The kernel refuses to attach to a nop10 that crosses a page boundary,
since it can't be atomically rewritten:
/* can_optimize(), arch/x86/kernel/uprobes.c */
/* We can't do cross page atomic writes yet. */
return PAGE_SIZE - (vaddr & ~PAGE_MASK) >= OPT_INSN_SIZE;
Whether the nop10 crosses a page is purely up to the binary layout, so
this does happen in practice. libbpf doesn't check for it and blindly
shifts the uprobe onto the nop10, and the attach then fails with
-ENOTSUPP. Just keep the uprobe on the preceding 1-byte nop in that
case, it works everywhere as a regular int3 uprobe.
Fixes: 41a5c7df4466 ("libbpf: Add support to detect nop,nop5 instructions combo
for usdt probe")
Signed-off-by: Jiayuan Chen <[email protected]>
---
tools/lib/bpf/usdt.c | 23 +++++++++++++++++++++--
1 file changed, 21 insertions(+), 2 deletions(-)
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index 2e56e3ab5b6c..c266ac93cbdd 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -614,11 +614,28 @@ static bool has_nop_combo(int fd, long off)
return false;
return memcmp(buf, nop_combo, 11) == 0;
}
+
+/*
+ * The kernel refuses to attach to a nop10 that crosses a page boundary,
+ * as it can't be atomically rewritten. Page offset of the probe is the
+ * same in the file and in any mapping, so this can be checked statically.
+ */
+static bool nop10_within_page(long off)
+{
+ long page_sz = getpagesize();
+
+ return off % page_sz + 10 <= page_sz;
+}
#else
static bool has_nop_combo(int fd, long off)
{
return false;
}
+
+static bool nop10_within_page(long off)
+{
+ return false;
+}
#endif
static int collect_usdt_targets(struct usdt_manager *man, struct elf_fd
*elf_fd, const char *path,
@@ -827,9 +844,11 @@ static int collect_usdt_targets(struct usdt_manager *man,
struct elf_fd *elf_fd,
/*
* We have uprobe syscall and usdt with nop,nop10 instructions
combo,
* so we can place the uprobe directly on nop10 (+1) and get
this probe
- * optimized.
+ * optimized. If the nop10 crosses a page boundary, keep the
uprobe
+ * on the preceding 1-byte nop, which the kernel accepts
everywhere.
*/
- if (man->has_uprobe_syscall && has_nop_combo(elf_fd->fd,
usdt_rel_ip)) {
+ if (man->has_uprobe_syscall && has_nop_combo(elf_fd->fd,
usdt_rel_ip) &&
+ nop10_within_page(usdt_rel_ip + 1)) {
usdt_abs_ip++;
usdt_rel_ip++;
}
--
2.43.0
