s390: add stack for machine check handler

The previous code used the normal kernel stack for machine checks.
This is problematic when a machine check interrupts a system call
or interrupt handler right at the beginning where registers are set up.

Assume system_call is interrupted at the first instruction and a machine
check is triggered. The machine check handler is called, checks the PSW
to see whether it is coming from user space, notices that it is already
in kernel mode but %r15 still contains the user space stack. This would
lead to a kernel crash.

There are basically two ways of fixing that: Either using the 'critical
cleanup' approach which compares the address in the PSW to see whether
it is already at a point where the stack has been set up, or use an extra
stack for the machine check handler.

For simplicity, we will go with the second approach and allocate an extra
stack. This adds some memory overhead for large systems, but usually large
system have plenty of memory so this isn't really a concern. But it keeps
the mchk stack setup simple and less error prone.

Fixes: 0b0ed657fe00 ("s390: remove critical section cleanup from entry.S")
Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Cc: <stable@kernel.org> # v5.8+
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>

1 files changed, 11 insertions, 6 deletions

diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index c5abbb94ac6e..e299892440b6 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -189,7 +189,7 @@ static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit)
 
 static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 {
-	unsigned long async_stack, nodat_stack;
+	unsigned long async_stack, nodat_stack, mcck_stack;
 	struct lowcore *lc;
 
 	if (pcpu != &pcpu_devices[0]) {
@@ -202,13 +202,15 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 		nodat_stack = pcpu->lowcore->nodat_stack - STACK_INIT_OFFSET;
 	}
 	async_stack = stack_alloc();
-	if (!async_stack)
-		goto out;
+	mcck_stack = stack_alloc();
+	if (!async_stack || !mcck_stack)
+		goto out_stack;
 	lc = pcpu->lowcore;
 	memcpy(lc, &S390_lowcore, 512);
 	memset((char *) lc + 512, 0, sizeof(*lc) - 512);
 	lc->async_stack = async_stack + STACK_INIT_OFFSET;
 	lc->nodat_stack = nodat_stack + STACK_INIT_OFFSET;
+	lc->mcck_stack = mcck_stack + STACK_INIT_OFFSET;
 	lc->cpu_nr = cpu;
 	lc->spinlock_lockval = arch_spin_lockval(cpu);
 	lc->spinlock_index = 0;
@@ -216,12 +218,13 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 	lc->return_lpswe = gen_lpswe(__LC_RETURN_PSW);
 	lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
 	if (nmi_alloc_per_cpu(lc))
-		goto out_async;
+		goto out_stack;
 	lowcore_ptr[cpu] = lc;
 	pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, (u32)(unsigned long) lc);
 	return 0;
 
-out_async:
+out_stack:
+	stack_free(mcck_stack);
 	stack_free(async_stack);
 out:
 	if (pcpu != &pcpu_devices[0]) {
@@ -233,16 +236,18 @@ out:
 
 static void pcpu_free_lowcore(struct pcpu *pcpu)
 {
-	unsigned long async_stack, nodat_stack, lowcore;
+	unsigned long async_stack, nodat_stack, mcck_stack, lowcore;
 
 	nodat_stack = pcpu->lowcore->nodat_stack - STACK_INIT_OFFSET;
 	async_stack = pcpu->lowcore->async_stack - STACK_INIT_OFFSET;
+	mcck_stack = pcpu->lowcore->mcck_stack - STACK_INIT_OFFSET;
 	lowcore = (unsigned long) pcpu->lowcore;
 
 	pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, 0);
 	lowcore_ptr[pcpu - pcpu_devices] = NULL;
 	nmi_free_per_cpu(pcpu->lowcore);
 	stack_free(async_stack);
+	stack_free(mcck_stack);
 	if (pcpu == &pcpu_devices[0])
 		return;
 	free_pages(nodat_stack, THREAD_SIZE_ORDER);