diff options
| author | Lai Jiangshan <laijs@linux.alibaba.com> | 2021-02-04 18:27:06 +0300 |
|---|---|---|
| committer | Thomas Gleixner <tglx@linutronix.de> | 2021-02-05 22:13:11 +0300 |
| commit | c4bed4b96918ff1d062ee81fdae4d207da4fa9b0 (patch) | |
| tree | c5fc2afad245c4b6f8116a139fbc3e5e2a8df1f5 | |
| parent | 25a068b8e9a4eb193d755d58efcb3c98928636e0 (diff) | |
| download | linux-c4bed4b96918ff1d062ee81fdae4d207da4fa9b0.tar.xz | |
x86/debug: Prevent data breakpoints on __per_cpu_offset
When FSGSBASE is enabled, paranoid_entry() fetches the per-CPU GSBASE value
via __per_cpu_offset or pcpu_unit_offsets.
When a data breakpoint is set on __per_cpu_offset[cpu] (read-write
operation), the specific CPU will be stuck in an infinite #DB loop.
RCU will try to send an NMI to the specific CPU, but it is not working
either since NMI also relies on paranoid_entry(). Which means it's
undebuggable.
Fixes: eaad981291ee3("x86/entry/64: Introduce the FIND_PERCPU_BASE macro")
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20210204152708.21308-1-jiangshanlai@gmail.com
| -rw-r--r-- | arch/x86/kernel/hw_breakpoint.c | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 6694c0f8e6c1..012ed82e5bd3 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -269,6 +269,20 @@ static inline bool within_cpu_entry(unsigned long addr, unsigned long end) CPU_ENTRY_AREA_TOTAL_SIZE)) return true; + /* + * When FSGSBASE is enabled, paranoid_entry() fetches the per-CPU + * GSBASE value via __per_cpu_offset or pcpu_unit_offsets. + */ +#ifdef CONFIG_SMP + if (within_area(addr, end, (unsigned long)__per_cpu_offset, + sizeof(unsigned long) * nr_cpu_ids)) + return true; +#else + if (within_area(addr, end, (unsigned long)&pcpu_unit_offsets, + sizeof(pcpu_unit_offsets))) + return true; +#endif + for_each_possible_cpu(cpu) { /* The original rw GDT is being used after load_direct_gdt() */ if (within_area(addr, end, (unsigned long)get_cpu_gdt_rw(cpu), |