Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 18 Mar 2018 16:49:30 +0000 (UTC)
From:      Mark Johnston <markj@FreeBSD.org>
To:        src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org
Subject:   svn commit: r331131 - head/sys/vm
Message-ID:  <201803181649.w2IGnULZ071778@repo.freebsd.org>

next in thread | raw e-mail | index | archive | help
Author: markj
Date: Sun Mar 18 16:49:30 2018
New Revision: 331131
URL: https://svnweb.freebsd.org/changeset/base/331131

Log:
  Avoid dequeuing the fault page during a soft fault.
  
  Such pages are re-enqueued at the end of the fault handler, preserving
  LRU. Rather than performing two separate operations per fault, simply
  requeue the page at the end of the fault (or bump its activation count
  if it resides in PQ_ACTIVE, avoiding the page queue lock entirely).
  This elides some page lock and page queue lock operations in common
  cases, e.g., CoW faults.
  
  Note that we must still dequeue the source page for "optimized" CoW
  faults since the page may not remain enqueued while it is moved to
  another object.
  
  Reviewed by:	alc, kib
  Tested by:	pho
  MFC after:	2 weeks
  Differential Revision:	https://reviews.freebsd.org/D14625

Modified:
  head/sys/vm/vm_fault.c

Modified: head/sys/vm/vm_fault.c
==============================================================================
--- head/sys/vm/vm_fault.c	Sun Mar 18 16:40:56 2018	(r331130)
+++ head/sys/vm/vm_fault.c	Sun Mar 18 16:49:30 2018	(r331131)
@@ -682,7 +682,7 @@ RetryFault:;
 				/*
 				 * Reference the page before unlocking and
 				 * sleeping so that the page daemon is less
-				 * likely to reclaim it. 
+				 * likely to reclaim it.
 				 */
 				vm_page_aflag_set(fs.m, PGA_REFERENCED);
 				if (fs.object != fs.first_object) {
@@ -710,9 +710,6 @@ RetryFault:;
 				vm_object_deallocate(fs.first_object);
 				goto RetryFault;
 			}
-			vm_page_lock(fs.m);
-			vm_page_remque(fs.m);
-			vm_page_unlock(fs.m);
 
 			/*
 			 * Mark page busy for other processes, and the 
@@ -723,7 +720,7 @@ RetryFault:;
 			vm_page_xbusy(fs.m);
 			if (fs.m->valid != VM_PAGE_BITS_ALL)
 				goto readrest;
-			break;
+			break; /* break to PAGE HAS BEEN FOUND */
 		}
 		KASSERT(fs.m == NULL, ("fs.m should be NULL, not %p", fs.m));
 
@@ -1105,6 +1102,7 @@ readrest:
 				 */
 			    fs.object == fs.first_object->backing_object) {
 				vm_page_lock(fs.m);
+				vm_page_remque(fs.m);
 				vm_page_remove(fs.m);
 				vm_page_unlock(fs.m);
 				vm_page_lock(fs.first_m);



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201803181649.w2IGnULZ071778>