page directory pages from VM_MIN_KERNEL_ADDRESS through the end of the
kernel's bss. Specifically, the dependence was in pmap_growkernel()'s one-
time initialization of kernel_vm_end, not in its main body. (I could not,
however, resist the urge to optimize the main body.)
Reduce the number of preallocated page directory pages to just those needed
to support NKPT page table pages. (In fact, this allows me to revert a
couple of my earlier changes to create_pagetables().)
ceiling as a fraction of the kernel map's size rather than an absolute
quantity. Thus, scaling of the kmem map's size will be automatic with
changes to the kernel map's size.
in practice, the error (currently) makes no difference because the computation
performed by KVADDR() hides the error. This revision fixes the error.
Also, eliminate a (now) unused definition.
ways:
(1) Cached pages are no longer kept in the object's resident page
splay tree and memq. Instead, they are kept in a separate per-object
splay tree of cached pages. However, access to this new per-object
splay tree is synchronized by the _free_ page queues lock, not to be
confused with the heavily contended page queues lock. Consequently, a
cached page can be reclaimed by vm_page_alloc(9) without acquiring the
object's lock or the page queues lock.
This solves a problem independently reported by tegge@ and Isilon.
Specifically, they observed the page daemon consuming a great deal of
CPU time because of pages bouncing back and forth between the cache
queue (PQ_CACHE) and the inactive queue (PQ_INACTIVE). The source of
this problem turned out to be a deadlock avoidance strategy employed
when selecting a cached page to reclaim in vm_page_select_cache().
However, the root cause was really that reclaiming a cached page
required the acquisition of an object lock while the page queues lock
was already held. Thus, this change addresses the problem at its
root, by eliminating the need to acquire the object's lock.
Moreover, keeping cached pages in the object's primary splay tree and
memq was, in effect, optimizing for the uncommon case. Cached pages
are reclaimed far, far more often than they are reactivated. Instead,
this change makes reclamation cheaper, especially in terms of
synchronization overhead, and reactivation more expensive, because
reactivated pages will have to be reentered into the object's primary
splay tree and memq.
(2) Cached pages are now stored alongside free pages in the physical
memory allocator's buddy queues, increasing the likelihood that large
allocations of contiguous physical memory (i.e., superpages) will
succeed.
Finally, as a result of this change long-standing restrictions on when
and where a cached page can be reclaimed and returned by
vm_page_alloc(9) are eliminated. Specifically, calls to
vm_page_alloc(9) specifying VM_ALLOC_INTERRUPT can now reclaim and
return a formerly cached page. Consequently, a call to malloc(9)
specifying M_NOWAIT is less likely to fail.
Discussed with: many over the course of the summer, including jeff@,
Justin Husted @ Isilon, peter@, tegge@
Tested by: an earlier version by kris@
Approved by: re (kensmith)
VM_PHYSSEG_SPARSE depending on whether the physical address space is
densely or sparsely populated with memory. The effect of this
definition is to determine which of two implementations of
vm_page_array and PHYS_TO_VM_PAGE() is used. The legacy
implementation is obtained by defining VM_PHYSSEG_DENSE, and a new
implementation that trades off time for space is obtained by defining
VM_PHYSSEG_SPARSE. For now, all architectures except for ia64 and
sparc64 define VM_PHYSSEG_DENSE. Defining VM_PHYSSEG_SPARSE on ia64
allows the entirety of my Itanium 2's memory to be used. Previously,
only the first 1 GB could be used. Defining VM_PHYSSEG_SPARSE on
sparc64 allows USIIIi-based systems to boot without crashing.
This change is a combination of Nathan Whitehorn's patch and my own
work in perforce.
Discussed with: kmacy, marius, Nathan Whitehorn
PR: 112194
vm.kmem_size_min. Useful when using ZFS to make sure that vm.kmem size will
be at least 256mb (for example) without forcing a particular value via vm.kmem_size.
Approved by: njl (mentor)
Reviewed by: alc
that was greater than 4G. I originally used the same values as i386 in
order to save opening a new PML4 page slot, but in the day of gigabytes
of memory, worrying about a 4K page seems futile. Moving from 8 to 32G
moves the page to a different index, it doesn't increase the number of
pages used.
32 bit binary stuff. 32 bit binaries do not like it much when the kernel
tries hard to put things above the 8GB mark.
I have a work-in-progress to fix this properly, but I didn't want to burn
anybody with this yet.
on the implied sign extension. The single unified VADDR() macro was
not able to avoid sign extending the VM_MAXUSER_ADDRESS/USRSTACK values.
Be explicit about UVADDR() (positive address space) and KVADDR()
(kernel negative address space) to make mistakes show up more
spectacularly.
Increase user VM space from 1/2TB (512GB) to 128TB.
systems. Of note:
- Implement a direct mapped region using 2MB pages. This eliminates the
need for temporary mappings when getting ptes. This supports up to
512GB of physical memory for now. This should be enough for a while.
- Implement a 4-tier page table system. Most of the infrastructure is
there for 128TB of userland virtual address space, but only 512GB is
presently enabled due to a mystery bug somewhere. The design of this
was heavily inspired by the alpha pmap.c.
- The kernel is moved into the negative address space(!).
- The kernel has 2GB of KVM available.
- Provide a uma memory allocator to use the direct map region to take
advantage of the 2MB TLBs.
- Fixed some assumptions in the bus_space macros about the ability
to fit virtual addresses in an 'int'.
Notable missing things:
- pmap_growkernel() should be able to grow to 512GB of KVM by expanding
downwards below kernbase. The kernel must be at the top 2GB of the
negative address space because of gcc code generation strategies.
- need to fix the >512GB user vm code.
Approved by: re (blanket)
a heavily stripped down FreeBSD/i386 (brutally stripped down actually) to
attempt to get a stable base to start from. There is a lot missing still.
Worth noting:
- The kernel runs at 1GB in order to cheat with the pmap code. pmap uses
a variation of the PAE code in order to avoid having to worry about 4
levels of page tables yet.
- It boots in 64 bit "long mode" with a tiny trampoline embedded in the
i386 loader. This simplifies locore.s greatly.
- There are still quite a few fragments of i386-specific code that have
not been translated yet, and some that I cheated and wrote dumb C
versions of (bcopy etc).
- It has both int 0x80 for syscalls (but using registers for argument
passing, as is native on the amd64 ABI), and the 'syscall' instruction
for syscalls. int 0x80 preserves all registers, 'syscall' does not.
- I have tried to minimize looking at the NetBSD code, except in a couple
of places (eg: to find which register they use to replace the trashed
%rcx register in the syscall instruction). As a result, there is not a
lot of similarity. I did look at NetBSD a few times while debugging to
get some ideas about what I might have done wrong in my first attempt.
the top of the address space to be reclaimed. The problem is that with
the APTD gone the mapable kernel address space runs right to the end of
the 32 bit address space. As a max this is 0x100000000, which can't be
represented in 32 bits, so we have to use ptd entry n-1 and pte offset
n-1, instead of ptd entry n and pte offset 0. There's still 1 page we
can't use, but we gain just under 4 megs of kva (8 megs with PAE).
Sponsored by: DARPA, Network Associates Laboratories
- Changed VM_MAXUSER_ADDRESS to be defined in terms of PTDPTDI. In order for
assumptions about the recursive page table map to work it must be the base
of the recursive map. Any pte offset that's not NPTEPG will break these
assumptions.
Sponsored by: DARPA, Network Associates Laboratories
via sysctl. It's done pretty simply but it should be quite adequate.
Also move SHMMAXPGS from $machine/include/vmparam.h as the comments that
went with it were wrong... we don't allocate KVM space for the pages so
that comment is bogus.. The only practical limit is how much physical
ram you want to lock up as this stuff isn't paged out or swap backed.
in a way identically as before.) I had problems with the system properly
handling the number of vnodes when there is alot of system memory, and the
default VM_KMEM_SIZE. Two new options "VM_KMEM_SIZE_SCALE" and
"VM_KMEM_SIZE_MAX" have been added to support better auto-sizing for systems
with greater than 128MB.
Add some accouting for vm_zone memory allocations, and provide properly
for vm_zone allocations out of the kmem_map. Also move the vm_zone
allocation stats to the VM OID tree from the KERN OID tree.
of the various ad-hoc schemes.
2) When bringing in UPAGES, the pmap code needs to do another vm_page_lookup.
3) When appropriate, set the PG_A or PG_M bits a-priori to both avoid some
processor errata, and to minimize redundant processor updating of page
tables.
4) Modify pmap_protect so that it can only remove permissions (as it
originally supported.) The additional capability is not needed.
5) Streamline read-only to read-write page mappings.
6) For pmap_copy_page, don't enable write mapping for source page.
7) Correct and clean-up pmap_incore.
8) Cluster initial kern_exec pagin.
9) Removal of some minor lint from kern_malloc.
10) Correct some ioopt code.
11) Remove some dead code from the MI swapout routine.
12) Correct vm_object_deallocate (to remove backing_object ref.)
13) Fix dead object handling, that had problems under heavy memory load.
14) Add minor vm_page_lookup improvements.
15) Some pages are not in objects, and make sure that the vm_page.c can
properly support such pages.
16) Add some more page deficit handling.
17) Some minor code readability improvements.
available to the kernel (VM_KMEM_SIZE). The default (32 MB) is too low
when having 512 MB or more physical memory in a server environment. This is
relevant on systems where "panic: kmem_malloc: kmem_map too small" is a
problem.
Rename the PT* index KSTK* #defines to UMAX*, since we don't have a kernel
stack there any more..
These are used to calculate VM_MAXUSER_ADDRESS and USRSTACK, and really
do not want to be changed with UPAGES since BSD/OS 2.x binary compatability
depends on it.
This will make a number of things easier in the future, as well as (finally!)
avoiding the Id-smashing problem which has plagued developers for so long.
Boy, I'm glad we're not using sup anymore. This update would have been
insane otherwise.
also implies VM_PROT_EXEC. We support it that way for now,
since the break system call by default gives VM_PROT_ALL. Now
we have a better chance of coalesing map entries when mixing
mmap/break type operations. This was contributing to excessive
numbers of map entries on the modula-3 runtime system. The
problem is still not "solved", but the situation makes more
sense.
Eventually, when we work on architectures where VM_PROT_READ
is orthogonal to VM_PROT_EXEC, we will have to visit this
issue carefully (esp. regarding security issues.)
page dir+table index.
pmap.h: remove NUPDE, it was wrong and not used. Sanitize KSTKPTEOFF.
vmparam.h: Calculate virtual addr from PDI+PTI from pmap.h rather than
using magic math. Remove UPDT, not used.
in machdep.c (it should use the global nmbclusters). Moved the calculation
of nmbclusters into conf/param.c (same place where nmbclusters has always
been assigned), and made the calculation include an extra amount based
on "maxusers". NMBCLUSTERS can still be overrided in the kernel config
file as always, but this change will make that generally unnecessary. This
fixes the "bug" reports from people who have misconfigured kernels seeing
the network hang when the mbuf cluster pool runs out.
Reviewed by: John Dyson
much higher filesystem I/O performance, and much better paging performance. It
represents the culmination of over 6 months of R&D.
The majority of the merged VM/cache work is by John Dyson.
The following highlights the most significant changes. Additionally, there are
(mostly minor) changes to the various filesystem modules (nfs, msdosfs, etc) to
support the new VM/buffer scheme.
vfs_bio.c:
Significant rewrite of most of vfs_bio to support the merged VM buffer cache
scheme. The scheme is almost fully compatible with the old filesystem
interface. Significant improvement in the number of opportunities for write
clustering.
vfs_cluster.c, vfs_subr.c
Upgrade and performance enhancements in vfs layer code to support merged
VM/buffer cache. Fixup of vfs_cluster to eliminate the bogus pagemove stuff.
vm_object.c:
Yet more improvements in the collapse code. Elimination of some windows that
can cause list corruption.
vm_pageout.c:
Fixed it, it really works better now. Somehow in 2.0, some "enhancements"
broke the code. This code has been reworked from the ground-up.
vm_fault.c, vm_page.c, pmap.c, vm_object.c
Support for small-block filesystems with merged VM/buffer cache scheme.
pmap.c vm_map.c
Dynamic kernel VM size, now we dont have to pre-allocate excessive numbers of
kernel PTs.
vm_glue.c
Much simpler and more effective swapping code. No more gratuitous swapping.
proc.h
Fixed the problem that the p_lock flag was not being cleared on a fork.
swap_pager.c, vnode_pager.c
Removal of old vfs_bio cruft to support the past pseudo-coherency. Now the
code doesn't need it anymore.
machdep.c
Changes to better support the parameter values for the merged VM/buffer cache
scheme.
machdep.c, kern_exec.c, vm_glue.c
Implemented a seperate submap for temporary exec string space and another one
to contain process upages. This eliminates all map fragmentation problems
that previously existed.
ffs_inode.c, ufs_inode.c, ufs_readwrite.c
Changes for merged VM/buffer cache. Add "bypass" support for sneaking in on
busy buffers.
Submitted by: John Dyson and David Greenman
