diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 5113fd423cdfc049209c0ea8d250d3e1756dc796..048c655315f13a8be5678d1c2a328026ffc5b597 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -181,6 +181,16 @@ bpf_probe_read_user_str_common(void *dst, u32 size,
{
int ret;
+ /*
+ * NB: We rely on strncpy_from_user() not copying junk past the NUL
+ * terminator into `dst`.
+ *
+ * strncpy_from_user() does long-sized strides in the fast path. If the
+ * strncpy does not mask out the bytes after the NUL in `unsafe_ptr`,
+ * then there could be junk after the NUL in `dst`. If user takes `dst`
+ * and keys a hash map with it, then semantically identical strings can
+ * occupy multiple entries in the map.
+ */
ret = strncpy_from_user_nofault(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
memset(dst, 0, size);
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
index e6d5fcc2cdf3ea1143e98c417a8d617519c87434..122d8d0e253cb56eec8e423b186f968f8f862cc7 100644
--- a/lib/strncpy_from_user.c
+++ b/lib/strncpy_from_user.c
@@ -35,17 +35,32 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src,
goto byte_at_a_time;
while (max >= sizeof(unsigned long)) {
- unsigned long c, data;
+ unsigned long c, data, mask;
/* Fall back to byte-at-a-time if we get a page fault */
unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time);
- *(unsigned long *)(dst+res) = c;
+ /*
+ * Note that we mask out the bytes following the NUL. This is
+ * important to do because string oblivious code may read past
+ * the NUL. For those routines, we don't want to give them
+ * potentially random bytes after the NUL in `src`.
+ *
+ * One example of such code is BPF map keys. BPF treats map keys
+ * as an opaque set of bytes. Without the post-NUL mask, any BPF
+ * maps keyed by strings returned from strncpy_from_user() may
+ * have multiple entries for semantically identical strings.
+ */
if (has_zero(c, &data, &constants)) {
data = prep_zero_mask(c, data, &constants);
data = create_zero_mask(data);
+ mask = zero_bytemask(data);
+ *(unsigned long *)(dst+res) = c & mask;
return res + find_zero(data);
}
+
+ *(unsigned long *)(dst+res) = c;
+
res += sizeof(unsigned long);
max -= sizeof(unsigned long);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c b/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c
new file mode 100644
index 0000000000000000000000000000000000000000..e419298132b5e2d1800ca4c99a27e761235e530b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "test_probe_read_user_str.skel.h"
+
+static const char str1[] = "mestring";
+static const char str2[] = "mestringalittlebigger";
+static const char str3[] = "mestringblubblubblubblubblub";
+
+static int test_one_str(struct test_probe_read_user_str *skel, const char *str,
+ size_t len)
+{
+ int err, duration = 0;
+ char buf[256];
+
+ /* Ensure bytes after string are ones */
+ memset(buf, 1, sizeof(buf));
+ memcpy(buf, str, len);
+
+ /* Give prog our userspace pointer */
+ skel->bss->user_ptr = buf;
+
+ /* Trigger tracepoint */
+ usleep(1);
+
+ /* Did helper fail? */
+ if (CHECK(skel->bss->ret < 0, "prog_ret", "prog returned: %ld\n",
+ skel->bss->ret))
+ return 1;
+
+ /* Check that string was copied correctly */
+ err = memcmp(skel->bss->buf, str, len);
+ if (CHECK(err, "memcmp", "prog copied wrong string"))
+ return 1;
+
+ /* Now check that no extra trailing bytes were copied */
+ memset(buf, 0, sizeof(buf));
+ err = memcmp(skel->bss->buf + len, buf, sizeof(buf) - len);
+ if (CHECK(err, "memcmp", "trailing bytes were not stripped"))
+ return 1;
+
+ return 0;
+}
+
+void test_probe_read_user_str(void)
+{
+ struct test_probe_read_user_str *skel;
+ int err, duration = 0;
+
+ skel = test_probe_read_user_str__open_and_load();
+ if (CHECK(!skel, "test_probe_read_user_str__open_and_load",
+ "skeleton open and load failed\n"))
+ return;
+
+ /* Give pid to bpf prog so it doesn't read from anyone else */
+ skel->bss->pid = getpid();
+
+ err = test_probe_read_user_str__attach(skel);
+ if (CHECK(err, "test_probe_read_user_str__attach",
+ "skeleton attach failed: %d\n", err))
+ goto out;
+
+ if (test_one_str(skel, str1, sizeof(str1)))
+ goto out;
+ if (test_one_str(skel, str2, sizeof(str2)))
+ goto out;
+ if (test_one_str(skel, str3, sizeof(str3)))
+ goto out;
+
+out:
+ test_probe_read_user_str__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c
new file mode 100644
index 0000000000000000000000000000000000000000..3ae398b75dcd69b2b6102463a3c71ccd454f36f3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include <sys/types.h>
+
+pid_t pid = 0;
+long ret = 0;
+void *user_ptr = 0;
+char buf[256] = {};
+
+SEC("tracepoint/syscalls/sys_enter_nanosleep")
+int on_write(void *ctx)
+{
+ if (pid != (bpf_get_current_pid_tgid() >> 32))
+ return 0;
+
+ ret = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";