powerpc: Avoid nmi_enter/nmi_exit in real mode interrupt.

nmi_enter()/nmi_exit() touches per cpu variables which can lead to kernel
crash when invoked during real mode interrupt handling (e.g. early HMI/MCE
interrupt handler) if percpu allocation comes from vmalloc area.

Early HMI/MCE handlers are called through DEFINE_INTERRUPT_HANDLER_NMI()
wrapper which invokes nmi_enter/nmi_exit calls. We don't see any issue when
percpu allocation is from the embedded first chunk. However with
CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK enabled there are chances where percpu
allocation can come from the vmalloc area.

With kernel command line "percpu_alloc=page" we can force percpu allocation
to come from vmalloc area and can see kernel crash in machine_check_early:

[    1.215714] NIP [c000000000e49eb4] rcu_nmi_enter+0x24/0x110
[    1.215717] LR [c0000000000461a0] machine_check_early+0xf0/0x2c0
[    1.215719] --- interrupt: 200
[    1.215720] [c000000fffd73180] [0000000000000000] 0x0 (unreliable)
[    1.215722] [c000000fffd731b0] [0000000000000000] 0x0
[    1.215724] [c000000fffd73210] [c000000000008364] machine_check_early_common+0x134/0x1f8

Fix this by avoiding use of nmi_enter()/nmi_exit() in real mode if percpu
first chunk is not embedded.

Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Shirisha Ganta <shirisha@linux.ibm.com>
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240410043006.81577-1-mahesh@linux.ibm.com

3 files changed, 22 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 7b610864b364..2d6c886b40f4 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -336,6 +336,14 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte
 	if (IS_ENABLED(CONFIG_KASAN))
 		return;
 
+	/*
+	 * Likewise, do not use it in real mode if percpu first chunk is not
+	 * embedded. With CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK enabled there
+	 * are chances where percpu allocation can come from vmalloc area.
+	 */
+	if (percpu_first_chunk_is_paged)
+		return;
+
 	/* Otherwise, it should be safe to call it */
 	nmi_enter();
 }
@@ -351,6 +359,8 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter
 		// no nmi_exit for a pseries hash guest taking a real mode exception
 	} else if (IS_ENABLED(CONFIG_KASAN)) {
 		// no nmi_exit for KASAN in real mode
+	} else if (percpu_first_chunk_is_paged) {
+		// no nmi_exit if percpu first chunk is not embedded
 	} else {
 		nmi_exit();
 	}
diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h
index 8e5b7d0b851c..634970ce13c6 100644
--- a/arch/powerpc/include/asm/percpu.h
+++ b/arch/powerpc/include/asm/percpu.h
@@ -15,6 +15,16 @@
 #endif /* CONFIG_SMP */
 #endif /* __powerpc64__ */
 
+#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) && defined(CONFIG_SMP)
+#include <linux/jump_label.h>
+DECLARE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged);
+
+#define percpu_first_chunk_is_paged	\
+		(static_key_enabled(&__percpu_first_chunk_is_paged.key))
+#else
+#define percpu_first_chunk_is_paged	false
+#endif /* CONFIG_PPC64 && CONFIG_SMP */
+
 #include <asm-generic/percpu.h>
 
 #include <asm/paca.h>
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 2f19d5e94485..ae36a129789f 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -834,6 +834,7 @@ static __init int pcpu_cpu_to_node(int cpu)
 
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
+DEFINE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged);
 
 void __init setup_per_cpu_areas(void)
 {
@@ -876,6 +877,7 @@ void __init setup_per_cpu_areas(void)
 	if (rc < 0)
 		panic("cannot initialize percpu area (err=%d)", rc);
 
+	static_key_enable(&__percpu_first_chunk_is_paged.key);
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu) {
                 __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];