ring-buffer: Flush and stop persistent ring buffer on panic

On real hardware, panic and machine reboot may not flush hardware cache
to memory. This means the persistent ring buffer, which relies on a
coherent state of memory, may not have its events written to the buffer
and they may be lost. Moreover, there may be inconsistency with the
counters which are used for validation of the integrity of the
persistent ring buffer which may cause all data to be discarded.

To avoid this issue, stop recording of the ring buffer on panic and
flush the cache of the ring buffer's memory.

Fixes: e645535a95 ("tracing: Add option to use memmapped memory for trace boot instance")
Cc: stable@vger.kernel.org
Cc: Will Deacon <will@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Ian Rogers <irogers@google.com>
Link: https://patch.msgid.link/177751969602.2136606.12031934362587643488.stgit@mhiramat.tok.corp.google.com
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

arch/alpha/include/asm/Kbuild

@@ -5,4 +5,5 @@ generic-y += agp.h
 generic-y += asm-offsets.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
+generic-y += ring_buffer.h
 generic-y += text-patching.h

arch/arc/include/asm/Kbuild

@@ -5,5 +5,6 @@ generic-y += extable.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h
+generic-y += ring_buffer.h
 generic-y += user.h
 generic-y += text-patching.h

arch/arm/include/asm/Kbuild

@@ -3,6 +3,7 @@ generic-y += early_ioremap.h
 generic-y += extable.h
 generic-y += flat.h
 generic-y += parport.h
+generic-y += ring_buffer.h
 
 generated-y += mach-types.h
 generated-y += unistd-nr.h

arch/arm64/include/asm/ring_buffer.h

@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_ARM64_RING_BUFFER_H
+#define _ASM_ARM64_RING_BUFFER_H
+
+#include <asm/cacheflush.h>
+
+/* Flush D-cache on persistent ring buffer */
+#define arch_ring_buffer_flush_range(start, end)	dcache_clean_pop(start, end)
+
+#endif /* _ASM_ARM64_RING_BUFFER_H */

arch/csky/include/asm/Kbuild

@@ -9,6 +9,7 @@ generic-y += qrwlock.h
 generic-y += qrwlock_types.h
 generic-y += qspinlock.h
 generic-y += parport.h
+generic-y += ring_buffer.h
 generic-y += user.h
 generic-y += vmlinux.lds.h
 generic-y += text-patching.h

arch/hexagon/include/asm/Kbuild

@@ -5,4 +5,5 @@ generic-y += extable.h
 generic-y += iomap.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
+generic-y += ring_buffer.h
 generic-y += text-patching.h

arch/loongarch/include/asm/Kbuild

@@ -10,5 +10,6 @@ generic-y += qrwlock.h
 generic-y += user.h
 generic-y += ioctl.h
 generic-y += mmzone.h
+generic-y += ring_buffer.h
 generic-y += statfs.h
 generic-y += text-patching.h

arch/m68k/include/asm/Kbuild

@@ -3,5 +3,6 @@ generated-y += syscall_table.h
 generic-y += extable.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
+generic-y += ring_buffer.h
 generic-y += spinlock.h
 generic-y += text-patching.h

arch/microblaze/include/asm/Kbuild

@@ -5,6 +5,7 @@ generic-y += extable.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h
+generic-y += ring_buffer.h
 generic-y += syscalls.h
 generic-y += tlb.h
 generic-y += user.h

arch/mips/include/asm/Kbuild

@@ -12,5 +12,6 @@ generic-y += mcs_spinlock.h
 generic-y += parport.h
 generic-y += qrwlock.h
 generic-y += qspinlock.h
+generic-y += ring_buffer.h
 generic-y += user.h
 generic-y += text-patching.h

arch/nios2/include/asm/Kbuild

@@ -5,6 +5,7 @@ generic-y += cmpxchg.h
 generic-y += extable.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
+generic-y += ring_buffer.h
 generic-y += spinlock.h
 generic-y += user.h
 generic-y += text-patching.h

arch/openrisc/include/asm/Kbuild

@@ -8,4 +8,5 @@ generic-y += spinlock_types.h
 generic-y += spinlock.h
 generic-y += qrwlock_types.h
 generic-y += qrwlock.h
+generic-y += ring_buffer.h
 generic-y += user.h

arch/parisc/include/asm/Kbuild

@@ -4,4 +4,5 @@ generated-y += syscall_table_64.h
 generic-y += agp.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
+generic-y += ring_buffer.h
 generic-y += user.h

arch/powerpc/include/asm/Kbuild

@@ -5,4 +5,5 @@ generated-y += syscall_table_spu.h
 generic-y += agp.h
 generic-y += mcs_spinlock.h
 generic-y += qrwlock.h
+generic-y += ring_buffer.h
 generic-y += early_ioremap.h

arch/riscv/include/asm/Kbuild

@@ -14,5 +14,6 @@ generic-y += ticket_spinlock.h
 generic-y += qrwlock.h
 generic-y += qrwlock_types.h
 generic-y += qspinlock.h
+generic-y += ring_buffer.h
 generic-y += user.h
 generic-y += vmlinux.lds.h

arch/s390/include/asm/Kbuild

@@ -7,3 +7,4 @@ generated-y += unistd_nr.h
 generic-y += asm-offsets.h
 generic-y += mcs_spinlock.h
 generic-y += mmzone.h
+generic-y += ring_buffer.h

arch/sh/include/asm/Kbuild

@@ -3,4 +3,5 @@ generated-y += syscall_table.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h
+generic-y += ring_buffer.h
 generic-y += text-patching.h

arch/sparc/include/asm/Kbuild

@@ -4,4 +4,5 @@ generated-y += syscall_table_64.h
 generic-y += agp.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
+generic-y += ring_buffer.h
 generic-y += text-patching.h

arch/um/include/asm/Kbuild

@@ -17,6 +17,7 @@ generic-y += module.lds.h
 generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h
+generic-y += ring_buffer.h
 generic-y += runtime-const.h
 generic-y += softirq_stack.h
 generic-y += switch_to.h

arch/x86/include/asm/Kbuild

@@ -14,3 +14,4 @@ generic-y += early_ioremap.h
 generic-y += fprobe.h
 generic-y += mcs_spinlock.h
 generic-y += mmzone.h
+generic-y += ring_buffer.h

arch/xtensa/include/asm/Kbuild

@@ -6,5 +6,6 @@ generic-y += mcs_spinlock.h
 generic-y += parport.h
 generic-y += qrwlock.h
 generic-y += qspinlock.h
+generic-y += ring_buffer.h
 generic-y += user.h
 generic-y += text-patching.h

include/asm-generic/ring_buffer.h

@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Generic arch dependent ring_buffer macros.
+ */
+#ifndef __ASM_GENERIC_RING_BUFFER_H__
+#define __ASM_GENERIC_RING_BUFFER_H__
+
+#include <linux/cacheflush.h>
+
+/* Flush cache on ring buffer range if needed. Do nothing by default. */
+#define arch_ring_buffer_flush_range(start, end)	do { } while (0)
+
+#endif /* __ASM_GENERIC_RING_BUFFER_H__ */

kernel/trace/ring_buffer.c

@@ -7,6 +7,7 @@
 #include <linux/ring_buffer_types.h>
 #include <linux/sched/isolation.h>
 #include <linux/trace_recursion.h>
+#include <linux/panic_notifier.h>
 #include <linux/trace_events.h>
 #include <linux/ring_buffer.h>
 #include <linux/trace_clock.h>
@@ -31,6 +32,7 @@
 #include <linux/oom.h>
 #include <linux/mm.h>
 
+#include <asm/ring_buffer.h>
 #include <asm/local64.h>
 #include <asm/local.h>
 #include <asm/setup.h>
@@ -559,6 +561,7 @@ struct trace_buffer {
 
 	unsigned long			range_addr_start;
 	unsigned long			range_addr_end;
+	struct notifier_block		flush_nb;
 
 	struct ring_buffer_meta		*meta;
 
@@ -2521,6 +2524,16 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 	kfree(cpu_buffer);
 }
 
+/* Stop recording on a persistent buffer and flush cache if needed. */
+static int rb_flush_buffer_cb(struct notifier_block *nb, unsigned long event, void *data)
+{
+	struct trace_buffer *buffer = container_of(nb, struct trace_buffer, flush_nb);
+
+	ring_buffer_record_off(buffer);
+	arch_ring_buffer_flush_range(buffer->range_addr_start, buffer->range_addr_end);
+	return NOTIFY_DONE;
+}
+
 static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
 					 int order, unsigned long start,
 					 unsigned long end,
@@ -2651,6 +2664,12 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
 
 	mutex_init(&buffer->mutex);
 
+	/* Persistent ring buffer needs to flush cache before reboot. */
+	if (start && end) {
+		buffer->flush_nb.notifier_call = rb_flush_buffer_cb;
+		atomic_notifier_chain_register(&panic_notifier_list, &buffer->flush_nb);
+	}
+
 	return_ptr(buffer);
 
  fail_free_buffers:
@@ -2749,6 +2768,9 @@ ring_buffer_free(struct trace_buffer *buffer)
 {
 	int cpu;
 
+	if (buffer->range_addr_start && buffer->range_addr_end)
+		atomic_notifier_chain_unregister(&panic_notifier_list, &buffer->flush_nb);
+
 	cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
 
 	irq_work_sync(&buffer->irq_work.work);