[PATCH 1/3] perf/core: Make sure the ring-buffer is mapped in all page-tables

[Joerg Roedel]

From: Joerg Roedel <jroedel@xxxxxxx>

The ring-buffer is accessed in the NMI handler, so we better
avoid faulting on it. Sync the vmalloc range with all
page-tables in system to make sure everyone has it mapped.

This fixes a WARN_ON_ONCE() that can be triggered with PTI
enabled on x86-32:

	WARNING: CPU: 4 PID: 0 at arch/x86/mm/fault.c:320 vmalloc_fault+0x220/0x230

This triggers because with PTI enabled on an PAE kernel the
PMDs are no longer shared between the page-tables, so the
vmalloc changes do not propagate automatically.

Signed-off-by: Joerg Roedel <jroedel@xxxxxxx>
---
 kernel/events/ring_buffer.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 5d3cf40..7b0e9aa 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -814,6 +814,9 @@ static void rb_free_work(struct work_struct *work)
 
 	vfree(base);
 	kfree(rb);
+
+	/* Make sure buffer is unmapped in all page-tables */
+	vmalloc_sync_all();
 }
 
 void rb_free(struct ring_buffer *rb)
@@ -840,6 +843,13 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	if (!all_buf)
 		goto fail_all_buf;
 
+	/*
+	 * The buffer is accessed in NMI handlers, make sure it is
+	 * mapped in all page-tables in the system so that we don't
+	 * fault on the range in an NMI handler.
+	 */
+	vmalloc_sync_all();
+
 	rb->user_page = all_buf;
 	rb->data_pages[0] = all_buf + PAGE_SIZE;
 	if (nr_pages) {
-- 
2.7.4