Some VM improvements, including elimination of alot of Sig-11

problems.  Tor Egge and others have helped with various VM bugs
lately, but don't blame him -- blame me!!!

pmap.c:
1)	Create an object for kernel page table allocations.  This
	fixes a bogus allocation method previously used for such, by
	grabbing pages from the kernel object, using bogus pindexes.
	(This was a code cleanup, and perhaps a minor system stability
	 issue.)

pmap.c:
2)	Pre-set the modify and accessed bits when prudent.  This will
	decrease bus traffic under certain circumstances.

vfs_bio.c, vfs_cluster.c:
3)	Rather than calculating the beginning virtual byte offset
	multiple times, stick the offset into the buffer header, so
	that the calculated offset can be reused.  (Long long multiplies
	are often expensive, and this is a probably unmeasurable performance
	improvement, and code cleanup.)

vfs_bio.c:
4)	Handle write recursion more intelligently (but not perfectly) so
	that it is less likely to cause a system panic, and is also
	much more robust.

vfs_bio.c:
5)	getblk incorrectly wrote out blocks that are incorrectly sized.
	The problem is fixed, and writes blocks out ONLY when B_DELWRI
	is true.

vfs_bio.c:
6)	Check that already constituted buffers have fully valid pages.  If
	not, then make sure that the B_CACHE bit is not set. (This was
	a major source of Sig-11 type problems.)

vfs_bio.c:
7)	Fix a potential system deadlock due to an incorrectly specified
	sleep priority while waiting for a buffer write operation.  The
	change that I made opens the system up to serious problems, and
	we need to examine the issue of process sleep priorities.

vfs_cluster.c, vfs_bio.c:
8)	Make clustered reads work more correctly (and more completely)
	when buffers are already constituted, but not fully valid.
	(This was another system reliability issue.)

vfs_subr.c, ffs_inode.c:
9)	Create a vtruncbuf function, which is used by filesystems that
	can truncate files.  The vinvalbuf forced a file sync type operation,
	while vtruncbuf only invalidates the buffers past the new end of file,
	and also invalidates the appropriate pages.  (This was a system reliabiliy
	and performance issue.)

10)	Modify FFS to use vtruncbuf.

vm_object.c:
11)	Make the object rundown mechanism for OBJT_VNODE type objects work
	more correctly.  Included in that fix, create pager entries for
	the OBJT_DEAD pager type, so that paging requests that might slip
	in during race conditions are properly handled.  (This was a system
	reliability issue.)

vm_page.c:
12)	Make some of the page validation routines be a little less picky
	about arguments passed to them.  Also, support page invalidation
	change the object generation count so that we handle generation
	counts a little more robustly.

vm_pageout.c:
13)	Further reduce pageout daemon activity when the system doesn't
	need help from it.  There should be no additional performance
	decrease even when the pageout daemon is running.  (This was
	a significant performance issue.)

vnode_pager.c:
14)	Teach the vnode pager to handle race conditions during vnode
	deallocations.

1 files changed, 25 insertions, 16 deletions

diff --git a/sys/kern/vfs_cluster.c b/sys/kern/vfs_cluster.c
index 0022ac9..f2c12d4 100644
--- a/sys/kern/vfs_cluster.c
+++ b/sys/kern/vfs_cluster.c
@@ -33,7 +33,7 @@
  * SUCH DAMAGE.
  *
  *	@(#)vfs_cluster.c	8.7 (Berkeley) 2/13/94
- * $Id: vfs_cluster.c,v 1.56 1998/03/07 21:35:28 dyson Exp $
+ * $Id: vfs_cluster.c,v 1.57 1998/03/08 09:57:09 julian Exp $
  */
 
 #include "opt_debug_cluster.h"
@@ -165,8 +165,8 @@ cluster_read(vp, filesize, lblkno, size, cred, totread, seqcount, bpp)
 		}
 		reqbp = bp = NULL;
 	} else {
-		u_quad_t firstread;
-		firstread = (u_quad_t) lblkno * size;
+		off_t firstread;
+		firstread = bp->b_offset;
 		if (firstread + totread > filesize)
 			totread = filesize - firstread;
 		if (totread > size) {
@@ -253,6 +253,7 @@ single_block_read:
 			curproc->p_stats->p_ru.ru_inblock++;
 		}
 	}
+
 	/*
 	 * and if we have read-aheads, do them too
 	 */
@@ -346,6 +347,7 @@ cluster_rbuild(vp, filesize, lbn, blkno, size, run, fbp)
 	bp->b_iodone = cluster_callback;
 	bp->b_blkno = blkno;
 	bp->b_lblkno = lbn;
+	bp->b_offset = tbp->b_offset;
 	pbgetvp(vp, bp);
 
 	TAILQ_INIT(&bp->b_cluster.cluster_head);
@@ -363,8 +365,20 @@ cluster_rbuild(vp, filesize, lbn, blkno, size, run, fbp)
 				round_page(size) > vp->v_maxio)
 				break;
 
-			if (incore(vp, lbn + i))
-				break;
+			if (tbp = incore(vp, lbn + i)) {
+				if (tbp->b_flags & B_BUSY)
+					break;
+
+				for (j = 0; j < tbp->b_npages; j++)
+					if (tbp->b_pages[j]->valid)
+						break;
+				
+				if (j != tbp->b_npages)
+					break;
+	
+				if (tbp->b_bcount != size)
+					break;
+			}
 
 			tbp = getblk(vp, lbn + i, size, 0, 0);
 
@@ -374,18 +388,12 @@ cluster_rbuild(vp, filesize, lbn, blkno, size, run, fbp)
 				break;
 			}
 
-			for (j=0;j<tbp->b_npages;j++) {
-				if (tbp->b_pages[j]->valid) {
+			for (j = 0;j < tbp->b_npages; j++)
+				if (tbp->b_pages[j]->valid)
 					break;
-				}
-			}
 
 			if (j != tbp->b_npages) {
-				/*
-				 * force buffer to be re-constituted later
-				 */
-				tbp->b_flags |= B_RELBUF;
-				brelse(tbp);
+				bqrelse(tbp);
 				break;
 			}
 
@@ -525,7 +533,7 @@ cluster_write(bp, filesize)
 			 */
 			cursize = vp->v_lastw - vp->v_cstart + 1;
 #ifndef notyet_block_reallocation_enabled
-			if (((u_quad_t)(lbn + 1) * lblocksize) != filesize ||
+			if (((u_quad_t) bp->b_offset + lblocksize) != filesize ||
 				lbn != vp->v_lastw + 1 ||
 				vp->v_clen <= cursize) {
 				if (!async)
@@ -576,7 +584,7 @@ cluster_write(bp, filesize)
 		 * existing cluster.
 		 */
 		if ((vp->v_type == VREG) &&
-			((u_quad_t) (lbn + 1) * lblocksize) != filesize &&
+			((u_quad_t) bp->b_offset + lblocksize) != filesize &&
 		    (bp->b_blkno == bp->b_lblkno) &&
 		    (VOP_BMAP(vp, lbn, NULL, &bp->b_blkno, &maxclen, NULL) ||
 		     bp->b_blkno == -1)) {
@@ -682,6 +690,7 @@ cluster_wbuild(vp, size, start_lbn, len)
 
 		bp->b_blkno = tbp->b_blkno;
 		bp->b_lblkno = tbp->b_lblkno;
+		bp->b_offset = tbp->b_offset;
 		(vm_offset_t) bp->b_data |= ((vm_offset_t) tbp->b_data) & PAGE_MASK;
 		bp->b_flags |= B_CALL | B_BUSY | B_CLUSTER |
 						(tbp->b_flags & (B_VMIO|B_NEEDCOMMIT));