diff options
author | Mark Kettenis <kettenis@cvs.openbsd.org> | 2023-12-11 22:12:54 +0000 |
---|---|---|
committer | Mark Kettenis <kettenis@cvs.openbsd.org> | 2023-12-11 22:12:54 +0000 |
commit | 0de6004f3c4b6c0d9c50014c604793d658cd1421 (patch) | |
tree | d7228f737247d13c5e1dcc0b85ebbfebd24fcf8e /sys/arch/m88k | |
parent | 70e28086c36f6c95d45010d325ff4280b90c00be (diff) |
Implement per-CPU caching for the page table page (vp) pool and the PTE
descriptor (pted) pool in the arm64 pmap implementation. This
significantly reduces the side-effects of lock contention on the kernel
map lock that is (incorrectly) translated into excessive page daemon
wakeups. This is not a perfect solution but it does lead to significant
speedups on machines with many CPU cores.
This requires adding a new pmap_init_percpu() function that gets called
at the point where kernel is ready to set up the per-CPU pool caches.
Dummy implementations of this function are added for all non-arm64
architectures. Some other architectures can probably benefit from
providing an actual implementation that sets up per-CPU caches for
pmap pools as well.
ok phessler@, claudio@, miod@, patrick@
Diffstat (limited to 'sys/arch/m88k')
-rw-r--r-- | sys/arch/m88k/include/pmap.h | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/sys/arch/m88k/include/pmap.h b/sys/arch/m88k/include/pmap.h index 746ed8ec8dc..735945313f9 100644 --- a/sys/arch/m88k/include/pmap.h +++ b/sys/arch/m88k/include/pmap.h @@ -1,4 +1,4 @@ -/* $OpenBSD: pmap.h,v 1.29 2023/04/13 15:23:22 miod Exp $ */ +/* $OpenBSD: pmap.h,v 1.30 2023/12/11 22:12:53 kettenis Exp $ */ /* * Mach Operating System * Copyright (c) 1991 Carnegie Mellon University @@ -64,6 +64,7 @@ int pmap_set_modify(pmap_t, vaddr_t); void pmap_unmap_firmware(void); boolean_t pmap_unsetbit(struct vm_page *, int); +#define pmap_init_percpu() do { /* nothing */ } while (0) #define pmap_unuse_final(p) /* nothing */ #define pmap_remove_holes(vm) do { /* nothing */ } while (0) |