[SRU][B][PATCH 1/5] Revert "perf/core: Make sure the ring-buffer is mapped in all page-tables"

[Andrea Righi]

From: Joerg Roedel <jroedel at suse.de>

BugLink: https://bugs.launchpad.net/bugs/1827884

This reverts commit 77754cfa09a6c528c38cbca9ee4cc4f7cf6ad6f2.

The patch was necessary to silence a WARN_ON_ONCE(in_nmi())
that triggered in the vmalloc_fault() function when PTI was
enabled on x86-32.

Faulting in an NMI handler turned out to be safe and the
warning in vmalloc_fault() is gone now. So the above patch
can be reverted.

Signed-off-by: Joerg Roedel <jroedel at suse.de>
Signed-off-by: Thomas Gleixner <tglx at linutronix.de>
Tested-by: David H. Gutteridge <dhgutteridge at sympatico.ca>
Cc: "H . Peter Anvin" <hpa at zytor.com>
Cc: linux-mm at kvack.org
Cc: Linus Torvalds <torvalds at linux-foundation.org>
Cc: Andy Lutomirski <luto at kernel.org>
Cc: Dave Hansen <dave.hansen at intel.com>
Cc: Josh Poimboeuf <jpoimboe at redhat.com>
Cc: Juergen Gross <jgross at suse.com>
Cc: Peter Zijlstra <peterz at infradead.org>
Cc: Borislav Petkov <bp at alien8.de>
Cc: Jiri Kosina <jkosina at suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky at oracle.com>
Cc: Brian Gerst <brgerst at gmail.com>
Cc: David Laight <David.Laight at aculab.com>
Cc: Denys Vlasenko <dvlasenk at redhat.com>
Cc: Eduardo Valentin <eduval at amazon.com>
Cc: Greg KH <gregkh at linuxfoundation.org>
Cc: Will Deacon <will.deacon at arm.com>
Cc: aliguori at amazon.com
Cc: daniel.gruss at iaik.tugraz.at
Cc: hughd at google.com
Cc: keescook at google.com
Cc: Andrea Arcangeli <aarcange at redhat.com>
Cc: Waiman Long <llong at redhat.com>
Cc: Pavel Machek <pavel at ucw.cz>
Cc: Arnaldo Carvalho de Melo <acme at kernel.org>
Cc: Alexander Shishkin <alexander.shishkin at linux.intel.com>
Cc: Jiri Olsa <jolsa at redhat.com>
Cc: Namhyung Kim <namhyung at kernel.org>
Cc: joro at 8bytes.org
Link: https://lkml.kernel.org/r/1532533683-5988-3-git-send-email-joro@8bytes.org

(cherry picked from commit 0e664eee65337082be49fbbd2ee24aa0d111d0f2)
Signed-off-by: Andrea Righi <andrea.righi at canonical.com>
---
 kernel/events/ring_buffer.c | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 5d8f4476d22e..dea024a6e0fb 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -813,13 +813,6 @@ static void rb_free_work(struct work_struct *work)
 
 	vfree(base);
 	kfree(rb);
-
-	/*
-	 * FIXME: PAE workaround for vmalloc_fault(): Make sure buffer is
-	 * unmapped in all page-tables.
-	 */
-	if (IS_ENABLED(CONFIG_X86_PAE))
-		vmalloc_sync_all();
 }
 
 void rb_free(struct ring_buffer *rb)
@@ -846,15 +839,6 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	if (!all_buf)
 		goto fail_all_buf;
 
-	/*
-	 * FIXME: PAE workaround for vmalloc_fault(): 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.
-	 */
-	if (IS_ENABLED(CONFIG_X86_PAE))
-		vmalloc_sync_all();
-
 	rb->user_page = all_buf;
 	rb->data_pages[0] = all_buf + PAGE_SIZE;
 	if (nr_pages) {
-- 
2.20.1