From: "Alexei Starovoitov" <alexei.starovoitov@gmail.com>
To: <rtm@csail.mit.edu>, "Daniel Borkmann" <daniel@iogearbox.net>,
"John Fastabend" <john.fastabend@gmail.com>
Cc: <bpf@vger.kernel.org>
Subject: Re: a riscv ebpf uprobe can wedge the machine by writing pt_regs.status
Date: Mon, 16 Nov 2026 18:47:41 +0000 [thread overview]
Message-ID: <DMWUY4M0QXMH.33XAPR76ZXKRT@gmail.com> (raw)
In-Reply-To: <30318.1794850523@30-11-166.wireless.csail.mit.edu>
On Mon, Nov 16, 2026 at 09:35 AM rtm@csail.mit.edu <rtm@csail.mit.edu> wrote:
> On riscv, kprobe_prog_is_valid_access() allows a "uprobe" ebpf program
> to write ctx at offset 256, which is pt_regs.status. When returning to
> user space, ret_from_exception copies whatever value the ebpf program
> provided to the CPU's sstatus. One way this can cause trouble is if
> the ebpf program sets sstatus.SPP to 1, indicating that the trap
> should return to user space in supervisor mode rather than user mode.
Yes. It's a real bug, and it's not only riscv.
The exit path trusts some of the fields. ptrace guards the same fields:
arch field exit path ptrace
------ ------ ------------------------------ -------------------
riscv status csrw CSR_STATUS, a0 not in the regset
arm64 pstate msr spsr_el1, x22 valid_user_regs()
x86-64 cs, ss (cs & 3) == 0: iretq to ring 0 set_segment_reg()
x86-64 flags iretq loads IF and IOPL set_flags()
A uprobe prog should write only the registers that ptrace sets to any
value. The verifier can reject the other offsets at load time.
Each arch lists its registers. An arch without a list gets no writes.
flags and pstate become read-only, the condition bits too.
Jiri,
pls commandeer the following:
diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c
index 2a9b0bc..1e6ac47 100644
--- a/arch/arm64/kernel/probes/uprobes.c
+++ b/arch/arm64/kernel/probes/uprobes.c
@@ -152,6 +152,12 @@ bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
return regs->sp < ret->stack;
}
+bool arch_uprobe_regs_writable(int off, int size)
+{
+ /* From x0 to x30, sp, pc. */
+ return off + size <= offsetof(struct pt_regs, pstate);
+}
+
unsigned long
arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr,
struct pt_regs *regs)
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
index eb177d0..dbb1534 100644
--- a/arch/riscv/kernel/probes/uprobes.c
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -126,6 +126,12 @@ bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
return regs->sp < ret->stack;
}
+bool arch_uprobe_regs_writable(int off, int size)
+{
+ /* epc, from ra to t6. */
+ return off + size <= offsetof(struct pt_regs, status);
+}
+
unsigned long
arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr,
struct pt_regs *regs)
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 0f60c0d..fc07bcd 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -1888,6 +1888,21 @@ bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
return regs->sp <= ret->stack;
}
+bool arch_uprobe_regs_writable(int off, int size)
+{
+ int end = off + size;
+
+ /* The 32-bit pt_regs has segments in front of orig_ax. */
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return false;
+ /* From r15 to di. Not orig_ax, cs, flags, ss. */
+ if (end <= offsetof(struct pt_regs, orig_ax))
+ return true;
+ if (off >= offsetof(struct pt_regs, ip) && end <= offsetofend(struct pt_regs, ip))
+ return true;
+ return off >= offsetof(struct pt_regs, sp) && end <= offsetofend(struct pt_regs, sp);
+}
+
/*
* Heuristic-based check if uprobe is installed at the function entry.
*
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index d34dbc0..43b250b 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -239,6 +239,7 @@ extern void uprobe_copy_from_page(struct page *page, unsigned long vaddr, void *
extern void handle_syscall_uprobe(struct pt_regs *regs, unsigned long bp_vaddr);
extern void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr);
extern unsigned long arch_uprobe_get_xol_area(void);
+extern bool arch_uprobe_regs_writable(int off, int size);
#else /* !CONFIG_UPROBES */
struct uprobes_state {
};
@@ -300,5 +301,9 @@ static inline void uprobe_copy_process(struct task_struct *t, u64 flags)
static inline void uprobe_clear_state(struct mm_struct *mm)
{
}
+static inline bool arch_uprobe_regs_writable(int off, int size)
+{
+ return false;
+}
#endif /* !CONFIG_UPROBES */
#endif /* _LINUX_UPROBES_H */
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index caf4447..c47b1ee 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -2703,6 +2703,15 @@ void __weak arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vadd
{
}
+/*
+ * Can a bpf prog write these bytes of pt_regs? An arch opts in and lists the
+ * registers that ptrace can set to any value.
+ */
+bool __weak arch_uprobe_regs_writable(int off, int size)
+{
+ return false;
+}
+
/*
* Run handler and ask thread to singlestep.
* Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index b4ff9d4..4f1be6c 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1398,8 +1398,16 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type
if (off + size > sizeof(struct pt_regs))
return false;
- if (type == BPF_WRITE)
+ if (type == BPF_WRITE) {
+ /*
+ * pt_regs also holds what the kernel restores on the way to
+ * user space: cs and flags on x86, pstate on arm64, status on
+ * riscv. A prog can write the registers of the task only.
+ */
+ if (!arch_uprobe_regs_writable(off, size))
+ return false;
prog->aux->kprobe_write_ctx = true;
+ }
return true;
}
prev parent reply other threads:[~2026-11-16 18:47 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-16 17:35 a riscv ebpf uprobe can wedge the machine by writing pt_regs.status rtm
2026-11-16 18:37 ` Andrii Nakryiko
2026-11-16 18:47 ` Alexei Starovoitov [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=DMWUY4M0QXMH.33XAPR76ZXKRT@gmail.com \
--to=alexei.starovoitov@gmail.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=john.fastabend@gmail.com \
--cc=rtm@csail.mit.edu \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox