h> -#include <stdio.h> -#include <stdlib.h> - -#include "generated/bit-length.h" - -#include "maple-shared.h" -#include "vma_internal.h" - -/* Include so header guard set. */ -#include "../../../mm/vma.h" - -static bool fail_prealloc; - -/* Then override vma_iter_prealloc() so we can choose to fail it. */ -#define vma_iter_prealloc(vmi, vma) \ - (fail_prealloc ? -ENOMEM : mas_preallocate(&(vmi)->mas, (vma), GFP_KERNEL)) - -#define CONFIG_DEFAULT_MMAP_MIN_ADDR 65536 - -unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; -unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; -unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT; - -/* - * Directly import the VMA implementation here. Our vma_internal.h wrapper - * provides userland-equivalent functionality for everything vma.c uses. - */ -#include "../../../mm/vma_init.c" -#include "../../../mm/vma_exec.c" -#include "../../../mm/vma.c" - -const struct vm_operations_struct vma_dummy_vm_ops; -static struct anon_vma dummy_anon_vma; - -#define ASSERT_TRUE(_expr) \ - do { \ - if (!(_expr)) { \ - fprintf(stderr, \ - "Assert FAILED at %s:%d:%s(): %s is FALSE.\n", \ - __FILE__, __LINE__, __FUNCTION__, #_expr); \ - return false; \ - } \ - } while (0) -#define ASSERT_FALSE(_expr) ASSERT_TRUE(!(_expr)) -#define ASSERT_EQ(_val1, _val2) ASSERT_TRUE((_val1) == (_val2)) -#define ASSERT_NE(_val1, _val2) ASSERT_TRUE((_val1) != (_val2)) - -#define IS_SET(_val, _flags) ((_val & _flags) == _flags) - -static struct task_struct __current; - -struct task_struct *get_current(void) -{ - return &__current; -} - -unsigned long rlimit(unsigned int limit) -{ - return (unsigned long)-1; -} - -/* Helper function to simply allocate a VMA. */ -static struct vm_area_struct *alloc_vma(struct mm_struct *mm, - unsigned long start, - unsigned long end, - pgoff_t pgoff, - vm_flags_t vm_flags) -{ - struct vm_area_struct *vma = vm_area_alloc(mm); - - if (vma == NULL) - return NULL; - - vma->vm_start = start; - vma->vm_end = end; - vma->vm_pgoff = pgoff; - vm_flags_reset(vma, vm_flags); - vma_assert_detached(vma); - - return vma; -} - -/* Helper function to allocate a VMA and link it to the tree. */ -static int attach_vma(struct mm_struct *mm, struct vm_area_struct *vma) -{ - int res; - - res = vma_link(mm, vma); - if (!res) - vma_assert_attached(vma); - return res; -} - -static void detach_free_vma(struct vm_area_struct *vma) -{ - vma_mark_detached(vma); - vm_area_free(vma); -} - -/* Helper function to allocate a VMA and link it to the tree. */ -static struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm, - unsigned long start, - unsigned long end, - pgoff_t pgoff, - vm_flags_t vm_flags) -{ - struct vm_area_struct *vma = alloc_vma(mm, start, end, pgoff, vm_flags); - - if (vma == NULL) - return NULL; - - if (attach_vma(mm, vma)) { - detach_free_vma(vma); - return NULL; - } - - /* - * Reset this counter which we use to track whether writes have - * begun. Linking to the tree will have caused this to be incremented, - * which means we will get a false positive otherwise. - */ - vma->vm_lock_seq = UINT_MAX; - - return vma; -} - /* Helper function which provides a wrapper around a merge new VMA operation. */ static struct vm_area_struct *merge_new(struct vma_merge_struct *vmg) { @@ -147,20 +20,6 @@ static struct vm_area_struct *merge_new(struct vma_merge_struct *vmg) } /* - * Helper function which provides a wrapper around a merge existing VMA - * operation. - */ -static struct vm_area_struct *merge_existing(struct vma_merge_struct *vmg) -{ - struct vm_area_struct *vma; - - vma = vma_merge_existing_range(vmg); - if (vma) - vma_assert_attached(vma); - return vma; -} - -/* * Helper function which provides a wrapper around the expansion of an existing * VMA. */ @@ -173,8 +32,8 @@ static int expand_existing(struct vma_merge_struct *vmg) * Helper function to reset merge state the associated VMA iterator to a * specified new range. */ -static void vmg_set_range(struct vma_merge_struct *vmg, unsigned long start, - unsigned long end, pgoff_t pgoff, vm_flags_t vm_flags) +void vmg_set_range(struct vma_merge_struct *vmg, unsigned long start, + unsigned long end, pgoff_t pgoff, vm_flags_t vm_flags) { vma_iter_set(vmg->vmi, start); @@ -197,8 +56,8 @@ static void vmg_set_range(struct vma_merge_struct *vmg, unsigned long start, /* Helper function to set both the VMG range and its anon_vma. */ static void vmg_set_range_anon_vma(struct vma_merge_struct *vmg, unsigned long start, - unsigned long end, pgoff_t pgoff, vm_flags_t vm_flags, - struct anon_vma *anon_vma) + unsigned long end, pgoff_t pgoff, vm_flags_t vm_flags, + struct anon_vma *anon_vma) { vmg_set_range(vmg, start, end, pgoff, vm_flags); vmg->anon_vma = anon_vma; @@ -211,10 +70,9 @@ static void vmg_set_range_anon_vma(struct vma_merge_struct *vmg, unsigned long s * VMA, link it to the maple tree and return it. */ static struct vm_area_struct *try_merge_new_vma(struct mm_struct *mm, - struct vma_merge_struct *vmg, - unsigned long start, unsigned long end, - pgoff_t pgoff, vm_flags_t vm_flags, - bool *was_merged) + struct vma_merge_struct *vmg, unsigned long start, + unsigned long end, pgoff_t pgoff, vm_flags_t vm_flags, + bool *was_merged) { struct vm_area_struct *merged; @@ -234,72 +92,6 @@ static struct vm_area_struct *try_merge_new_vma(struct mm_struct *mm, return alloc_and_link_vma(mm, start, end, pgoff, vm_flags); } -/* - * Helper function to reset the dummy anon_vma to indicate it has not been - * duplicated. - */ -static void reset_dummy_anon_vma(void) -{ - dummy_anon_vma.was_cloned = false; - dummy_anon_vma.was_unlinked = false; -} - -/* - * Helper function to remove all VMAs and destroy the maple tree associated with - * a virtual address space. Returns a count of VMAs in the tree. - */ -static int cleanup_mm(struct mm_struct *mm, struct vma_iterator *vmi) -{ - struct vm_area_struct *vma; - int count = 0; - - fail_prealloc = false; - reset_dummy_anon_vma(); - - vma_iter_set(vmi, 0); - for_each_vma(*vmi, vma) { - detach_free_vma(vma); - count++; - } - - mtree_destroy(&mm->mm_mt); - mm->map_count = 0; - return count; -} - -/* Helper function to determine if VMA has had vma_start_write() performed. */ -static bool vma_write_started(struct vm_area_struct *vma) -{ - int seq = vma->vm_lock_seq; - - /* We reset after each check. */ - vma->vm_lock_seq = UINT_MAX; - - /* The vma_start_write() stub simply increments this value. */ - return seq > -1; -} - -/* Helper function providing a dummy vm_ops->close() method.*/ -static void dummy_close(struct vm_area_struct *) -{ -} - -static void __vma_set_dummy_anon_vma(struct vm_area_struct *vma, - struct anon_vma_chain *avc, - struct anon_vma *anon_vma) -{ - vma->anon_vma = anon_vma; - INIT_LIST_HEAD(&vma->anon_vma_chain); - list_add(&avc->same_vma, &vma->anon_vma_chain); - avc->anon_vma = vma->anon_vma; -} - -static void vma_set_dummy_anon_vma(struct vm_area_struct *vma, - struct anon_vma_chain *avc) -{ - __vma_set_dummy_anon_vma(vma, avc, &dummy_anon_vma); -} - static bool test_simple_merge(void) { struct vm_area_struct *vma; @@ -1616,39 +1408,6 @@ static bool test_merge_extend(void) return true; } -static bool test_copy_vma(void) -{ - vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE; - struct mm_struct mm = {}; - bool need_locks = false; - VMA_ITERATOR(vmi, &mm, 0); - struct vm_area_struct *vma, *vma_new, *vma_next; - - /* Move backwards and do not merge. */ - - vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags); - vma_new = copy_vma(&vma, 0, 0x2000, 0, &need_locks); - ASSERT_NE(vma_new, vma); - ASSERT_EQ(vma_new->vm_start, 0); - ASSERT_EQ(vma_new->vm_end, 0x2000); - ASSERT_EQ(vma_new->vm_pgoff, 0); - vma_assert_attached(vma_new); - - cleanup_mm(&mm, &vmi); - - /* Move a VMA into position next to another and merge the two. */ - - vma = alloc_and_link_vma(&mm, 0, 0x2000, 0, vm_flags); - vma_next = alloc_and_link_vma(&mm, 0x6000, 0x8000, 6, vm_flags); - vma_new = copy_vma(&vma, 0x4000, 0x2000, 4, &need_locks); - vma_assert_attached(vma_new); - - ASSERT_EQ(vma_new, vma_next); - - cleanup_mm(&mm, &vmi); - return true; -} - static bool test_expand_only_mode(void) { vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE; @@ -1689,73 +1448,8 @@ static bool test_expand_only_mode(void) return true; } -static bool test_mmap_region_basic(void) -{ - struct mm_struct mm = {}; - unsigned long addr; - struct vm_area_struct *vma; - VMA_ITERATOR(vmi, &mm, 0); - - current->mm = &mm; - - /* Map at 0x300000, length 0x3000. */ - addr = __mmap_region(NULL, 0x300000, 0x3000, - VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, - 0x300, NULL); - ASSERT_EQ(addr, 0x300000); - - /* Map at 0x250000, length 0x3000. */ - addr = __mmap_region(NULL, 0x250000, 0x3000, - VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, - 0x250, NULL); - ASSERT_EQ(addr, 0x250000); - - /* Map at 0x303000, merging to 0x300000 of length 0x6000. */ - addr = __mmap_region(NULL, 0x303000, 0x3000, - VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, - 0x303, NULL); - ASSERT_EQ(addr, 0x303000); - - /* Map at 0x24d000, merging to 0x250000 of length 0x6000. */ - addr = __mmap_region(NULL, 0x24d000, 0x3000, - VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, - 0x24d, NULL); - ASSERT_EQ(addr, 0x24d000); - - ASSERT_EQ(mm.map_count, 2); - - for_each_vma(vmi, vma) { - if (vma->vm_start == 0x300000) { - ASSERT_EQ(vma->vm_end, 0x306000); - ASSERT_EQ(vma->vm_pgoff, 0x300); - } else if (vma->vm_start == 0x24d000) { - ASSERT_EQ(vma->vm_end, 0x253000); - ASSERT_EQ(vma->vm_pgoff, 0x24d); - } else { - ASSERT_FALSE(true); - } - } - - cleanup_mm(&mm, &vmi); - return true; -} - -int main(void) +static void run_merge_tests(int *num_tests, int *num_fail) { - int num_tests = 0, num_fail = 0; - - maple_tree_init(); - vma_state_init(); - -#define TEST(name) \ - do { \ - num_tests++; \ - if (!test_##name()) { \ - num_fail++; \ - fprintf(stderr, "Test " #name " FAILED\n"); \ - } \ - } while (0) - /* Very simple tests to kick the tyres. */ TEST(simple_merge); TEST(simple_modify); @@ -1771,15 +1465,5 @@ int main(void) TEST(dup_anon_vma); TEST(vmi_prealloc_fail); TEST(merge_extend); - TEST(copy_vma); TEST(expand_only_mode); - - TEST(mmap_region_basic); - -#undef TEST - - printf("%d tests run, %d passed, %d failed.\n", - num_tests, num_tests - num_fail, num_fail); - - return num_fail == 0 ? EXIT_SUCCESS : EXIT_FAILURE; } diff --git a/tools/testing/vma/tests/mmap.c b/tools/testing/vma/tests/mmap.c new file mode 100644 index 000000000000..bded4ecbe5db --- /dev/null +++ b/tools/testing/vma/tests/mmap.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +static bool test_mmap_region_basic(void) +{ + struct mm_struct mm = {}; + unsigned long addr; + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, &mm, 0); + + current->mm = &mm; + + /* Map at 0x300000, length 0x3000. */ + addr = __mmap_region(NULL, 0x300000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x300, NULL); + ASSERT_EQ(addr, 0x300000); + + /* Map at 0x250000, length 0x3000. */ + addr = __mmap_region(NULL, 0x250000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x250, NULL); + ASSERT_EQ(addr, 0x250000); + + /* Map at 0x303000, merging to 0x300000 of length 0x6000. */ + addr = __mmap_region(NULL, 0x303000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x303, NULL); + ASSERT_EQ(addr, 0x303000); + + /* Map at 0x24d000, merging to 0x250000 of length 0x6000. */ + addr = __mmap_region(NULL, 0x24d000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x24d, NULL); + ASSERT_EQ(addr, 0x24d000); + + ASSERT_EQ(mm.map_count, 2); + + for_each_vma(vmi, vma) { + if (vma->vm_start == 0x300000) { + ASSERT_EQ(vma->vm_end, 0x306000); + ASSERT_EQ(vma->vm_pgoff, 0x300); + } else if (vma->vm_start == 0x24d000) { + ASSERT_EQ(vma->vm_end, 0x253000); + ASSERT_EQ(vma->vm_pgoff, 0x24d); + } else { + ASSERT_FALSE(true); + } + } + + cleanup_mm(&mm, &vmi); + return true; +} + +static void run_mmap_tests(int *num_tests, int *num_fail) +{ + TEST(mmap_region_basic); +} diff --git a/tools/testing/vma/tests/vma.c b/tools/testing/vma/tests/vma.c new file mode 100644 index 000000000000..c54ffc954f11 --- /dev/null +++ b/tools/testing/vma/tests/vma.c @@ -0,0 +1,339 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +static bool compare_legacy_flags(vm_flags_t legacy_flags, vma_flags_t flags) +{ + const unsigned long legacy_val = legacy_flags; + /* The lower word should contain the precise same value. */ + const unsigned long flags_lower = flags.__vma_flags[0]; +#if NUM_VMA_FLAGS > BITS_PER_LONG + int i; + + /* All bits in higher flag values should be zero. */ + for (i = 1; i < NUM_VMA_FLAGS / BITS_PER_LONG; i++) { + if (flags.__vma_flags[i] != 0) + return false; + } +#endif + + static_assert(sizeof(legacy_flags) == sizeof(unsigned long)); + + return legacy_val == flags_lower; +} + +static bool test_copy_vma(void) +{ + vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE; + struct mm_struct mm = {}; + bool need_locks = false; + VMA_ITERATOR(vmi, &mm, 0); + struct vm_area_struct *vma, *vma_new, *vma_next; + + /* Move backwards and do not merge. */ + + vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags); + vma_new = copy_vma(&vma, 0, 0x2000, 0, &need_locks); + ASSERT_NE(vma_new, vma); + ASSERT_EQ(vma_new->vm_start, 0); + ASSERT_EQ(vma_new->vm_end, 0x2000); + ASSERT_EQ(vma_new->vm_pgoff, 0); + vma_assert_attached(vma_new); + + cleanup_mm(&mm, &vmi); + + /* Move a VMA into position next to another and merge the two. */ + + vma = alloc_and_link_vma(&mm, 0, 0x2000, 0, vm_flags); + vma_next = alloc_and_link_vma(&mm, 0x6000, 0x8000, 6, vm_flags); + vma_new = copy_vma(&vma, 0x4000, 0x2000, 4, &need_locks); + vma_assert_attached(vma_new); + + ASSERT_EQ(vma_new, vma_next); + + cleanup_mm(&mm, &vmi); + return true; +} + +static bool test_vma_flags_unchanged(void) +{ + vma_flags_t flags = EMPTY_VMA_FLAGS; + vm_flags_t legacy_flags = 0; + int bit; + struct vm_area_struct vma; + struct vm_area_desc desc; + + + vma.flags = EMPTY_VMA_FLAGS; + desc.vma_flags = EMPTY_VMA_FLAGS; + + for (bit = 0; bit < BITS_PER_LONG; bit++) { + vma_flags_t mask = mk_vma_flags(bit); + + legacy_flags |= (1UL << bit); + + /* Individual flags. */ + vma_flags_set(&flags, bit); + ASSERT_TRUE(compare_legacy_flags(legacy_flags, flags)); + + /* Via mask. */ + vma_flags_set_mask(&flags, mask); + ASSERT_TRUE(compare_legacy_flags(legacy_flags, flags)); + + /* Same for VMA. */ + vma_set_flags(&vma, bit); + ASSERT_TRUE(compare_legacy_flags(legacy_flags, vma.flags)); + vma_set_flags_mask(&vma, mask); + ASSERT_TRUE(compare_legacy_flags(legacy_flags, vma.flags)); + + /* Same for VMA descriptor. */ + vma_desc_set_flags(&desc, bit); + ASSERT_TRUE(compare_legacy_flags(legacy_flags, desc.vma_flags)); + vma_desc_set_flags_mask(&desc, mask); + ASSERT_TRUE(compare_legacy_flags(legacy_flags, desc.vma_flags)); + } + + return true; +} + +static bool test_vma_flags_cleared(void) +{ + const vma_flags_t empty = EMPTY_VMA_FLAGS; + vma_flags_t flags; + int i; + + /* Set all bits high. */ + memset(&flags, 1, sizeof(flags)); + /* Try to clear. */ + vma_flags_clear_all(&flags); + /* Equal to EMPTY_VMA_FLAGS? */ + ASSERT_EQ(memcmp(&empty, &flags, sizeof(flags)), 0); + /* Make sure every unsigned long entry in bitmap array zero. */ + for (i = 0; i < sizeof(flags) / BITS_PER_LONG; i++) { + const unsigned long val = flags.__vma_flags[i]; + + ASSERT_EQ(val, 0); + } + + return true; +} + +/* + * Assert that VMA flag functions that operate at the system word level function + * correctly. + */ +static bool test_vma_flags_word(void) +{ + vma_flags_t flags = EMPTY_VMA_FLAGS; + const vma_flags_t comparison = + mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT, 64, 65); + + /* Set some custom high flags. */ + vma_flags_set(&flags, 64, 65); + /* Now overwrite the first word. */ + vma_flags_overwrite_word(&flags, VM_READ | VM_WRITE); + /* Ensure they are equal. */ + ASSERT_EQ(memcmp(&flags, &comparison, sizeof(flags)), 0); + + flags = EMPTY_VMA_FLAGS; + vma_flags_set(&flags, 64, 65); + + /* Do the same with the _once() equivalent. */ + vma_flags_overwrite_word_once(&flags, VM_READ | VM_WRITE); + ASSERT_EQ(memcmp(&flags, &comparison, sizeof(flags)), 0); + + flags = EMPTY_VMA_FLAGS; + vma_flags_set(&flags, 64, 65); + + /* Make sure we can set a word without disturbing other bits. */ + vma_flags_set(&flags, VMA_WRITE_BIT); + vma_flags_set_word(&flags, VM_READ); + ASSERT_EQ(memcmp(&flags, &comparison, sizeof(flags)), 0); + + flags = EMPTY_VMA_FLAGS; + vma_flags_set(&flags, 64, 65); + + /* Make sure we can clear a word without disturbing other bits. */ + vma_flags_set(&flags, VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT); + vma_flags_clear_word(&flags, VM_EXEC); + ASSERT_EQ(memcmp(&flags, &comparison, sizeof(flags)), 0); + + return true; +} + +/* Ensure that vma_flags_test() and friends works correctly. */ +static bool test_vma_flags_test(void) +{ + const vma_flags_t flags = mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT, + VMA_EXEC_BIT, 64, 65); + struct vm_area_struct vma; + struct vm_area_desc desc; + + vma.flags = flags; + desc.vma_flags = flags; + +#define do_test(...) \ + ASSERT_TRUE(vma_flags_test(&flags, __VA_ARGS__)); \ + ASSERT_TRUE(vma_desc_test_flags(&desc, __VA_ARGS__)) + +#define do_test_all_true(...) \ + ASSERT_TRUE(vma_flags_test_all(&flags, __VA_ARGS__)); \ + ASSERT_TRUE(vma_test_all_flags(&vma, __VA_ARGS__)) + +#define do_test_all_false(...) \ + ASSERT_FALSE(vma_flags_test_all(&flags, __VA_ARGS__)); \ + ASSERT_FALSE(vma_test_all_flags(&vma, __VA_ARGS__)) + + /* + * Testing for some flags that are present, some that are not - should + * pass. ANY flags matching should work. + */ + do_test(VMA_READ_BIT, VMA_MAYREAD_BIT, VMA_SEQ_READ_BIT); + /* However, the ...test_all() variant should NOT pass. */ + do_test_all_false(VMA_READ_BIT, VMA_MAYREAD_BIT, VMA_SEQ_READ_BIT); + /* But should pass for flags present. */ + do_test_all_true(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT, 64, 65); + /* Also subsets... */ + do_test_all_true(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT, 64); + do_test_all_true(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT); + do_test_all_true(VMA_READ_BIT, VMA_WRITE_BIT); + do_test_all_true(VMA_READ_BIT); + /* + * Check _mask variant. We don't need to test extensively as macro + * helper is the equivalent. + */ + ASSERT_TRUE(vma_flags_test_mask(&flags, flags)); + ASSERT_TRUE(vma_flags_test_all_mask(&flags, flags)); + + /* Single bits. */ + do_test(VMA_READ_BIT); + do_test(VMA_WRITE_BIT); + do_test(VMA_EXEC_BIT); +#if NUM_VMA_FLAG_BITS > 64 + do_test(64); + do_test(65); +#endif + + /* Two bits. */ + do_test(VMA_READ_BIT, VMA_WRITE_BIT); + do_test(VMA_READ_BIT, VMA_EXEC_BIT); + do_test(VMA_WRITE_BIT, VMA_EXEC_BIT); + /* Ordering shouldn't matter. */ + do_test(VMA_WRITE_BIT, VMA_READ_BIT); + do_test(VMA_EXEC_BIT, VMA_READ_BIT); + do_test(VMA_EXEC_BIT, VMA_WRITE_BIT); +#if NUM_VMA_FLAG_BITS > 64 + do_test(VMA_READ_BIT, 64); + do_test(VMA_WRITE_BIT, 64); + do_test(64, VMA_READ_BIT); + do_test(64, VMA_WRITE_BIT); + do_test(VMA_READ_BIT, 65); + do_test(VMA_WRITE_BIT, 65); + do_test(65, VMA_READ_BIT); + do_test(65, VMA_WRITE_BIT); +#endif + /* Three bits. */ + do_test(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT); +#if NUM_VMA_FLAG_BITS > 64 + /* No need to consider every single permutation. */ + do_test(VMA_READ_BIT, VMA_WRITE_BIT, 64); + do_test(VMA_READ_BIT, VMA_WRITE_BIT, 65); + + /* Four bits. */ + do_test(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT, 64); + do_test(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT, 65); + + /* Five bits. */ + do_test(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT, 64, 65); +#endif + +#undef do_test +#undef do_test_all_true +#undef do_test_all_false + + return true; +} + +/* Ensure that vma_flags_clear() and friends works correctly. */ +static bool test_vma_flags_clear(void) +{ + vma_flags_t flags = mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT, + VMA_EXEC_BIT, 64, 65); + vma_flags_t mask = mk_vma_flags(VMA_EXEC_BIT, 64); + struct vm_area_struct vma; + struct vm_area_desc desc; + + vma.flags = flags; + desc.vma_flags = flags; + + /* Cursory check of _mask() variant, as the helper macros imply. */ + vma_flags_clear_mask(&flags, mask); + vma_flags_clear_mask(&vma.flags, mask); + vma_desc_clear_flags_mask(&desc, mask); + ASSERT_FALSE(vma_flags_test(&flags, VMA_EXEC_BIT, 64)); + ASSERT_FALSE(vma_flags_test(&vma.flags, VMA_EXEC_BIT, 64)); + ASSERT_FALSE(vma_desc_test_flags(&desc, VMA_EXEC_BIT, 64)); + /* Reset. */ + vma_flags_set(&flags, VMA_EXEC_BIT, 64); + vma_set_flags(&vma, VMA_EXEC_BIT, 64); + vma_desc_set_flags(&desc, VMA_EXEC_BIT, 64); + + /* + * Clear the flags and assert clear worked, then reset flags back to + * include specified flags. + */ +#define do_test_and_reset(...) \ + vma_flags_clear(&flags, __VA_ARGS__); \ + vma_flags_clear(&vma.flags, __VA_ARGS__); \ + vma_desc_clear_flags(&desc, __VA_ARGS__); \ + ASSERT_FALSE(vma_flags_test(&flags, __VA_ARGS__)); \ + ASSERT_FALSE(vma_flags_test(&vma.flags, __VA_ARGS__)); \ + ASSERT_FALSE(vma_desc_test_flags(&desc, __VA_ARGS__)); \ + vma_flags_set(&flags, __VA_ARGS__); \ + vma_set_flags(&vma, __VA_ARGS__); \ + vma_desc_set_flags(&desc, __VA_ARGS__) + + /* Single flags. */ + do_test_and_reset(VMA_READ_BIT); + do_test_and_reset(VMA_WRITE_BIT); + do_test_and_reset(VMA_EXEC_BIT); + do_test_and_reset(64); + do_test_and_reset(65); + + /* Two flags, in different orders. */ + do_test_and_reset(VMA_READ_BIT, VMA_WRITE_BIT); + do_test_and_reset(VMA_READ_BIT, VMA_EXEC_BIT); + do_test_and_reset(VMA_READ_BIT, 64); + do_test_and_reset(VMA_READ_BIT, 65); + do_test_and_reset(VMA_WRITE_BIT, VMA_READ_BIT); + do_test_and_reset(VMA_WRITE_BIT, VMA_EXEC_BIT); + do_test_and_reset(VMA_WRITE_BIT, 64); + do_test_and_reset(VMA_WRITE_BIT, 65); + do_test_and_reset(VMA_EXEC_BIT, VMA_READ_BIT); + do_test_and_reset(VMA_EXEC_BIT, VMA_WRITE_BIT); + do_test_and_reset(VMA_EXEC_BIT, 64); + do_test_and_reset(VMA_EXEC_BIT, 65); + do_test_and_reset(64, VMA_READ_BIT); + do_test_and_reset(64, VMA_WRITE_BIT); + do_test_and_reset(64, VMA_EXEC_BIT); + do_test_and_reset(64, 65); + do_test_and_reset(65, VMA_READ_BIT); + do_test_and_reset(65, VMA_WRITE_BIT); + do_test_and_reset(65, VMA_EXEC_BIT); + do_test_and_reset(65, 64); + + /* Three flags. */ + +#undef do_test_some_missing +#undef do_test_and_reset + + return true; +} + +static void run_vma_tests(int *num_tests, int *num_fail) +{ + TEST(copy_vma); + TEST(vma_flags_unchanged); + TEST(vma_flags_cleared); + TEST(vma_flags_word); + TEST(vma_flags_test); + TEST(vma_flags_clear); +} diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index 7fa56dcc53a6..0e1121e2ef23 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -12,16 +12,18 @@ #ifndef __MM_VMA_INTERNAL_H #define __MM_VMA_INTERNAL_H -#define __private -#define __bitwise -#define __randomize_layout +#include <stdlib.h> #define CONFIG_MMU #define CONFIG_PER_VMA_LOCK -#include <stdlib.h> +#ifdef __CONCAT +#undef __CONCAT +#endif +#include <linux/args.h> #include <linux/atomic.h> +#include <linux/bitmap.h> #include <linux/list.h> #include <linux/maple_tree.h> #include <linux/mm.h> @@ -29,1839 +31,28 @@ #include <linux/refcount.h> #include <linux/slab.h> -extern unsigned long stack_guard_gap; -#ifdef CONFIG_MMU -extern unsigned long mmap_min_addr; -extern unsigned long dac_mmap_min_addr; -#else -#define mmap_min_addr 0UL -#define dac_mmap_min_addr 0UL -#endif - -#define VM_WARN_ON(_expr) (WARN_ON(_expr)) -#define VM_WARN_ON_ONCE(_expr) (WARN_ON_ONCE(_expr)) -#define VM_WARN_ON_VMG(_expr, _vmg) (WARN_ON(_expr)) -#define VM_BUG_ON(_expr) (BUG_ON(_expr)) -#define VM_BUG_ON_VMA(_expr, _vma) (BUG_ON(_expr)) - -#define MMF_HAS_MDWE 28 - -/* - * vm_flags in vm_area_struct, see mm_types.h. - * When changing, update also include/trace/events/mmflags.h - */ - -#define VM_NONE 0x00000000 - -/** - * typedef vma_flag_t - specifies an individual VMA flag by bit number. - * - * This value is made type safe by sparse to avoid passing invalid flag values - * around. - */ -typedef int __bitwise vma_flag_t; - -#define DECLARE_VMA_BIT(name, bitnum) \ - VMA_ ## name ## _BIT = ((__force vma_flag_t)bitnum) -#define DECLARE_VMA_BIT_ALIAS(name, aliased) \ - VMA_ ## name ## _BIT = VMA_ ## aliased ## _BIT -enum { - DECLARE_VMA_BIT(READ, 0), - DECLARE_VMA_BIT(WRITE, 1), - DECLARE_VMA_BIT(EXEC, 2), - DECLARE_VMA_BIT(SHARED, 3), - /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ - DECLARE_VMA_BIT(MAYREAD, 4), /* limits for mprotect() etc. */ - DECLARE_VMA_BIT(MAYWRITE, 5), - DECLARE_VMA_BIT(MAYEXEC, 6), - DECLARE_VMA_BIT(MAYSHARE, 7), - DECLARE_VMA_BIT(GROWSDOWN, 8), /* general info on the segment */ -#ifdef CONFIG_MMU - DECLARE_VMA_BIT(UFFD_MISSING, 9),/* missing pages tracking */ -#else - /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */ - DECLARE_VMA_BIT(MAYOVERLAY, 9), -#endif /* CONFIG_MMU */ - /* Page-ranges managed without "struct page", just pure PFN */ - DECLARE_VMA_BIT(PFNMAP, 10), - DECLARE_VMA_BIT(MAYBE_GUARD, 11), - DECLARE_VMA_BIT(UFFD_WP, 12), /* wrprotect pages tracking */ - DECLARE_VMA_BIT(LOCKED, 13), - DECLARE_VMA_BIT(IO, 14), /* Memory mapped I/O or similar */ - DECLARE_VMA_BIT(SEQ_READ, 15), /* App will access data sequentially */ - DECLARE_VMA_BIT(RAND_READ, 16), /* App will not benefit from clustered reads */ - DECLARE_VMA_BIT(DONTCOPY, 17), /* Do not copy this vma on fork */ - DECLARE_VMA_BIT(DONTEXPAND, 18),/* Cannot expand with mremap() */ - DECLARE_VMA_BIT(LOCKONFAULT, 19),/* Lock pages covered when faulted in */ - DECLARE_VMA_BIT(ACCOUNT, 20), /* Is a VM accounted object */ - DECLARE_VMA_BIT(NORESERVE, 21), /* should the VM suppress accounting */ - DECLARE_VMA_BIT(HUGETLB, 22), /* Huge TLB Page VM */ - DECLARE_VMA_BIT(SYNC, 23), /* Synchronous page faults */ - DECLARE_VMA_BIT(ARCH_1, 24), /* Architecture-specific flag */ - DECLARE_VMA_BIT(WIPEONFORK, 25),/* Wipe VMA contents in child. */ - DECLARE_VMA_BIT(DONTDUMP, 26), /* Do not include in the core dump */ - DECLARE_VMA_BIT(SOFTDIRTY, 27), /* NOT soft dirty clean area */ - DECLARE_VMA_BIT(MIXEDMAP, 28), /* Can contain struct page and pure PFN pages */ - DECLARE_VMA_BIT(HUGEPAGE, 29), /* MADV_HUGEPAGE marked this vma */ - DECLARE_VMA_BIT(NOHUGEPAGE, 30),/* MADV_NOHUGEPAGE marked this vma */ - DECLARE_VMA_BIT(MERGEABLE, 31), /* KSM may merge identical pages */ - /* These bits are reused, we define specific uses below. */ - DECLARE_VMA_BIT(HIGH_ARCH_0, 32), - DECLARE_VMA_BIT(HIGH_ARCH_1, 33), - DECLARE_VMA_BIT(HIGH_ARCH_2, 34), - DECLARE_VMA_BIT(HIGH_ARCH_3, 35), - DECLARE_VMA_BIT(HIGH_ARCH_4, 36), - DECLARE_VMA_BIT(HIGH_ARCH_5, 37), - DECLARE_VMA_BIT(HIGH_ARCH_6, 38), - /* - * This flag is used to connect VFIO to arch specific KVM code. It - * indicates that the memory under this VMA is safe for use with any - * non-cachable memory type inside KVM. Some VFIO devices, on some - * platforms, are thought to be unsafe and can cause machine crashes - * if KVM does not lock down the memory type. - */ - DECLARE_VMA_BIT(ALLOW_ANY_UNCACHED, 39), -#ifdef CONFIG_PPC32 - DECLARE_VMA_BIT_ALIAS(DROPPABLE, ARCH_1), -#else - DECLARE_VMA_BIT(DROPPABLE, 40), -#endif - DECLARE_VMA_BIT(UFFD_MINOR, 41), - DECLARE_VMA_BIT(SEALED, 42), - /* Flags that reuse flags above. */ - DECLARE_VMA_BIT_ALIAS(PKEY_BIT0, HIGH_ARCH_0), - DECLARE_VMA_BIT_ALIAS(PKEY_BIT1, HIGH_ARCH_1), - DECLARE_VMA_BIT_ALIAS(PKEY_BIT2, HIGH_ARCH_2), - DECLARE_VMA_BIT_ALIAS(PKEY_BIT3, HIGH_ARCH_3), - DECLARE_VMA_BIT_ALIAS(PKEY_BIT4, HIGH_ARCH_4), -#if defined(CONFIG_X86_USER_SHADOW_STACK) - /* - * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of - * support core mm. - * - * These VMAs will get a single end guard page. This helps userspace - * protect itself from attacks. A single page is enough for current - * shadow stack archs (x86). See the comments near alloc_shstk() in - * arch/x86/kernel/shstk.c for more details on the guard size. - */ - DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_5), -#elif defined(CONFIG_ARM64_GCS) - /* - * arm64's Guarded Control Stack implements similar functionality and - * has similar constraints to shadow stacks. - */ - DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_6), -#endif - DECLARE_VMA_BIT_ALIAS(SAO, ARCH_1), /* Strong Access Ordering (powerpc) */ - DECLARE_VMA_BIT_ALIAS(GROWSUP, ARCH_1), /* parisc */ - DECLARE_VMA_BIT_ALIAS(SPARC_ADI, ARCH_1), /* sparc64 */ - DECLARE_VMA_BIT_ALIAS(ARM64_BTI, ARCH_1), /* arm64 */ - DECLARE_VMA_BIT_ALIAS(ARCH_CLEAR, ARCH_1), /* sparc64, arm64 */ - DECLARE_VMA_BIT_ALIAS(MAPPED_COPY, ARCH_1), /* !CONFIG_MMU */ - DECLARE_VMA_BIT_ALIAS(MTE, HIGH_ARCH_4), /* arm64 */ - DECLARE_VMA_BIT_ALIAS(MTE_ALLOWED, HIGH_ARCH_5),/* arm64 */ -#ifdef CONFIG_STACK_GROWSUP - DECLARE_VMA_BIT_ALIAS(STACK, GROWSUP), - DECLARE_VMA_BIT_ALIAS(STACK_EARLY, GROWSDOWN), -#else - DECLARE_VMA_BIT_ALIAS(STACK, GROWSDOWN), -#endif -}; - -#define INIT_VM_FLAG(name) BIT((__force int) VMA_ ## name ## _BIT) -#define VM_READ INIT_VM_FLAG(READ) -#define VM_WRITE INIT_VM_FLAG(WRITE) -#define VM_EXEC INIT_VM_FLAG(EXEC) -#define VM_SHARED INIT_VM_FLAG(SHARED) -#define VM_MAYREAD INIT_VM_FLAG(MAYREAD) -#define VM_MAYWRITE INIT_VM_FLAG(MAYWRITE) -#define VM_MAYEXEC INIT_VM_FLAG(MAYEXEC) -#define VM_MAYSHARE INIT_VM_FLAG(MAYSHARE) -#define VM_GROWSDOWN INIT_VM_FLAG(GROWSDOWN) -#ifdef CONFIG_MMU -#define VM_UFFD_MISSING INIT_VM_FLAG(UFFD_MISSING) -#else -#define VM_UFFD_MISSING VM_NONE -#define VM_MAYOVERLAY INIT_VM_FLAG(MAYOVERLAY) -#endif -#define VM_PFNMAP INIT_VM_FLAG(PFNMAP) -#define VM_MAYBE_GUARD INIT_VM_FLAG(MAYBE_GUARD) -#define VM_UFFD_WP INIT_VM_FLAG(UFFD_WP) -#define VM_LOCKED INIT_VM_FLAG(LOCKED) -#define VM_IO INIT_VM_FLAG(IO) -#define VM_SEQ_READ INIT_VM_FLAG(SEQ_READ) -#define VM_RAND_READ INIT_VM_FLAG(RAND_READ) -#define VM_DONTCOPY INIT_VM_FLAG(DONTCOPY) -#define VM_DONTEXPAND INIT_VM_FLAG(DONTEXPAND) -#define VM_LOCKONFAULT INIT_VM_FLAG(LOCKONFAULT) -#define VM_ACCOUNT INIT_VM_FLAG(ACCOUNT) -#define VM_NORESERVE INIT_VM_FLAG(NORESERVE) -#define VM_HUGETLB INIT_VM_FLAG(HUGETLB) -#define VM_SYNC INIT_VM_FLAG(SYNC) -#define VM_ARCH_1 INIT_VM_FLAG(ARCH_1) -#define VM_WIPEONFORK INIT_VM_FLAG(WIPEONFORK) -#define VM_DONTDUMP INIT_VM_FLAG(DONTDUMP) -#ifdef CONFIG_MEM_SOFT_DIRTY -#define VM_SOFTDIRTY INIT_VM_FLAG(SOFTDIRTY) -#else -#define VM_SOFTDIRTY VM_NONE -#endif -#define VM_MIXEDMAP INIT_VM_FLAG(MIXEDMAP) -#define VM_HUGEPAGE INIT_VM_FLAG(HUGEPAGE) -#define VM_NOHUGEPAGE INIT_VM_FLAG(NOHUGEPAGE) -#define VM_MERGEABLE INIT_VM_FLAG(MERGEABLE) -#define VM_STACK INIT_VM_FLAG(STACK) -#ifdef CONFIG_STACK_GROWS_UP -#define VM_STACK_EARLY INIT_VM_FLAG(STACK_EARLY) -#else -#define VM_STACK_EARLY VM_NONE -#endif -#ifdef CONFIG_ARCH_HAS_PKEYS -#define VM_PKEY_SHIFT ((__force int)VMA_HIGH_ARCH_0_BIT) -/* Despite the naming, these are FLAGS not bits. */ -#define VM_PKEY_BIT0 INIT_VM_FLAG(PKEY_BIT0) -#define VM_PKEY_BIT1 INIT_VM_FLAG(PKEY_BIT1) -#define VM_PKEY_BIT2 INIT_VM_FLAG(PKEY_BIT2) -#if CONFIG_ARCH_PKEY_BITS > 3 -#define VM_PKEY_BIT3 INIT_VM_FLAG(PKEY_BIT3) -#else -#define VM_PKEY_BIT3 VM_NONE -#endif /* CONFIG_ARCH_PKEY_BITS > 3 */ -#if CONFIG_ARCH_PKEY_BITS > 4 -#define VM_PKEY_BIT4 INIT_VM_FLAG(PKEY_BIT4) -#else -#define VM_PKEY_BIT4 VM_NONE -#endif /* CONFIG_ARCH_PKEY_BITS > 4 */ -#endif /* CONFIG_ARCH_HAS_PKEYS */ -#if defined(CONFIG_X86_USER_SHADOW_STACK) || defined(CONFIG_ARM64_GCS) -#define VM_SHADOW_STACK INIT_VM_FLAG(SHADOW_STACK) -#else -#define VM_SHADOW_STACK VM_NONE -#endif -#if defined(CONFIG_PPC64) -#define VM_SAO INIT_VM_FLAG(SAO) -#elif defined(CONFIG_PARISC) -#define VM_GROWSUP INIT_VM_FLAG(GROWSUP) -#elif defined(CONFIG_SPARC64) -#define VM_SPARC_ADI INIT_VM_FLAG(SPARC_ADI) -#define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR) -#elif defined(CONFIG_ARM64) -#define VM_ARM64_BTI INIT_VM_FLAG(ARM64_BTI) -#define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR) -#elif !defined(CONFIG_MMU) -#define VM_MAPPED_COPY INIT_VM_FLAG(MAPPED_COPY) -#endif -#ifndef VM_GROWSUP -#define VM_GROWSUP VM_NONE -#endif -#ifdef CONFIG_ARM64_MTE -#define VM_MTE INIT_VM_FLAG(MTE) -#define VM_MTE_ALLOWED INIT_VM_FLAG(MTE_ALLOWED) -#else -#define VM_MTE VM_NONE -#define VM_MTE_ALLOWED VM_NONE -#endif -#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR -#define VM_UFFD_MINOR INIT_VM_FLAG(UFFD_MINOR) -#else -#define VM_UFFD_MINOR VM_NONE -#endif -#ifdef CONFIG_64BIT -#define VM_ALLOW_ANY_UNCACHED INIT_VM_FLAG(ALLOW_ANY_UNCACHED) -#define VM_SEALED INIT_VM_FLAG(SEALED) -#else -#define VM_ALLOW_ANY_UNCACHED VM_NONE -#define VM_SEALED VM_NONE -#endif -#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32) -#define VM_DROPPABLE INIT_VM_FLAG(DROPPABLE) -#else -#define VM_DROPPABLE VM_NONE -#endif - -/* Bits set in the VMA until the stack is in its final location */ -#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY) - -#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) - -/* Common data flag combinations */ -#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -#define VM_DATA_FLAGS_NON_EXEC (VM_READ | VM_WRITE | VM_MAYREAD | \ - VM_MAYWRITE | VM_MAYEXEC) -#define VM_DATA_FLAGS_EXEC (VM_READ | VM_WRITE | VM_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) - -#ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */ -#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_EXEC -#endif - -#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ -#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS -#endif - -#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK) - -#define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) - -/* VMA basic access permission flags */ -#define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) - -/* - * Special vmas that are non-mergable, non-mlock()able. - */ -#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) - -#define DEFAULT_MAP_WINDOW ((1UL << 47) - PAGE_SIZE) -#define TASK_SIZE_LOW DEFAULT_MAP_WINDOW -#define TASK_SIZE_MAX DEFAULT_MAP_WINDOW -#define STACK_TOP TASK_SIZE_LOW -#define STACK_TOP_MAX TASK_SIZE_MAX - -/* This mask represents all the VMA flag bits used by mlock */ -#define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) - -#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) - -#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) - -#define RLIMIT_STACK 3 /* max stack size */ -#define RLIMIT_MEMLOCK 8 /* max locked-in-memory address space */ - -#define CAP_IPC_LOCK 14 - -/* - * Flags which should be 'sticky' on merge - that is, flags which, when one VMA - * possesses it but the other does not, the merged VMA should nonetheless have - * applied to it: - * - * VM_SOFTDIRTY - if a VMA is marked soft-dirty, that is has not had its - * references cleared via /proc/$pid/clear_refs, any merged VMA - * should be considered soft-dirty also as it operates at a VMA - * granularity. - */ -#define VM_STICKY (VM_SOFTDIRTY | VM_MAYBE_GUARD) - -/* - * VMA flags we ignore for the purposes of merge, i.e. one VMA possessing one - * of these flags and the other not does not preclude a merge. - * - * VM_STICKY - When merging VMAs, VMA flags must match, unless they are - * 'sticky'. If any sticky flags exist in either VMA, we simply - * set all of them on the merged VMA. - */ -#define VM_IGNORE_MERGE VM_STICKY - -/* - * Flags which should result in page tables being copied on fork. These are - * flags which indicate that the VMA maps page tables which cannot be - * reconsistuted upon page fault, so necessitate page table copying upon - * - * VM_PFNMAP / VM_MIXEDMAP - These contain kernel-mapped data which cannot be - * reasonably reconstructed on page fault. - * - * VM_UFFD_WP - Encodes metadata about an installed uffd - * write protect handler, which cannot be - * reconstructed on page fault. - * - * We always copy pgtables when dst_vma has uffd-wp - * enabled even if it's file-backed - * (e.g. shmem). Because when uffd-wp is enabled, - * pgtable contains uffd-wp protection information, - * that's something we can't retrieve from page cache, - * and skip copying will lose those info. - * - * VM_MAYBE_GUARD - Could contain page guard region markers which - * by design are a property of the page tables - * only and thus cannot be reconstructed on page - * fault. - */ -#define VM_COPY_ON_FORK (VM_PFNMAP | VM_MIXEDMAP | VM_UFFD_WP | VM_MAYBE_GUARD) - -#define FIRST_USER_ADDRESS 0UL -#define USER_PGTABLES_CEILING 0UL - -#define vma_policy(vma) NULL - -#define down_write_nest_lock(sem, nest_lock) - -#define pgprot_val(x) ((x).pgprot) -#define __pgprot(x) ((pgprot_t) { (x) } ) - -#define for_each_vma(__vmi, __vma) \ - while (((__vma) = vma_next(&(__vmi))) != NULL) - -/* The MM code likes to work with exclusive end addresses */ -#define for_each_vma_range(__vmi, __vma, __end) \ - while (((__vma) = vma_find(&(__vmi), (__end))) != NULL) - -#define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) - -#define PHYS_PFN(x) ((unsigned long)((x) >> PAGE_SHIFT)) - -#define test_and_set_bit(nr, addr) __test_and_set_bit(nr, addr) -#define test_and_clear_bit(nr, addr) __test_and_clear_bit(nr, addr) - -#define TASK_SIZE ((1ul << 47)-PAGE_SIZE) - -#define AS_MM_ALL_LOCKS 2 - -/* We hardcode this for now. */ -#define sysctl_max_map_count 0x1000000UL - -#define pgoff_t unsigned long -typedef unsigned long pgprotval_t; -typedef struct pgprot { pgprotval_t pgprot; } pgprot_t; -typedef unsigned long vm_flags_t; -typedef __bitwise unsigned int vm_fault_t; - -/* - * The shared stubs do not implement this, it amounts to an fprintf(STDERR,...) - * either way :) - */ -#define pr_warn_once pr_err - -#define data_race(expr) expr - -#define ASSERT_EXCLUSIVE_WRITER(x) - -#define pgtable_supports_soft_dirty() 1 - -/** - * swap - swap values of @a and @b - * @a: first value - * @b: second value - */ -#define swap(a, b) \ - do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) - -struct kref { - refcount_t refcount; -}; - -/* - * Define the task command name length as enum, then it can be visible to - * BPF programs. - */ -enum { - TASK_COMM_LEN = 16, -}; - /* - * Flags for bug emulation. - * - * These occupy the top three bytes. + * DUPLICATE typedef definitions from kernel source that have to be declared + * ahead of all other headers. */ -enum { - READ_IMPLIES_EXEC = 0x0400000, -}; - -struct task_struct { - char comm[TASK_COMM_LEN]; - pid_t pid; - struct mm_struct *mm; - - /* Used for emulating ABI behavior of previous Linux versions: */ - unsigned int personality; -}; - -struct task_struct *get_current(void); -#define current get_current() - -struct anon_vma { - struct anon_vma *root; - struct rb_root_cached rb_root; - - /* Test fields. */ - bool was_cloned; - bool was_unlinked; -}; - -struct anon_vma_chain { - struct anon_vma *anon_vma; - struct list_head same_vma; -}; - -struct anon_vma_name { - struct kref kref; - /* The name needs to be at the end because it is dynamically sized. */ - char name[]; -}; - -struct vma_iterator { - struct ma_state mas; -}; - -#define VMA_ITERATOR(name, __mm, __addr) \ - struct vma_iterator name = { \ - .mas = { \ - .tree = &(__mm)->mm_mt, \ - .index = __addr, \ - .node = NULL, \ - .status = ma_start, \ - }, \ - } - -struct address_space { - struct rb_root_cached i_mmap; - unsigned long flags; - atomic_t i_mmap_writable; -}; - -struct vm_userfaultfd_ctx {}; -struct mempolicy {}; -struct mmu_gather {}; -struct mutex {}; -#define DEFINE_MUTEX(mutexname) \ - struct mutex mutexname = {} - -#define DECLARE_BITMAP(name, bits) \ - unsigned long name[BITS_TO_LONGS(bits)] - -#define NUM_MM_FLAG_BITS (64) +#define __private +/* NUM_MM_FLAG_BITS defined by test code. */ typedef struct { __private DECLARE_BITMAP(__mm_flags, NUM_MM_FLAG_BITS); } mm_flags_t; - -/* - * Opaque type representing current VMA (vm_area_struct) flag state. Must be - * accessed via vma_flags_xxx() helper functions. - */ -#define NUM_VMA_FLAG_BITS BITS_PER_LONG +/* NUM_VMA_FLAG_BITS defined by test code. */ typedef struct { DECLARE_BITMAP(__vma_flags, NUM_VMA_FLAG_BITS); } __private vma_flags_t; -struct mm_struct { - struct maple_tree mm_mt; - int map_count; /* number of VMAs */ - unsigned long total_vm; /* Total pages mapped */ - unsigned long locked_vm; /* Pages that have PG_mlocked set */ - unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ - unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ - unsigned long stack_vm; /* VM_STACK */ - - unsigned long def_flags; - - mm_flags_t flags; /* Must use mm_flags_* helpers to access */ -}; - -struct vm_area_struct; - - -/* What action should be taken after an .mmap_prepare call is complete? */ -enum mmap_action_type { - MMAP_NOTHING, /* Mapping is complete, no further action. */ - MMAP_REMAP_PFN, /* Remap PFN range. */ - MMAP_IO_REMAP_PFN, /* I/O remap PFN range. */ -}; - -/* - * Describes an action an mmap_prepare hook can instruct to be taken to complete - * the mapping of a VMA. Specified in vm_area_desc. - */ -struct mmap_action { - union { - /* Remap range. */ - struct { - unsigned long start; - unsigned long start_pfn; - unsigned long size; - pgprot_t pgprot; - } remap; - }; - enum mmap_action_type type; - - /* - * If specified, this hook is invoked after the selected action has been - * successfully completed. Note that the VMA write lock still held. - * - * The absolute minimum ought to be done here. - * - * Returns 0 on success, or an error code. - */ - int (*success_hook)(const struct vm_area_struct *vma); - - /* - * If specified, this hook is invoked when an error occurred when - * attempting the selection action. - * - * The hook can return an error code in order to filter the error, but - * it is not valid to clear the error here. - */ - int (*error_hook)(int err); - - /* - * This should be set in rare instances where the operation required - * that the rmap should not be able to access the VMA until - * completely set up. - */ - bool hide_from_rmap_until_complete :1; -}; - -/* Operations which modify VMAs. */ -enum vma_operation { - VMA_OP_SPLIT, - VMA_OP_MERGE_UNFAULTED, - VMA_OP_REMAP, - VMA_OP_FORK, -}; - -/* - * Describes a VMA that is about to be mmap()'ed. Drivers may choose to - * manipulate mutable fields which will cause those fields to be updated in the - * resultant VMA. - * - * Helper functions are not required for manipulating any field. - */ -struct vm_area_desc { - /* Immutable state. */ - const struct mm_struct *const mm; - struct file *const file; /* May vary from vm_file in stacked callers. */ - unsigned long start; - unsigned long end; - - /* Mutable fields. Populated with initial state. */ - pgoff_t pgoff; - struct file *vm_file; - union { - vm_flags_t vm_flags; - vma_flags_t vma_flags; - }; - pgprot_t page_prot; - - /* Write-only fields. */ - const struct vm_operations_struct *vm_ops; - void *private_data; - - /* Take further action? */ - struct mmap_action action; -}; - -struct file_operations { - int (*mmap)(struct file *, struct vm_area_struct *); - int (*mmap_prepare)(struct vm_area_desc *); -}; - -struct file { - struct address_space *f_mapping; - const struct file_operations *f_op; -}; - -#define VMA_LOCK_OFFSET 0x40000000 - -typedef struct { unsigned long v; } freeptr_t; - -struct vm_area_struct { - /* The first cache line has the info for VMA tree walking. */ - - union { - struct { - /* VMA covers [vm_start; vm_end) addresses within mm */ - unsigned long vm_start; - unsigned long vm_end; - }; - freeptr_t vm_freeptr; /* Pointer used by SLAB_TYPESAFE_BY_RCU */ - }; - - struct mm_struct *vm_mm; /* The address space we belong to. */ - pgprot_t vm_page_prot; /* Access permissions of this VMA. */ - - /* - * Flags, see mm.h. - * To modify use vm_flags_{init|reset|set|clear|mod} functions. - */ - union { - const vm_flags_t vm_flags; - vma_flags_t flags; - }; - -#ifdef CONFIG_PER_VMA_LOCK - /* - * Can only be written (using WRITE_ONCE()) while holding both: - * - mmap_lock (in write mode) - * - vm_refcnt bit at VMA_LOCK_OFFSET is set - * Can be read reliably while holding one of: - * - mmap_lock (in read or write mode) - * - vm_refcnt bit at VMA_LOCK_OFFSET is set or vm_refcnt > 1 - * Can be read unreliably (using READ_ONCE()) for pessimistic bailout - * while holding nothing (except RCU to keep the VMA struct allocated). - * - * This sequence counter is explicitly allowed to overflow; sequence - * counter reuse can only lead to occasional unnecessary use of the - * slowpath. - */ - unsigned int vm_lock_seq; -#endif - - /* - * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma - * list, after a COW of one of the file pages. A MAP_SHARED vma - * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack - * or brk vma (with NULL file) can only be in an anon_vma list. - */ - struct list_head anon_vma_chain; /* Serialized by mmap_lock & - * page_table_lock */ - struct anon_vma *anon_vma; /* Serialized by page_table_lock */ - - /* Function pointers to deal with this struct. */ - const struct vm_operations_struct *vm_ops; - - /* Information about our backing store: */ - unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE - units */ - struct file * vm_file; /* File we map to (can be NULL). */ - void * vm_private_data; /* was vm_pte (shared mem) */ - -#ifdef CONFIG_SWAP - atomic_long_t swap_readahead_info; -#endif -#ifndef CONFIG_MMU - struct vm_region *vm_region; /* NOMMU mapping region */ -#endif -#ifdef CONFIG_NUMA - struct mempolicy *vm_policy; /* NUMA policy for the VMA */ -#endif -#ifdef CONFIG_NUMA_BALANCING - struct vma_numab_state *numab_state; /* NUMA Balancing state */ -#endif -#ifdef CONFIG_PER_VMA_LOCK - /* Unstable RCU readers are allowed to read this. */ - refcount_t vm_refcnt; -#endif - /* - * For areas with an address space and backing store, - * linkage into the address_space->i_mmap interval tree. - * - */ - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } shared; -#ifdef CONFIG_ANON_VMA_NAME - /* - * For private and shared anonymous mappings, a pointer to a null - * terminated string containing the name given to the vma, or NULL if - * unnamed. Serialized by mmap_lock. Use anon_vma_name to access. - */ - struct anon_vma_name *anon_name; -#endif - struct vm_userfaultfd_ctx vm_userfaultfd_ctx; -} __randomize_layout; - -struct vm_fault {}; - -struct vm_operations_struct { - void (*open)(struct vm_area_struct * area); - /** - * @close: Called when the VMA is being removed from the MM. - * Context: User context. May sleep. Caller holds mmap_lock. - */ - void (*close)(struct vm_area_struct * area); - /* Called any time before splitting to check if it's allowed */ - int (*may_split)(struct vm_area_struct *area, unsigned long addr); - int (*mremap)(struct vm_area_struct *area); - /* - * Called by mprotect() to make driver-specific permission - * checks before mprotect() is finalised. The VMA must not - * be modified. Returns 0 if mprotect() can proceed. - */ - int (*mprotect)(struct vm_area_struct *vma, unsigned long start, - unsigned long end, unsigned long newflags); - vm_fault_t (*fault)(struct vm_fault *vmf); - vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order); - vm_fault_t (*map_pages)(struct vm_fault *vmf, - pgoff_t start_pgoff, pgoff_t end_pgoff); - unsigned long (*pagesize)(struct vm_area_struct * area); - - /* notification that a previously read-only page is about to become - * writable, if an error is returned it will cause a SIGBUS */ - vm_fault_t (*page_mkwrite)(struct vm_fault *vmf); - - /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */ - vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf); - - /* called by access_process_vm when get_user_pages() fails, typically - * for use by special VMAs. See also generic_access_phys() for a generic - * implementation useful for any iomem mapping. - */ - int (*access)(struct vm_area_struct *vma, unsigned long addr, - void *buf, int len, int write); - - /* Called by the /proc/PID/maps code to ask the vma whether it - * has a special name. Returning non-NULL will also cause this - * vma to be dumped unconditionally. */ - const char *(*name)(struct vm_area_struct *vma); - -#ifdef CONFIG_NUMA - /* - * set_policy() op must add a reference to any non-NULL @new mempolicy - * to hold the policy upon return. Caller should pass NULL @new to - * remove a policy and fall back to surrounding context--i.e. do not - * install a MPOL_DEFAULT policy, nor the task or system default - * mempolicy. - */ - int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); - - /* - * get_policy() op must add reference [mpol_get()] to any policy at - * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure - * in mm/mempolicy.c will do this automatically. - * get_policy() must NOT add a ref if the policy at (vma,addr) is not - * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. - * If no [shared/vma] mempolicy exists at the addr, get_policy() op - * must return NULL--i.e., do not "fallback" to task or system default - * policy. - */ - struct mempolicy *(*get_policy)(struct vm_area_struct *vma, - unsigned long addr, pgoff_t *ilx); -#endif -#ifdef CONFIG_FIND_NORMAL_PAGE - /* - * Called by vm_normal_page() for special PTEs in @vma at @addr. This - * allows for returning a "normal" page from vm_normal_page() even - * though the PTE indicates that the "struct page" either does not exist - * or should not be touched: "special". - * - * Do not add new users: this really only works when a "normal" page - * was mapped, but then the PTE got changed to something weird (+ - * marked special) that would not make pte_pfn() identify the originally - * inserted page. - */ - struct page *(*find_normal_page)(struct vm_area_struct *vma, - unsigned long addr); -#endif /* CONFIG_FIND_NORMAL_PAGE */ -}; - -struct vm_unmapped_area_info { -#define VM_UNMAPPED_AREA_TOPDOWN 1 - unsigned long flags; - unsigned long length; - unsigned long low_limit; - unsigned long high_limit; - unsigned long align_mask; - unsigned long align_offset; - unsigned long start_gap; -}; - -struct pagetable_move_control { - struct vm_area_struct *old; /* Source VMA. */ - struct vm_area_struct *new; /* Destination VMA. */ - unsigned long old_addr; /* Address from which the move begins. */ - unsigned long old_end; /* Exclusive address at which old range ends. */ - unsigned long new_addr; /* Address to move page tables to. */ - unsigned long len_in; /* Bytes to remap specified by user. */ - - bool need_rmap_locks; /* Do rmap locks need to be taken? */ - bool for_stack; /* Is this an early temp stack being moved? */ -}; - -#define PAGETABLE_MOVE(name, old_, new_, old_addr_, new_addr_, len_) \ - struct pagetable_move_control name = { \ - .old = old_, \ - .new = new_, \ - .old_addr = old_addr_, \ - .old_end = (old_addr_) + (len_), \ - .new_addr = new_addr_, \ - .len_in = len_, \ - } - -static inline void vma_iter_invalidate(struct vma_iterator *vmi) -{ - mas_pause(&vmi->mas); -} - -static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) -{ - return __pgprot(pgprot_val(oldprot) | pgprot_val(newprot)); -} - -static inline pgprot_t vm_get_page_prot(vm_flags_t vm_flags) -{ - return __pgprot(vm_flags); -} - -static inline bool is_shared_maywrite(vm_flags_t vm_flags) -{ - return (vm_flags & (VM_SHARED | VM_MAYWRITE)) == - (VM_SHARED | VM_MAYWRITE); -} - -static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma) -{ - return is_shared_maywrite(vma->vm_flags); -} - -static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) -{ - /* - * Uses mas_find() to get the first VMA when the iterator starts. - * Calling mas_next() could skip the first entry. - */ - return mas_find(&vmi->mas, ULONG_MAX); -} - -/* - * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these - * assertions should be made either under mmap_write_lock or when the object - * has been isolated under mmap_write_lock, ensuring no competing writers. - */ -static inline void vma_assert_attached(struct vm_area_struct *vma) -{ - WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt)); -} - -static inline void vma_assert_detached(struct vm_area_struct *vma) -{ - WARN_ON_ONCE(refcount_read(&vma->vm_refcnt)); -} - -static inline void vma_assert_write_locked(struct vm_area_struct *); -static inline void vma_mark_attached(struct vm_area_struct *vma) -{ - vma_assert_write_locked(vma); - vma_assert_detached(vma); - refcount_set_release(&vma->vm_refcnt, 1); -} - -static inline void vma_mark_detached(struct vm_area_struct *vma) -{ - vma_assert_write_locked(vma); - vma_assert_attached(vma); - /* We are the only writer, so no need to use vma_refcount_put(). */ - if (unlikely(!refcount_dec_and_test(&vma->vm_refcnt))) { - /* - * Reader must have temporarily raised vm_refcnt but it will - * drop it without using the vma since vma is write-locked. - */ - } -} - -extern const struct vm_operations_struct vma_dummy_vm_ops; - -extern unsigned long rlimit(unsigned int limit); - -static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) -{ - memset(vma, 0, sizeof(*vma)); - vma->vm_mm = mm; - vma->vm_ops = &vma_dummy_vm_ops; - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_lock_seq = UINT_MAX; -} - -/* - * These are defined in vma.h, but sadly vm_stat_account() is referenced by - * kernel/fork.c, so we have to these broadly available there, and temporarily - * define them here to resolve the dependency cycle. - */ - -#define is_exec_mapping(flags) \ - ((flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC) - -#define is_stack_mapping(flags) \ - (((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK)) - -#define is_data_mapping(flags) \ - ((flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE) - -static inline void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, - long npages) -{ - WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages); - - if (is_exec_mapping(flags)) - mm->exec_vm += npages; - else if (is_stack_mapping(flags)) - mm->stack_vm += npages; - else if (is_data_mapping(flags)) - mm->data_vm += npages; -} - -#undef is_exec_mapping -#undef is_stack_mapping -#undef is_data_mapping - -/* Currently stubbed but we may later wish to un-stub. */ -static inline void vm_acct_memory(long pages); -static inline void vm_unacct_memory(long pages) -{ - vm_acct_memory(-pages); -} - -static inline void mapping_allow_writable(struct address_space *mapping) -{ - atomic_inc(&mapping->i_mmap_writable); -} - -static inline void vma_set_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - pgoff_t pgoff) -{ - vma->vm_start = start; - vma->vm_end = end; - vma->vm_pgoff = pgoff; -} - -static inline -struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) -{ - return mas_find(&vmi->mas, max - 1); -} - -static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, - unsigned long start, unsigned long end, gfp_t gfp) -{ - __mas_set_range(&vmi->mas, start, end - 1); - mas_store_gfp(&vmi->mas, NULL, gfp); - if (unlikely(mas_is_err(&vmi->mas))) - return -ENOMEM; - - return 0; -} - -static inline void mmap_assert_locked(struct mm_struct *); -static inline struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, - unsigned long start_addr, - unsigned long end_addr) -{ - unsigned long index = start_addr; - - mmap_assert_locked(mm); - return mt_find(&mm->mm_mt, &index, end_addr - 1); -} - -static inline -struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) -{ - return mtree_load(&mm->mm_mt, addr); -} - -static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) -{ - return mas_prev(&vmi->mas, 0); -} - -static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr) -{ - mas_set(&vmi->mas, addr); -} - -static inline bool vma_is_anonymous(struct vm_area_struct *vma) -{ - return !vma->vm_ops; -} - -/* Defined in vma.h, so temporarily define here to avoid circular dependency. */ -#define vma_iter_load(vmi) \ - mas_walk(&(vmi)->mas) - -static inline struct vm_area_struct * -find_vma_prev(struct mm_struct *mm, unsigned long addr, - struct vm_area_struct **pprev) -{ - struct vm_area_struct *vma; - VMA_ITERATOR(vmi, mm, addr); - - vma = vma_iter_load(&vmi); - *pprev = vma_prev(&vmi); - if (!vma) - vma = vma_next(&vmi); - return vma; -} - -#undef vma_iter_load - -static inline void vma_iter_init(struct vma_iterator *vmi, - struct mm_struct *mm, unsigned long addr) -{ - mas_init(&vmi->mas, &mm->mm_mt, addr); -} - -/* Stubbed functions. */ - -static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) -{ - return NULL; -} - -static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, - struct vm_userfaultfd_ctx vm_ctx) -{ - return true; -} - -static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, - struct anon_vma_name *anon_name2) -{ - return true; -} - -static inline void might_sleep(void) -{ -} - -static inline unsigned long vma_pages(struct vm_area_struct *vma) -{ - return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; -} - -static inline void fput(struct file *file) -{ -} - -static inline void mpol_put(struct mempolicy *pol) -{ -} - -static inline void lru_add_drain(void) -{ -} - -static inline void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm) -{ -} - -static inline void update_hiwater_rss(struct mm_struct *mm) -{ -} - -static inline void update_hiwater_vm(struct mm_struct *mm) -{ -} - -static inline void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, - struct vm_area_struct *vma, unsigned long start_addr, - unsigned long end_addr, unsigned long tree_end) -{ -} - -static inline void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, - struct vm_area_struct *vma, unsigned long floor, - unsigned long ceiling, bool mm_wr_locked) -{ -} - -static inline void mapping_unmap_writable(struct address_space *mapping) -{ -} - -static inline void flush_dcache_mmap_lock(struct address_space *mapping) -{ -} - -static inline void tlb_finish_mmu(struct mmu_gather *tlb) -{ -} - -static inline struct file *get_file(struct file *f) -{ - return f; -} - -static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) -{ - return 0; -} - -static inline int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src, - enum vma_operation operation) -{ - /* For testing purposes. We indicate that an anon_vma has been cloned. */ - if (src->anon_vma != NULL) { - dst->anon_vma = src->anon_vma; - dst->anon_vma->was_cloned = true; - } - - return 0; -} - -static inline void vma_start_write(struct vm_area_struct *vma) -{ - /* Used to indicate to tests that a write operation has begun. */ - vma->vm_lock_seq++; -} - -static inline __must_check -int vma_start_write_killable(struct vm_area_struct *vma) -{ - /* Used to indicate to tests that a write operation has begun. */ - vma->vm_lock_seq++; - return 0; -} - -static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, - unsigned long start, - unsigned long end, - struct vm_area_struct *next) -{ -} - -static inline void hugetlb_split(struct vm_area_struct *, unsigned long) {} - -static inline void vma_iter_free(struct vma_iterator *vmi) -{ - mas_destroy(&vmi->mas); -} - -static inline -struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi) -{ - return mas_next_range(&vmi->mas, ULONG_MAX); -} - -static inline void vm_acct_memory(long pages) -{ -} - -static inline void vma_interval_tree_insert(struct vm_area_struct *vma, - struct rb_root_cached *rb) -{ -} - -static inline void vma_interval_tree_remove(struct vm_area_struct *vma, - struct rb_root_cached *rb) -{ -} - -static inline void flush_dcache_mmap_unlock(struct address_space *mapping) -{ -} - -static inline void anon_vma_interval_tree_insert(struct anon_vma_chain *avc, - struct rb_root_cached *rb) -{ -} - -static inline void anon_vma_interval_tree_remove(struct anon_vma_chain *avc, - struct rb_root_cached *rb) -{ -} - -static inline void uprobe_mmap(struct vm_area_struct *vma) -{ -} - -static inline void uprobe_munmap(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ -} - -static inline void i_mmap_lock_write(struct address_space *mapping) -{ -} - -static inline void anon_vma_lock_write(struct anon_vma *anon_vma) -{ -} - -static inline void vma_assert_write_locked(struct vm_area_struct *vma) -{ -} - -static inline void unlink_anon_vmas(struct vm_area_struct *vma) -{ - /* For testing purposes, indicate that the anon_vma was unlinked. */ - vma->anon_vma->was_unlinked = true; -} - -static inline void anon_vma_unlock_write(struct anon_vma *anon_vma) -{ -} - -static inline void i_mmap_unlock_write(struct address_space *mapping) -{ -} - -static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, - unsigned long start, - unsigned long end, - struct list_head *unmaps) -{ - return 0; -} - -static inline void mmap_write_downgrade(struct mm_struct *mm) -{ -} - -static inline void mmap_read_unlock(struct mm_struct *mm) -{ -} - -static inline void mmap_write_unlock(struct mm_struct *mm) -{ -} - -static inline int mmap_write_lock_killable(struct mm_struct *mm) -{ - return 0; -} - -static inline bool can_modify_mm(struct mm_struct *mm, - unsigned long start, - unsigned long end) -{ - return true; -} - -static inline void arch_unmap(struct mm_struct *mm, - unsigned long start, - unsigned long end) -{ -} - -static inline void mmap_assert_locked(struct mm_struct *mm) -{ -} - -static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) -{ - return true; -} - -static inline void khugepaged_enter_vma(struct vm_area_struct *vma, - vm_flags_t vm_flags) -{ -} - -static inline bool mapping_can_writeback(struct address_space *mapping) -{ - return true; -} - -static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma) -{ - return false; -} - -static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) -{ - return false; -} - -static inline bool userfaultfd_wp(struct vm_area_struct *vma) -{ - return false; -} - -static inline void mmap_assert_write_locked(struct mm_struct *mm) -{ -} - -static inline void mutex_lock(struct mutex *lock) -{ -} - -static inline void mutex_unlock(struct mutex *lock) -{ -} - -static inline bool mutex_is_locked(struct mutex *lock) -{ - return true; -} - -static inline bool signal_pending(void *p) -{ - return false; -} - -static inline bool is_file_hugepages(struct file *file) -{ - return false; -} - -static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) -{ - return 0; -} - -static inline bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, - unsigned long npages) -{ - return true; -} - -static inline int shmem_zero_setup(struct vm_area_struct *vma) -{ - return 0; -} - -static inline void vma_set_anonymous(struct vm_area_struct *vma) -{ - vma->vm_ops = NULL; -} - -static inline void ksm_add_vma(struct vm_area_struct *vma) -{ -} - -static inline void perf_event_mmap(struct vm_area_struct *vma) -{ -} - -static inline bool vma_is_dax(struct vm_area_struct *vma) -{ - return false; -} - -static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm) -{ - return NULL; -} - -bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); - -/* Update vma->vm_page_prot to reflect vma->vm_flags. */ -static inline void vma_set_page_prot(struct vm_area_struct *vma) -{ - vm_flags_t vm_flags = vma->vm_flags; - pgprot_t vm_page_prot; - - /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */ - vm_page_prot = pgprot_modify(vma->vm_page_prot, vm_get_page_prot(vm_flags)); - - if (vma_wants_writenotify(vma, vm_page_prot)) { - vm_flags &= ~VM_SHARED; - /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */ - vm_page_prot = pgprot_modify(vm_page_prot, vm_get_page_prot(vm_flags)); - } - /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */ - WRITE_ONCE(vma->vm_page_prot, vm_page_prot); -} - -static inline bool arch_validate_flags(vm_flags_t flags) -{ - return true; -} - -static inline void vma_close(struct vm_area_struct *vma) -{ -} - -static inline int mmap_file(struct file *file, struct vm_area_struct *vma) -{ - return 0; -} - -static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) -{ - if (vma->vm_flags & VM_GROWSDOWN) - return stack_guard_gap; - - /* See reasoning around the VM_SHADOW_STACK definition */ - if (vma->vm_flags & VM_SHADOW_STACK) - return PAGE_SIZE; - - return 0; -} - -static inline unsigned long vm_start_gap(struct vm_area_struct *vma) -{ - unsigned long gap = stack_guard_start_gap(vma); - unsigned long vm_start = vma->vm_start; - - vm_start -= gap; - if (vm_start > vma->vm_start) - vm_start = 0; - return vm_start; -} - -static inline unsigned long vm_end_gap(struct vm_area_struct *vma) -{ - unsigned long vm_end = vma->vm_end; - - if (vma->vm_flags & VM_GROWSUP) { - vm_end += stack_guard_gap; - if (vm_end < vma->vm_end) - vm_end = -PAGE_SIZE; - } - return vm_end; -} - -static inline int is_hugepage_only_range(struct mm_struct *mm, - unsigned long addr, unsigned long len) -{ - return 0; -} - -static inline bool vma_is_accessible(struct vm_area_struct *vma) -{ - return vma->vm_flags & VM_ACCESS_FLAGS; -} - -static inline bool capable(int cap) -{ - return true; -} - -static inline bool mlock_future_ok(const struct mm_struct *mm, - vm_flags_t vm_flags, unsigned long bytes) -{ - unsigned long locked_pages, limit_pages; - - if (!(vm_flags & VM_LOCKED) || capable(CAP_IPC_LOCK)) - return true; - - locked_pages = bytes >> PAGE_SHIFT; - locked_pages += mm->locked_vm; - - limit_pages = rlimit(RLIMIT_MEMLOCK); - limit_pages >>= PAGE_SHIFT; - - return locked_pages <= limit_pages; -} - -static inline int __anon_vma_prepare(struct vm_area_struct *vma) -{ - struct anon_vma *anon_vma = calloc(1, sizeof(struct anon_vma)); - - if (!anon_vma) - return -ENOMEM; - - anon_vma->root = anon_vma; - vma->anon_vma = anon_vma; - - return 0; -} - -static inline int anon_vma_prepare(struct vm_area_struct *vma) -{ - if (likely(vma->anon_vma)) - return 0; - - return __anon_vma_prepare(vma); -} - -static inline void userfaultfd_unmap_complete(struct mm_struct *mm, - struct list_head *uf) -{ -} - -#define ACCESS_PRIVATE(p, member) ((p)->member) - -#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) - -static __always_inline void bitmap_zero(unsigned long *dst, unsigned int nbits) -{ - unsigned int len = bitmap_size(nbits); - - if (small_const_nbits(nbits)) - *dst = 0; - else - memset(dst, 0, len); -} - -static inline bool mm_flags_test(int flag, const struct mm_struct *mm) -{ - return test_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); -} - -/* Clears all bits in the VMA flags bitmap, non-atomically. */ -static inline void vma_flags_clear_all(vma_flags_t *flags) -{ - bitmap_zero(ACCESS_PRIVATE(flags, __vma_flags), NUM_VMA_FLAG_BITS); -} - -/* - * Copy value to the first system word of VMA flags, non-atomically. - * - * IMPORTANT: This does not overwrite bytes past the first system word. The - * caller must account for this. - */ -static inline void vma_flags_overwrite_word(vma_flags_t *flags, unsigned long value) -{ - *ACCESS_PRIVATE(flags, __vma_flags) = value; -} - -/* - * Copy value to the first system word of VMA flags ONCE, non-atomically. - * - * IMPORTANT: This does not overwrite bytes past the first system word. The - * caller must account for this. - */ -static inline void vma_flags_overwrite_word_once(vma_flags_t *flags, unsigned long value) -{ - unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags); - - WRITE_ONCE(*bitmap, value); -} - -/* Update the first system word of VMA flags setting bits, non-atomically. */ -static inline void vma_flags_set_word(vma_flags_t *flags, unsigned long value) -{ - unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags); - - *bitmap |= value; -} - -/* Update the first system word of VMA flags clearing bits, non-atomically. */ -static inline void vma_flags_clear_word(vma_flags_t *flags, unsigned long value) -{ - unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags); - - *bitmap &= ~value; -} - - -/* Use when VMA is not part of the VMA tree and needs no locking */ -static inline void vm_flags_init(struct vm_area_struct *vma, - vm_flags_t flags) -{ - vma_flags_clear_all(&vma->flags); - vma_flags_overwrite_word(&vma->flags, flags); -} - -/* - * Use when VMA is part of the VMA tree and modifications need coordination - * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and - * it should be locked explicitly beforehand. - */ -static inline void vm_flags_reset(struct vm_area_struct *vma, - vm_flags_t flags) -{ - vma_assert_write_locked(vma); - vm_flags_init(vma, flags); -} - -static inline void vm_flags_reset_once(struct vm_area_struct *vma, - vm_flags_t flags) -{ - vma_assert_write_locked(vma); - /* - * The user should only be interested in avoiding reordering of - * assignment to the first word. - */ - vma_flags_clear_all(&vma->flags); - vma_flags_overwrite_word_once(&vma->flags, flags); -} - -static inline void vm_flags_set(struct vm_area_struct *vma, - vm_flags_t flags) -{ - vma_start_write(vma); - vma_flags_set_word(&vma->flags, flags); -} - -static inline void vm_flags_clear(struct vm_area_struct *vma, - vm_flags_t flags) -{ - vma_start_write(vma); - vma_flags_clear_word(&vma->flags, flags); -} - -/* - * Denies creating a writable executable mapping or gaining executable permissions. - * - * This denies the following: - * - * a) mmap(PROT_WRITE | PROT_EXEC) - * - * b) mmap(PROT_WRITE) - * mprotect(PROT_EXEC) - * - * c) mmap(PROT_WRITE) - * mprotect(PROT_READ) - * mprotect(PROT_EXEC) - * - * But allows the following: - * - * d) mmap(PROT_READ | PROT_EXEC) - * mmap(PROT_READ | PROT_EXEC | PROT_BTI) - * - * This is only applicable if the user has set the Memory-Deny-Write-Execute - * (MDWE) protection mask for the current process. - * - * @old specifies the VMA flags the VMA originally possessed, and @new the ones - * we propose to set. - * - * Return: false if proposed change is OK, true if not ok and should be denied. - */ -static inline bool map_deny_write_exec(unsigned long old, unsigned long new) -{ - /* If MDWE is disabled, we have nothing to deny. */ - if (mm_flags_test(MMF_HAS_MDWE, current->mm)) - return false; - - /* If the new VMA is not executable, we have nothing to deny. */ - if (!(new & VM_EXEC)) - return false; - - /* Under MDWE we do not accept newly writably executable VMAs... */ - if (new & VM_WRITE) - return true; - - /* ...nor previously non-executable VMAs becoming executable. */ - if (!(old & VM_EXEC)) - return true; - - return false; -} - -static inline int mapping_map_writable(struct address_space *mapping) -{ - return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? - 0 : -EPERM; -} - -static inline unsigned long move_page_tables(struct pagetable_move_control *pmc) -{ - return 0; -} - -static inline void free_pgd_range(struct mmu_gather *tlb, - unsigned long addr, unsigned long end, - unsigned long floor, unsigned long ceiling) -{ -} - -static inline int ksm_execve(struct mm_struct *mm) -{ - return 0; -} - -static inline void ksm_exit(struct mm_struct *mm) -{ -} - -static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) -{ - if (reset_refcnt) - refcount_set(&vma->vm_refcnt, 0); -} - -static inline void vma_numab_state_init(struct vm_area_struct *vma) -{ -} - -static inline void vma_numab_state_free(struct vm_area_struct *vma) -{ -} - -static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, - struct vm_area_struct *new_vma) -{ -} - -static inline void free_anon_vma_name(struct vm_area_struct *vma) -{ -} - -/* Declared in vma.h. */ -static inline void set_vma_from_desc(struct vm_area_struct *vma, - struct vm_area_desc *desc); - -static inline void mmap_action_prepare(struct mmap_action *action, - struct vm_area_desc *desc) -{ -} - -static inline int mmap_action_complete(struct mmap_action *action, - struct vm_area_struct *vma) -{ - return 0; -} - -static inline int __compat_vma_mmap(const struct file_operations *f_op, - struct file *file, struct vm_area_struct *vma) -{ - struct vm_area_desc desc = { - .mm = vma->vm_mm, - .file = file, - .start = vma->vm_start, - .end = vma->vm_end, - - .pgoff = vma->vm_pgoff, - .vm_file = vma->vm_file, - .vm_flags = vma->vm_flags, - .page_prot = vma->vm_page_prot, - - .action.type = MMAP_NOTHING, /* Default */ - }; - int err; - - err = f_op->mmap_prepare(&desc); - if (err) - return err; - - mmap_action_prepare(&desc.action, &desc); - set_vma_from_desc(vma, &desc); - return mmap_action_complete(&desc.action, vma); -} - -static inline int compat_vma_mmap(struct file *file, - struct vm_area_struct *vma) -{ - return __compat_vma_mmap(file->f_op, file, vma); -} - -/* Did the driver provide valid mmap hook configuration? */ -static inline bool can_mmap_file(struct file *file) -{ - bool has_mmap = file->f_op->mmap; - bool has_mmap_prepare = file->f_op->mmap_prepare; - - /* Hooks are mutually exclusive. */ - if (WARN_ON_ONCE(has_mmap && has_mmap_prepare)) - return false; - if (!has_mmap && !has_mmap_prepare) - return false; - - return true; -} - -static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma) -{ - if (file->f_op->mmap_prepare) - return compat_vma_mmap(file, vma); - - return file->f_op->mmap(file, vma); -} - -static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc) -{ - return file->f_op->mmap_prepare(desc); -} - -static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) -{ -} - -static inline void vma_set_file(struct vm_area_struct *vma, struct file *file) -{ - /* Changing an anonymous vma with this is illegal */ - get_file(file); - swap(vma->vm_file, file); - fput(file); -} - -static inline bool shmem_file(struct file *file) -{ - return false; -} - -static inline vm_flags_t ksm_vma_flags(const struct mm_struct *mm, - const struct file *file, vm_flags_t vm_flags) -{ - return vm_flags; -} - -static inline void remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long pfn) -{ -} - -static inline int remap_pfn_range_complete(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, unsigned long size, pgprot_t pgprot) -{ - return 0; -} +typedef unsigned long vm_flags_t; +#define pgoff_t unsigned long +typedef unsigned long pgprotval_t; +typedef struct pgprot { pgprotval_t pgprot; } pgprot_t; +typedef __bitwise unsigned int vm_fault_t; -static inline int do_munmap(struct mm_struct *, unsigned long, size_t, - struct list_head *uf) -{ - return 0; -} +#include "include/stubs.h" +#include "include/dup.h" +#include "include/custom.h" #endif /* __MM_VMA_INTERNAL_H */ |
