kexec can leave MMU registers set when booting into a new kernel, PIDR in particular. The boot sequence does not zero PIDR, so it only gets set when CPUs first switch to a userspace processes (until then it's running a kernel thread with effective PID = 0).
This leaves a window where a process table entry and page tables are set up due to user processes running on other CPUs, that happen to match with a stale PID. The CPU with that PID may cause speculative accesses that address quadrant 0, which will result in cached translations and PWC for that process, on a CPU which is not in the mm_cpumask and so they will not get invalidated properly. The most common result is the kernel hanging in infinite page fault loops soon after kexec (usually in schedule_tail, which is usually the first non-speculative quardant 0 access to a new PID) due to a stale PWC. However being a stale translation error, it could result in anything up to security and data corruption problems. Fix this by zeroing out PIDR at boot and kexec. Signed-off-by: Nicholas Piggin <npig...@gmail.com> --- v3: do the register clearing in the early CPU setup code, suggested by Michael Ellerman, which already clears LPID. arch/powerpc/kernel/cpu_setup_power.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 610955fe8b81..679bbe714e85 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -102,6 +102,7 @@ _GLOBAL(__setup_cpu_power9) li r0,0 mtspr SPRN_PSSCR,r0 mtspr SPRN_LPID,r0 + mtspr SPRN_PID,r0 mfspr r3,SPRN_LPCR LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC) or r3, r3, r4 @@ -126,6 +127,7 @@ _GLOBAL(__restore_cpu_power9) li r0,0 mtspr SPRN_PSSCR,r0 mtspr SPRN_LPID,r0 + mtspr SPRN_PID,r0 mfspr r3,SPRN_LPCR LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC) or r3, r3, r4 -- 2.15.0