diff options
| author | kmacy <kmacy@FreeBSD.org> | 2010-04-30 00:46:43 +0000 |
|---|---|---|
| committer | kmacy <kmacy@FreeBSD.org> | 2010-04-30 00:46:43 +0000 |
| commit | 1dc1263413262d13f45f42d89c554d0ddc167ca2 (patch) | |
| tree | 250705d42bcb9b364f4fd2233c38faaadadf7ae0 /sys/net/bpf_zerocopy.c | |
| parent | a43425e8835983e7c93a15a2d6a42fdb292c1676 (diff) | |
| download | FreeBSD-src-1dc1263413262d13f45f42d89c554d0ddc167ca2.zip FreeBSD-src-1dc1263413262d13f45f42d89c554d0ddc167ca2.tar.gz | |
On Alan's advice, rather than do a wholesale conversion on a single
architecture from page queue lock to a hashed array of page locks
(based on a patch by Jeff Roberson), I've implemented page lock
support in the MI code and have only moved vm_page's hold_count
out from under page queue mutex to page lock. This changes
pmap_extract_and_hold on all pmaps.
Supported by: Bitgravity Inc.
Discussed with: alc, jeffr, and kib
Diffstat (limited to 'sys/net/bpf_zerocopy.c')
| -rw-r--r-- | sys/net/bpf_zerocopy.c | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/sys/net/bpf_zerocopy.c b/sys/net/bpf_zerocopy.c index a1dd923..3cf4b8d 100644 --- a/sys/net/bpf_zerocopy.c +++ b/sys/net/bpf_zerocopy.c @@ -168,10 +168,12 @@ zbuf_sfbuf_get(struct vm_map *map, vm_offset_t uaddr) VM_PROT_WRITE); if (pp == NULL) return (NULL); + vm_page_lock(pp); vm_page_lock_queues(); vm_page_wire(pp); vm_page_unhold(pp); vm_page_unlock_queues(); + vm_page_unlock(pp); sf = sf_buf_alloc(pp, SFB_NOWAIT); if (sf == NULL) { zbuf_page_free(pp); |
