virtual memory reservation and a private pool of memory pages -- by a scheme
based on memory pools.
This allows better utilization of memory because buffers can now be allocated
with a granularity finer than the system's native page size (useful for
filesystems with e.g. 1k or 2k fragment sizes). It also avoids fragmentation
of virtual to physical memory mappings (due to the former fixed virtual
address reservation) resulting in better utilization of MMU resources on some
platforms. Finally, the scheme is more flexible by allowing run-time decisions
on the amount of memory to be used for buffers.
On the other hand, the effectiveness of the LRU queue for buffer recycling
may be somewhat reduced compared to the traditional method since, due to the
nature of the pool based memory allocation, the actual least recently used
buffer may release its memory to a pool different from the one needed by a
newly allocated buffer. However, this effect will kick in only if the
system is under memory pressure.
- nothing needs to be done if ci_want_resched is already set.
- if the cpu isn't running any lwp, send a no-op ipi to it
so that it can resume immediately from halting in idle loop
without having to wait until the next clock tick.
some advices from Stephan Uphoff.
- pmap_enter: zap PTE and read attributes atomically to
eliminate a race window which could cause lost of attributes.
- reduce number of TLB shootdown by using some assumptions
about PTE handling.
for more details, see "SMP improvements for pmap" thread on port-i386@
around May 2003.
need the data in the mbuf later and m_clget() changes some fields
overlaid to regular mbuf data. Instead, rearange code a bit, create
data into a new allocated buffer and and use MEXTADD to attach it to
the mbuf, if the mbuf internal space is not sufficient.
This fixes a crash on sparc64 (and probably all other archs where
sizeof(int) != sizeof(struct file *)) when running
regress/sys/kern/unfdpass.
Idea for solution from Matt Thomas, with additional input from YAMAMOTO
Takashi.
- hpc1_hdd_{ctl,bufptr} and hpc3_hdd_{ctl,bufptr} are
established in hpcreg.h. All references to these fields
are updated with the exception of if_sq: (haltwo,
hpcdma). This makes reading the code and spotting bugs
easier.
- hpcdma.c was applying EOCHAIN to the wrong descriptor
word for the hpc1 case.
- I added scsi_max_xfer to the abstraction layer, and it
allows some crusty #defines in wdsc.c to be removed.
hpc1 now doesn't waste descriptors as it once did.
- hpcreg.h was updated to reflect the lack of XMITDONE
bit in hpc1. HPC1_REV15 added for a test in hpc.c
- hpc.c now verifies HPC1 revisions (1.0 vs 1.5) and
prints the output a little prettier ;)
- power interrupts shouldn't establish on non-IP22
platforms.
can't fail. Simplify life in rf_BootRaidframe(), and then nuke
rf_lkmgr_mutex_init(). Cleanup rf_threadstuff.h a bit more too.
rf_threadstuff.c is about to Go Away.
(other than NULL when raidPtr is initialized). That means
SignalReconDone() never does anything useful. Bye-bye!
Say good-bye to recon_done_procs and recon_done_procs_mutex (and its
initializer) as well.
Mash DO_RAID_COND in rf_driver.c out of existance.
- Nuke (already #if 0'ed) _rf_create_managed_lkmgr_mutex() while we're
busy here.
simplify DO_INIT in rf_engine.c
here" department.
remove _rf_init_threadgroup() and rf_destroy_threadgroup() which were
already #if 0'ed.
rf_cond_destroy() does nothing. Nuke it, and all callers.
rf_cond_init() doesn't deserve to be a separate function any more.
Fix up the remaining 3 callers, and nuke rf_cond_init().
Another 0.4K goes "poof", but still no functionality lost!
rf_mutex_init(m)
now. The rest of the fluff is no longer needed.
It also cannot fail, so error checking on rf_create_managed_mutex()
is just wasting space.
Nuke the #define's associated with rf_create_managed_mutex().
Convert rf_create_managed_mutex(listp,m) to just rf_mutex_init(m).
Remove wasteful "error checking" and simplify all instances where this
is called. (another 0.3K saved in the binary, but the real savings
is in code readability!)
neither of these ever fail, no need to have a return value. That
makes all the "error detection" on these functions completely
unneeded. But since we're here, if we don't have a return value, then
why not make these macros? My.. look how things keep shrinking, with
no loss in functionality!
clean_rad() were -- these days they only serve to clutter things up.
Remove the functions, and put the 2 lines of actual useful initialization
into rf_AllocMCPair().
thorpej