diff options
| author | Peter Wemm <peter@FreeBSD.org> | 2002-08-03 00:59:15 +0000 |
|---|---|---|
| committer | Peter Wemm <peter@FreeBSD.org> | 2002-08-03 00:59:15 +0000 |
| commit | 1af04fadd157e873398b1c01497c441decd84434 (patch) | |
| tree | aac4b29b0382493687f993ee07b046f6ed473ef5 /sys/amd64/amd64/mem.c | |
| parent | a0cd6004a95365928cd20dd2ef903d82305a4c99 (diff) | |
| download | src-1af04fadd157e873398b1c01497c441decd84434.tar.gz src-1af04fadd157e873398b1c01497c441decd84434.zip | |
Take a shot at fixing a nasty bug in the pmap changes that I did. I
missed the pmap_kenter/kremove in this file, which leads to read()/write()
of /dev/mem using stale TLB entries. (gah!) Fortunately, mmap of /dev/mem
wasn't affected, so it wasn't as bad as it could have been. This throws
some light on the 'X server affects stability' thread....
Pointed out by: bde
Notes
Notes:
svn path=/head/; revision=101248
Diffstat (limited to 'sys/amd64/amd64/mem.c')
| -rw-r--r-- | sys/amd64/amd64/mem.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/sys/amd64/amd64/mem.c b/sys/amd64/amd64/mem.c index 220bad373937..313e6c5cad7f 100644 --- a/sys/amd64/amd64/mem.c +++ b/sys/amd64/amd64/mem.c @@ -167,7 +167,7 @@ mmrw(dev_t dev, struct uio *uio, int flags) c = min(c, (u_int)(PAGE_SIZE - o)); c = min(c, (u_int)iov->iov_len); error = uiomove((caddr_t)&ptvmmap[o], (int)c, uio); - pmap_kremove((vm_offset_t)ptvmmap); + pmap_qremove((vm_offset_t)ptvmmap, 1); continue; /* minor device 1 is kernel memory */ |