Commit 9f564b92 authored by Björn Töpel's avatar Björn Töpel Committed by Palmer Dabbelt

riscv: Only consider swbp/ss handlers for correct privileged mode

RISC-V software breakpoint trap handlers are used for {k,u}probes.

When trapping from kernelmode, only the kernelmode handlers should be
considered. Vice versa, only usermode handlers for usermode
traps. This is not the case on RISC-V, which can trigger a bug if a
userspace process uses uprobes, and a WARN() is triggered from
kernelmode (which is implemented via {c.,}ebreak).

The kernel will trap on the kernelmode {c.,}ebreak, look for uprobes
handlers, realize incorrectly that uprobes need to be handled, and
exit the trap handler early. The trap returns to re-executing the
{c.,}ebreak, and enter an infinite trap-loop.

The issue was found running the BPF selftest [1].

Fix this issue by only considering the swbp/ss handlers for
kernel/usermode respectively. Also, move CONFIG ifdeffery from traps.c
to the asm/{k,u}probes.h headers.

Note that linux/uprobes.h only include asm/uprobes.h if CONFIG_UPROBES
is defined, which is why asm/uprobes.h needs to be unconditionally
included in traps.c

Link: https://lore.kernel.org/linux-riscv/87v8d19aun.fsf@all.your.base.are.belong.to.us/ # [1]
Fixes: 74784081 ("riscv: Add uprobes supported")
Reviewed-by: default avatarGuo Ren <guoren@kernel.org>
Reviewed-by: default avatarNam Cao <namcaov@gmail.com>
Tested-by: default avatarPuranjay Mohan <puranjay12@gmail.com>
Signed-off-by: default avatarBjörn Töpel <bjorn@rivosinc.com>
Link: https://lore.kernel.org/r/20230912065619.62020-1-bjorn@kernel.orgSigned-off-by: default avatarPalmer Dabbelt <palmer@rivosinc.com>
parent b06fab00
......@@ -40,6 +40,15 @@ void arch_remove_kprobe(struct kprobe *p);
int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr);
bool kprobe_breakpoint_handler(struct pt_regs *regs);
bool kprobe_single_step_handler(struct pt_regs *regs);
#else
static inline bool kprobe_breakpoint_handler(struct pt_regs *regs)
{
return false;
}
static inline bool kprobe_single_step_handler(struct pt_regs *regs)
{
return false;
}
#endif /* CONFIG_KPROBES */
#endif /* _ASM_RISCV_KPROBES_H */
......@@ -34,7 +34,18 @@ struct arch_uprobe {
bool simulate;
};
#ifdef CONFIG_UPROBES
bool uprobe_breakpoint_handler(struct pt_regs *regs);
bool uprobe_single_step_handler(struct pt_regs *regs);
#else
static inline bool uprobe_breakpoint_handler(struct pt_regs *regs)
{
return false;
}
static inline bool uprobe_single_step_handler(struct pt_regs *regs)
{
return false;
}
#endif /* CONFIG_UPROBES */
#endif /* _ASM_RISCV_UPROBES_H */
......@@ -13,6 +13,8 @@
#include <linux/kdebug.h>
#include <linux/uaccess.h>
#include <linux/kprobes.h>
#include <linux/uprobes.h>
#include <asm/uprobes.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/irq.h>
......@@ -247,22 +249,28 @@ static inline unsigned long get_break_insn_length(unsigned long pc)
return GET_INSN_LENGTH(insn);
}
static bool probe_single_step_handler(struct pt_regs *regs)
{
bool user = user_mode(regs);
return user ? uprobe_single_step_handler(regs) : kprobe_single_step_handler(regs);
}
static bool probe_breakpoint_handler(struct pt_regs *regs)
{
bool user = user_mode(regs);
return user ? uprobe_breakpoint_handler(regs) : kprobe_breakpoint_handler(regs);
}
void handle_break(struct pt_regs *regs)
{
#ifdef CONFIG_KPROBES
if (kprobe_single_step_handler(regs))
if (probe_single_step_handler(regs))
return;
if (kprobe_breakpoint_handler(regs))
return;
#endif
#ifdef CONFIG_UPROBES
if (uprobe_single_step_handler(regs))
if (probe_breakpoint_handler(regs))
return;
if (uprobe_breakpoint_handler(regs))
return;
#endif
current->thread.bad_cause = regs->cause;
if (user_mode(regs))
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment