summaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
authorAlexei Starovoitov <ast@kernel.org>2024-09-11 09:58:31 -0700
committerAlexei Starovoitov <ast@kernel.org>2024-09-11 09:58:32 -0700
commitf765274d0c9436bc130911abbd97e52b1648d13c (patch)
tree81f62219b389a87056cc64f6d14b29c0189cd566 /tools
parent58ff04e2e22319e63ea646d9a38890c17836a7f6 (diff)
parent3c217a182018e6c6d381b3fdc32626275eefbfb0 (diff)
Merge branch 'harden-and-extend-elf-build-id-parsing-logic'
Andrii Nakryiko says: ==================== Harden and extend ELF build ID parsing logic The goal of this patch set is to extend existing ELF build ID parsing logic, currently mostly used by BPF subsystem, with support for working in sleepable mode in which memory faults are allowed and can be relied upon to fetch relevant parts of ELF file to find and fetch .note.gnu.build-id information. This is useful and important for BPF subsystem itself, but also for PROCMAP_QUERY ioctl(), built atop of /proc/<pid>/maps functionality (see [0]), which makes use of the same build_id_parse() functionality. PROCMAP_QUERY is always called from sleepable user process context, so it doesn't have to suffer from current restrictions of build_id_parse() which are due to the NMI context assumption. Along the way, we harden the logic to avoid TOCTOU, overflow, out-of-bounds access problems. This is the very first patch, which can be backported to older releases, if necessary. We also lift existing limitations of only working as long as ELF program headers and build ID note section is contained strictly within the very first page of ELF file. We achieve all of the above without duplication of logic between sleepable and non-sleepable modes through freader abstraction that manages underlying folio from page cache (on demand) and gives a simple to use direct memory access interface. With that, single page restrictions and adding sleepable mode support is rather straightforward. We also extend existing set of BPF selftests with a few tests targeting build ID logic across sleepable and non-sleepabe contexts (we utilize sleepable and non-sleepable uprobes for that). [0] https://lore.kernel.org/linux-mm/20240627170900.1672542-4-andrii@kernel.org/ v6->v7: - added filemap_invalidate_{lock,unlock}_shared() around read_cache_folio and kept Eduard's Reviewed-by (Eduard); v5->v6: - use local phnum variable in get_build_id_32() (Jann); - switch memcmp() instead of strcmp() in parse_build_id() (Jann); v4->v5: - pass proper file reference to read_cache_folio() (Shakeel); - fix another potential overflow due to two u32 additions (Andi); - add PageUptodate() check to patch #1 (Jann); v3->v4: - fix few more potential overflow and out-of-bounds access issues (Andi); - use purely folio-based implementation for freader (Matthew); v2->v3: - remove unneeded READ_ONCE()s and force phoff to u64 for 32-bit mode (Andi); - moved hardening fixes to the front for easier backporting (Jann); - call freader_cleanup() from build_id_parse_buf() for consistency (Jiri); v1->v2: - ensure MADV_PAGEOUT works reliably by paging data in first (Shakeel); - to fix BPF CI build optionally define MADV_POPULATE_READ in selftest. ==================== Link: https://lore.kernel.org/r/20240829174232.3133883-1-andrii@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'tools')
-rw-r--r--tools/testing/selftests/bpf/Makefile5
-rw-r--r--tools/testing/selftests/bpf/prog_tests/build_id.c118
-rw-r--r--tools/testing/selftests/bpf/progs/test_build_id.c31
-rw-r--r--tools/testing/selftests/bpf/uprobe_multi.c41
-rw-r--r--tools/testing/selftests/bpf/uprobe_multi.ld11
5 files changed, 204 insertions, 2 deletions
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 04716a5e43f1..f04af11df8eb 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -845,9 +845,10 @@ $(OUTPUT)/veristat: $(OUTPUT)/veristat.o
# Linking uprobe_multi can fail due to relocation overflows on mips.
$(OUTPUT)/uprobe_multi: CFLAGS += $(if $(filter mips, $(ARCH)),-mxgot)
-$(OUTPUT)/uprobe_multi: uprobe_multi.c
+$(OUTPUT)/uprobe_multi: uprobe_multi.c uprobe_multi.ld
$(call msg,BINARY,,$@)
- $(Q)$(CC) $(CFLAGS) -O0 $(LDFLAGS) $^ $(LDLIBS) -o $@
+ $(Q)$(CC) $(CFLAGS) -Wl,-T,uprobe_multi.ld -O0 $(LDFLAGS) \
+ $(filter-out %.ld,$^) $(LDLIBS) -o $@
EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \
prog_tests/tests.h map_tests/tests.h verifier/tests.h \
diff --git a/tools/testing/selftests/bpf/prog_tests/build_id.c b/tools/testing/selftests/bpf/prog_tests/build_id.c
new file mode 100644
index 000000000000..aec9c8d6bc96
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/build_id.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+
+#include "test_build_id.skel.h"
+
+static char build_id[BPF_BUILD_ID_SIZE];
+static int build_id_sz;
+
+static void print_stack(struct bpf_stack_build_id *stack, int frame_cnt)
+{
+ int i, j;
+
+ for (i = 0; i < frame_cnt; i++) {
+ printf("FRAME #%02d: ", i);
+ switch (stack[i].status) {
+ case BPF_STACK_BUILD_ID_EMPTY:
+ printf("<EMPTY>\n");
+ break;
+ case BPF_STACK_BUILD_ID_VALID:
+ printf("BUILD ID = ");
+ for (j = 0; j < BPF_BUILD_ID_SIZE; j++)
+ printf("%02hhx", (unsigned)stack[i].build_id[j]);
+ printf(" OFFSET = %llx", (unsigned long long)stack[i].offset);
+ break;
+ case BPF_STACK_BUILD_ID_IP:
+ printf("IP = %llx", (unsigned long long)stack[i].ip);
+ break;
+ default:
+ printf("UNEXPECTED STATUS %d ", stack[i].status);
+ break;
+ }
+ printf("\n");
+ }
+}
+
+static void subtest_nofault(bool build_id_resident)
+{
+ struct test_build_id *skel;
+ struct bpf_stack_build_id *stack;
+ int frame_cnt;
+
+ skel = test_build_id__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ skel->links.uprobe_nofault = bpf_program__attach(skel->progs.uprobe_nofault);
+ if (!ASSERT_OK_PTR(skel->links.uprobe_nofault, "link"))
+ goto cleanup;
+
+ if (build_id_resident)
+ ASSERT_OK(system("./uprobe_multi uprobe-paged-in"), "trigger_uprobe");
+ else
+ ASSERT_OK(system("./uprobe_multi uprobe-paged-out"), "trigger_uprobe");
+
+ if (!ASSERT_GT(skel->bss->res_nofault, 0, "res"))
+ goto cleanup;
+
+ stack = skel->bss->stack_nofault;
+ frame_cnt = skel->bss->res_nofault / sizeof(struct bpf_stack_build_id);
+ if (env.verbosity >= VERBOSE_NORMAL)
+ print_stack(stack, frame_cnt);
+
+ if (build_id_resident) {
+ ASSERT_EQ(stack[0].status, BPF_STACK_BUILD_ID_VALID, "build_id_status");
+ ASSERT_EQ(memcmp(stack[0].build_id, build_id, build_id_sz), 0, "build_id_match");
+ } else {
+ ASSERT_EQ(stack[0].status, BPF_STACK_BUILD_ID_IP, "build_id_status");
+ }
+
+cleanup:
+ test_build_id__destroy(skel);
+}
+
+static void subtest_sleepable(void)
+{
+ struct test_build_id *skel;
+ struct bpf_stack_build_id *stack;
+ int frame_cnt;
+
+ skel = test_build_id__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ skel->links.uprobe_sleepable = bpf_program__attach(skel->progs.uprobe_sleepable);
+ if (!ASSERT_OK_PTR(skel->links.uprobe_sleepable, "link"))
+ goto cleanup;
+
+ /* force build ID to not be paged in */
+ ASSERT_OK(system("./uprobe_multi uprobe-paged-out"), "trigger_uprobe");
+
+ if (!ASSERT_GT(skel->bss->res_sleepable, 0, "res"))
+ goto cleanup;
+
+ stack = skel->bss->stack_sleepable;
+ frame_cnt = skel->bss->res_sleepable / sizeof(struct bpf_stack_build_id);
+ if (env.verbosity >= VERBOSE_NORMAL)
+ print_stack(stack, frame_cnt);
+
+ ASSERT_EQ(stack[0].status, BPF_STACK_BUILD_ID_VALID, "build_id_status");
+ ASSERT_EQ(memcmp(stack[0].build_id, build_id, build_id_sz), 0, "build_id_match");
+
+cleanup:
+ test_build_id__destroy(skel);
+}
+
+void serial_test_build_id(void)
+{
+ build_id_sz = read_build_id("uprobe_multi", build_id, sizeof(build_id));
+ ASSERT_EQ(build_id_sz, BPF_BUILD_ID_SIZE, "parse_build_id");
+
+ if (test__start_subtest("nofault-paged-out"))
+ subtest_nofault(false /* not resident */);
+ if (test__start_subtest("nofault-paged-in"))
+ subtest_nofault(true /* resident */);
+ if (test__start_subtest("sleepable"))
+ subtest_sleepable();
+}
diff --git a/tools/testing/selftests/bpf/progs/test_build_id.c b/tools/testing/selftests/bpf/progs/test_build_id.c
new file mode 100644
index 000000000000..32ce59f9aa27
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_build_id.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct bpf_stack_build_id stack_sleepable[128];
+int res_sleepable;
+
+struct bpf_stack_build_id stack_nofault[128];
+int res_nofault;
+
+SEC("uprobe.multi/./uprobe_multi:uprobe")
+int uprobe_nofault(struct pt_regs *ctx)
+{
+ res_nofault = bpf_get_stack(ctx, stack_nofault, sizeof(stack_nofault),
+ BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+
+ return 0;
+}
+
+SEC("uprobe.multi.s/./uprobe_multi:uprobe")
+int uprobe_sleepable(struct pt_regs *ctx)
+{
+ res_sleepable = bpf_get_stack(ctx, stack_sleepable, sizeof(stack_sleepable),
+ BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/uprobe_multi.c b/tools/testing/selftests/bpf/uprobe_multi.c
index 7ffa563ffeba..c7828b13e5ff 100644
--- a/tools/testing/selftests/bpf/uprobe_multi.c
+++ b/tools/testing/selftests/bpf/uprobe_multi.c
@@ -2,8 +2,21 @@
#include <stdio.h>
#include <string.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <sys/mman.h>
+#include <unistd.h>
#include <sdt.h>
+#ifndef MADV_POPULATE_READ
+#define MADV_POPULATE_READ 22
+#endif
+
+int __attribute__((weak)) uprobe(void)
+{
+ return 0;
+}
+
#define __PASTE(a, b) a##b
#define PASTE(a, b) __PASTE(a, b)
@@ -75,6 +88,30 @@ static int usdt(void)
return 0;
}
+extern char build_id_start[];
+extern char build_id_end[];
+
+int __attribute__((weak)) trigger_uprobe(bool build_id_resident)
+{
+ int page_sz = sysconf(_SC_PAGESIZE);
+ void *addr;
+
+ /* page-align build ID start */
+ addr = (void *)((uintptr_t)&build_id_start & ~(page_sz - 1));
+
+ /* to guarantee MADV_PAGEOUT work reliably, we need to ensure that
+ * memory range is mapped into current process, so we unconditionally
+ * do MADV_POPULATE_READ, and then MADV_PAGEOUT, if necessary
+ */
+ madvise(addr, page_sz, MADV_POPULATE_READ);
+ if (!build_id_resident)
+ madvise(addr, page_sz, MADV_PAGEOUT);
+
+ (void)uprobe();
+
+ return 0;
+}
+
int main(int argc, char **argv)
{
if (argc != 2)
@@ -84,6 +121,10 @@ int main(int argc, char **argv)
return bench();
if (!strcmp("usdt", argv[1]))
return usdt();
+ if (!strcmp("uprobe-paged-out", argv[1]))
+ return trigger_uprobe(false /* page-out build ID */);
+ if (!strcmp("uprobe-paged-in", argv[1]))
+ return trigger_uprobe(true /* page-in build ID */);
error:
fprintf(stderr, "usage: %s <bench|usdt>\n", argv[0]);
diff --git a/tools/testing/selftests/bpf/uprobe_multi.ld b/tools/testing/selftests/bpf/uprobe_multi.ld
new file mode 100644
index 000000000000..a2e94828bc8c
--- /dev/null
+++ b/tools/testing/selftests/bpf/uprobe_multi.ld
@@ -0,0 +1,11 @@
+SECTIONS
+{
+ . = ALIGN(4096);
+ .note.gnu.build-id : { *(.note.gnu.build-id) }
+ . = ALIGN(4096);
+}
+INSERT AFTER .text;
+
+build_id_start = ADDR(.note.gnu.build-id);
+build_id_end = ADDR(.note.gnu.build-id) + SIZEOF(.note.gnu.build-id);
+