Dave Hansen [Sun, 30 Oct 2005 01:16:50 +0000 (18:16 -0700)]
[PATCH] memory hotplug prep: break out zone initialization
If a zone is empty at boot-time and then hot-added to later, it needs to run
the same init code that would have been run on it at boot.
This patch breaks out zone table and per-cpu-pages functions for use by the
hotplug code. You can almost see all of the free_area_init_core() function on
one page now. :)
Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Dave Hansen [Sun, 30 Oct 2005 01:16:49 +0000 (18:16 -0700)]
[PATCH] memory hotplug prep: kill local_mapnr
The following series implements memory hot-add for ppc64 and i386. There are
x86_64 and ia64 implementations that will be submitted shortly as well,
through the normal maintainers.
This patch:
local_mapnr is unused, except for in an alpha header. Keep the alpha one,
kill the rest.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
We had a problem on ppc64 where with more than 4 threads a large system
wouldn't scale well while faulting in the .text (most of the time was spent
in the kernel despite it was an userland compute intensive app). The
reason is the useless overwrite of the same pte from all cpu.
I fixed it this way (verified on an older kernel but the forward port is
almost identical). This will benefit all archs not just ppc64.
Signed-off-by: Andrea Arcangeli <andrea@suse.de> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Adam Litke [Sun, 30 Oct 2005 01:16:47 +0000 (18:16 -0700)]
[PATCH] hugetlb: overcommit accounting check
Basic overcommit checking for hugetlb_file_map() based on an implementation
used with demand faulting in SLES9.
Since demand faulting can't guarantee the availability of pages at mmap
time, this patch implements a basic sanity check to ensure that the number
of huge pages required to satisfy the mmap are currently available.
Despite the obvious race, I think it is a good start on doing proper
accounting. I'd like to work towards an accounting system that mimics the
semantics of normal pages (especially for the MAP_PRIVATE/COW case). That
work is underway and builds on what this patch starts.
Huge page shared memory segments are simpler and still maintain their
commit on shmget semantics.
Signed-off-by: Adam Litke <agl@us.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Adam Litke [Sun, 30 Oct 2005 01:16:46 +0000 (18:16 -0700)]
[PATCH] hugetlb: demand fault handler
Below is a patch to implement demand faulting for huge pages. The main
motivation for changing from prefaulting to demand faulting is so that huge
page memory areas can be allocated according to NUMA policy.
Thanks to consolidated hugetlb code, switching the behavior requires changing
only one fault handler. The bulk of the patch just moves the logic from
hugelb_prefault() to hugetlb_pte_fault() and find_get_huge_page().
Signed-off-by: Adam Litke <agl@us.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Reformat hugelbfs_forget_inode and add the missing but harmless
write_inode_now call. It looks the same as generic_forget_inode now except
for the call to truncate_hugepages instead of truncate_inode_pages.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
[PATCH] hugetlbfs: clean up hugetlbfs_delete_inode
Make hugetlbfs looks the same as generic_detelte_inode, fixing a bunch of
missing updates to it at the same time. Rename it to
hugetlbfs_do_delete_inode and add a real hugetlbfs_delete_inode that
implements ->delete_inode.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Move hugetlbfs accounting into ->alloc_inode / ->destroy_inode. This keeps
the code simpler, fixes a loeak where a failing inode allocation wouldn't
decrement the counter and moves hugetlbfs_delete_inode and
hugetlbfs_forget_inode closer to their generic counterparts.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Hugh Dickins [Sun, 30 Oct 2005 01:16:41 +0000 (18:16 -0700)]
[PATCH] mm: fix rss and mmlist locking
A couple of oddities were guarded by page_table_lock, no longer properly
guarded when that is split.
The mm_counters of file_rss and anon_rss: make those an atomic_t, or an
atomic64_t if the architecture supports it, in such a case. Definitions by
courtesy of Christoph Lameter: who spent considerable effort on more scalable
ways of counting, but found insufficient benefit in practice.
And adding an mm with swap to the mmlist for swapoff: the list is well-
guarded by its own lock, but the list_empty check now has to be repeated
inside it.
Hugh Dickins [Sun, 30 Oct 2005 01:16:40 +0000 (18:16 -0700)]
[PATCH] mm: split page table lock
Christoph Lameter demonstrated very poor scalability on the SGI 512-way, with
a many-threaded application which concurrently initializes different parts of
a large anonymous area.
This patch corrects that, by using a separate spinlock per page table page, to
guard the page table entries in that page, instead of using the mm's single
page_table_lock. (But even then, page_table_lock is still used to guard page
table allocation, and anon_vma allocation.)
In this implementation, the spinlock is tucked inside the struct page of the
page table page: with a BUILD_BUG_ON in case it overflows - which it would in
the case of 32-bit PA-RISC with spinlock debugging enabled.
Splitting the lock is not quite for free: another cacheline access. Ideally,
I suppose we would use split ptlock only for multi-threaded processes on
multi-cpu machines; but deciding that dynamically would have its own costs.
So for now enable it by config, at some number of cpus - since the Kconfig
language doesn't support inequalities, let preprocessor compare that with
NR_CPUS. But I don't think it's worth being user-configurable: for good
testing of both split and unsplit configs, split now at 4 cpus, and perhaps
change that to 8 later.
There is a benefit even for singly threaded processes: kswapd can be attacking
one part of the mm while another part is busy faulting.
Hugh Dickins [Sun, 30 Oct 2005 01:16:39 +0000 (18:16 -0700)]
[PATCH] mm: uml kill unused
In worrying over the various pte operations in different architectures, I came
across some unused functions in UML: remove mprotect_kernel_vm,
protect_vm_page and addr_pte.
Hugh Dickins [Sun, 30 Oct 2005 01:16:37 +0000 (18:16 -0700)]
[PATCH] mm: cris v32 mmu_context_lock
The cris v32 switch_mm guards get_mmu_context with next->page_table_lock: good
it's not really SMP yet, since get_mmu_context messes with global variables
affecting other mms. Replace by global mmu_context_lock.
Hugh Dickins [Sun, 30 Oct 2005 01:16:36 +0000 (18:16 -0700)]
[PATCH] mm: parisc pte atomicity
There's a worrying function translation_exists in parisc cacheflush.h,
unaffected by split ptlock since flush_dcache_page is using it on some other
mm, without any relevant lock. Oh well, make it a slightly more robust by
factoring the pfn check within it. And it looked liable to confuse a
camouflaged swap or file entry with a good pte: fix that too.
Hugh Dickins [Sun, 30 Oct 2005 01:16:36 +0000 (18:16 -0700)]
[PATCH] mm: arm ready for split ptlock
Prepare arm for the split page_table_lock: three issues.
Signal handling's preserve and restore of iwmmxt context currently involves
reading and writing that context to and from user space, while holding
page_table_lock to secure the user page(s) against kswapd. If we split the
lock, then the structure might span two pages, secured by to read into and
write from a kernel stack buffer, copying that out and in without locking (the
structure is 160 bytes in size, and here we're near the top of the kernel
stack). Or would the overhead be noticeable?
arm_syscall's cmpxchg emulation use pte_offset_map_lock, instead of
pte_offset_map and mm-wide page_table_lock; and strictly, it should now also
take mmap_sem before descending to pmd, to guard against another thread
munmapping, and the page table pulled out beneath this thread.
Updated two comments in fault-armv.c. adjust_pte is interesting, since its
modification of a pte in one part of the mm depends on the lock held when
calling update_mmu_cache for a pte in some other part of that mm. This can't
be done with a split page_table_lock (and we've already taken the lowest lock
in the hierarchy here): so we'll have to disable split on arm, unless
CONFIG_CPU_CACHE_VIPT to ensures adjust_pte never used.
Hugh Dickins [Sun, 30 Oct 2005 01:16:34 +0000 (18:16 -0700)]
[PATCH] mm: i386 sh sh64 ready for split ptlock
Use pte_offset_map_lock, instead of pte_offset_map (or inappropriate
pte_offset_kernel) and mm-wide page_table_lock, in sundry arch places.
The i386 vm86 mark_screen_rdonly: yes, there was and is an assumption that the
screen fits inside the one page table, as indeed it does.
The sh __do_page_fault: which handles both kernel faults (without lock) and
user mm faults (locked - though it set_pte without locking before).
The sh64 flush_cache_range and helpers: which wrongly thought callers held
page_table_lock before (only its tlb_start_vma did, and no longer does so);
moved the flush loop down, and adjusted the large versus small range decision
to consider a range which spans page tables as large.
Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Hugh Dickins [Sun, 30 Oct 2005 01:16:33 +0000 (18:16 -0700)]
[PATCH] mm: follow_page with inner ptlock
Final step in pushing down common core's page_table_lock. follow_page no
longer wants caller to hold page_table_lock, uses pte_offset_map_lock itself;
and so no page_table_lock is taken in get_user_pages itself.
But get_user_pages (and get_futex_key) do then need follow_page to pin the
page for them: take Daniel's suggestion of bitflags to follow_page.
Need one for WRITE, another for TOUCH (it was the accessed flag before:
vanished along with check_user_page_readable, but surely get_numa_maps is
wrong to mark every page it finds as accessed), another for GET.
And another, ANON to dispose of untouched_anonymous_page: it seems silly for
that to descend a second time, let follow_page observe if there was no page
table and return ZERO_PAGE if so. Fix minor bug in that: check VM_LOCKED -
make_pages_present ought to make readonly anonymous present.
Give get_numa_maps a cond_resched while we're there.
Hugh Dickins [Sun, 30 Oct 2005 01:16:32 +0000 (18:16 -0700)]
[PATCH] mm: kill check_user_page_readable
check_user_page_readable is a problematic variant of follow_page. It's used
only by oprofile's i386 and arm backtrace code, at interrupt time, to
establish whether a userspace stackframe is currently readable.
This is problematic, because we want to push the page_table_lock down inside
follow_page, and later split it; whereas oprofile is doing a spin_trylock on
it (in the i386 case, forgotten in the arm case), and needs that to pin
perhaps two pages spanned by the stackframe (which might be covered by
different locks when we split).
I think oprofile is going about this in the wrong way: it doesn't need to know
the area is readable (neither i386 nor arm uses read protection of user
pages), it doesn't need to pin the memory, it should simply
__copy_from_user_inatomic, and see if that succeeds or not. Sorry, but I've
not got around to devising the sparse __user annotations for this.
Then we can eliminate check_user_page_readable, and return to a single
follow_page without the __follow_page variants.
Hugh Dickins [Sun, 30 Oct 2005 01:16:31 +0000 (18:16 -0700)]
[PATCH] mm: rmap with inner ptlock
rmap's page_check_address descend without page_table_lock. First just
pte_offset_map in case there's no pte present worth locking for, then take
page_table_lock for the full check, and pass ptl back to caller in the same
style as pte_offset_map_lock. __xip_unmap, page_referenced_one and
try_to_unmap_one use pte_unmap_unlock. try_to_unmap_cluster also.
page_check_address reformatted to avoid progressive indentation. No use is
made of its one error code, return NULL when it fails.
Hugh Dickins [Sun, 30 Oct 2005 01:16:31 +0000 (18:16 -0700)]
[PATCH] mm: xip_unmap ZERO_PAGE fix
Small fix to the PageReserved patch: the mips ZERO_PAGE(address) depends on
address, so __xip_unmap is wrong to initialize page with that before address
is initialized; and in fact must re-evaluate it each iteration.
Hugh Dickins [Sun, 30 Oct 2005 01:16:30 +0000 (18:16 -0700)]
[PATCH] mm: unmap_vmas with inner ptlock
Remove the page_table_lock from around the calls to unmap_vmas, and replace
the pte_offset_map in zap_pte_range by pte_offset_map_lock: all callers are
now safe to descend without page_table_lock.
Don't attempt fancy locking for hugepages, just take page_table_lock in
unmap_hugepage_range. Which makes zap_hugepage_range, and the hugetlb test in
zap_page_range, redundant: unmap_vmas calls unmap_hugepage_range anyway. Nor
does unmap_vmas have much use for its mm arg now.
The tlb_start_vma and tlb_end_vma in unmap_page_range are now called without
page_table_lock: if they're implemented at all, they typically come down to
flush_cache_range (usually done outside page_table_lock) and flush_tlb_range
(which we already audited for the mprotect case).
Hugh Dickins [Sun, 30 Oct 2005 01:16:29 +0000 (18:16 -0700)]
[PATCH] mm: unlink vma before pagetables
In most places the descent from pgd to pud to pmd to pte holds mmap_sem
(exclusively or not), which ensures that free_pgtables cannot be freeing page
tables from any level at the same time. But truncation and reverse mapping
descend without mmap_sem.
No problem: just make sure that a vma is unlinked from its prio_tree (or
nonlinear list) and from its anon_vma list, after zapping the vma, but before
freeing its page tables. Then neither vmtruncate nor rmap can reach that vma
whose page tables are now volatile (nor do they need to reach it, since all
its page entries have been zapped by this stage).
The i_mmap_lock and anon_vma->lock already serialize this correctly; but the
locking hierarchy is such that we cannot take them while holding
page_table_lock. Well, we're trying to push that down anyway. So in this
patch, move anon_vma_unlink and unlink_file_vma into free_pgtables, at the
same time as moving page_table_lock around calls to unmap_vmas.
tlb_gather_mmu and tlb_finish_mmu then fall outside the page_table_lock, but
we made them preempt_disable and preempt_enable earlier; and a long source
audit of all the architectures has shown no problem with removing
page_table_lock from them. free_pgtables doesn't need page_table_lock for
itself, nor for what it calls; tlb->mm->nr_ptes is usually protected by
page_table_lock, but partly by non-exclusive mmap_sem - here it's decremented
with exclusive mmap_sem, or mm_users 0. update_hiwater_rss and
vm_unacct_memory don't need page_table_lock either.
Hugh Dickins [Sun, 30 Oct 2005 01:16:28 +0000 (18:16 -0700)]
[PATCH] mm: flush_tlb_range outside ptlock
There was one small but very significant change in the previous patch:
mprotect's flush_tlb_range fell outside the page_table_lock: as it is in 2.4,
but that doesn't prove it safe in 2.6.
On some architectures flush_tlb_range comes to the same as flush_tlb_mm, which
has always been called from outside page_table_lock in dup_mmap, and is so
proved safe. Others required a deeper audit: I could find no reliance on
page_table_lock in any; but in ia64 and parisc found some code which looks a
bit as if it might want preemption disabled. That won't do any actual harm,
so pending a decision from the maintainers, disable preemption there.
Remove comments on page_table_lock from flush_tlb_mm, flush_tlb_range and
flush_tlb_page entries in cachetlb.txt: they were rather misleading (what
generic code does is different from what usually happens), the rules are now
changing, and it's not yet clear where we'll end up (will the generic
tlb_flush_mmu happen always under lock? never under lock? or sometimes under
and sometimes not?).
Hugh Dickins [Sun, 30 Oct 2005 01:16:27 +0000 (18:16 -0700)]
[PATCH] mm: pte_offset_map_lock loops
Convert those common loops using page_table_lock on the outside and
pte_offset_map within to use just pte_offset_map_lock within instead.
These all hold mmap_sem (some exclusively, some not), so at no level can a
page table be whipped away from beneath them. But whereas pte_alloc loops
tested with the "atomic" pmd_present, these loops are testing with pmd_none,
which on i386 PAE tests both lower and upper halves.
That's now unsafe, so add a cast into pmd_none to test only the vital lower
half: we lose a little sensitivity to a corrupt middle directory, but not
enough to worry about. It appears that i386 and UML were the only
architectures vulnerable in this way, and pgd and pud no problem.
Hugh Dickins [Sun, 30 Oct 2005 01:16:26 +0000 (18:16 -0700)]
[PATCH] mm: page fault handler locking
On the page fault path, the patch before last pushed acquiring the
page_table_lock down to the head of handle_pte_fault (though it's also taken
and dropped earlier when a new page table has to be allocated).
Now delete that line, read "entry = *pte" without it, and go off to this or
that page fault handler on the basis of this unlocked peek. Usually the
handler can proceed without the lock, relying on the subsequent locked
pte_same or pte_none test to back out when necessary; though do_wp_page needs
the lock immediately, and do_file_page doesn't check (if there's a race,
install_page just zaps the entry and reinstalls it).
But on those architectures (notably i386 with PAE) whose pte is too big to be
read atomically, if SMP or preemption is enabled, do_swap_page and
do_file_page might cause irretrievable damage if passed a Frankenstein entry
stitched together from unrelated parts. In those configs, "pte_unmap_same"
has to take page_table_lock, validate orig_pte still the same, and drop
page_table_lock before unmapping, before proceeding.
Use pte_offset_map_lock and pte_unmap_unlock throughout the handlers; but lock
avoidance leaves more lone maps and unmaps than elsewhere.
Hugh Dickins [Sun, 30 Oct 2005 01:16:24 +0000 (18:16 -0700)]
[PATCH] mm: arches skip ptlock
Convert those few architectures which are calling pud_alloc, pmd_alloc,
pte_alloc_map on a user mm, not to take the page_table_lock first, nor drop it
after. Each of these can continue to use pte_alloc_map, no need to change
over to pte_alloc_map_lock, they're neither racy nor swappable.
In the sparc64 io_remap_pfn_range, flush_tlb_range then falls outside of the
page_table_lock: that's okay, on sparc64 it's like flush_tlb_mm, and that has
always been called from outside of page_table_lock in dup_mmap.
Hugh Dickins [Sun, 30 Oct 2005 01:16:23 +0000 (18:16 -0700)]
[PATCH] mm: ptd_alloc take ptlock
Second step in pushing down the page_table_lock. Remove the temporary
bridging hack from __pud_alloc, __pmd_alloc, __pte_alloc: expect callers not
to hold page_table_lock, whether it's on init_mm or a user mm; take
page_table_lock internally to check if a racing task already allocated.
Convert their callers from common code. But avoid coming back to change them
again later: instead of moving the spin_lock(&mm->page_table_lock) down,
switch over to new macros pte_alloc_map_lock and pte_unmap_unlock, which
encapsulate the mapping+locking and unlocking+unmapping together, and in the
end may use alternatives to the mm page_table_lock itself.
These callers all hold mmap_sem (some exclusively, some not), so at no level
can a page table be whipped away from beneath them; and pte_alloc uses the
"atomic" pmd_present to test whether it needs to allocate. It appears that on
all arches we can safely descend without page_table_lock.
Hugh Dickins [Sun, 30 Oct 2005 01:16:22 +0000 (18:16 -0700)]
[PATCH] mm: ptd_alloc inline and out
It seems odd to me that, whereas pud_alloc and pmd_alloc test inline, only
calling out-of-line __pud_alloc __pmd_alloc if allocation needed,
pte_alloc_map and pte_alloc_kernel are entirely out-of-line. Though it does
add a little to kernel size, change them to macros testing inline, calling
__pte_alloc or __pte_alloc_kernel to allocate out-of-line. Mark none of them
as fastcalls, leave that to CONFIG_REGPARM or not.
It also seems more natural for the out-of-line functions to leave the offset
calculation and map to the inline, which has to do it anyway for the common
case. At least mremap move wants __pte_alloc without _map.
Macros rather than inline functions, certainly to avoid the header file issues
which arise from CONFIG_HIGHPTE needing kmap_types.h, but also in case any
architectures I haven't built would have other such problems.
Hugh Dickins [Sun, 30 Oct 2005 01:16:21 +0000 (18:16 -0700)]
[PATCH] mm: init_mm without ptlock
First step in pushing down the page_table_lock. init_mm.page_table_lock has
been used throughout the architectures (usually for ioremap): not to serialize
kernel address space allocation (that's usually vmlist_lock), but because
pud_alloc,pmd_alloc,pte_alloc_kernel expect caller holds it.
Reverse that: don't lock or unlock init_mm.page_table_lock in any of the
architectures; instead rely on pud_alloc,pmd_alloc,pte_alloc_kernel to take
and drop it when allocating a new one, to check lest a racing task already
did. Similarly no page_table_lock in vmalloc's map_vm_area.
Some temporary ugliness in __pud_alloc and __pmd_alloc: since they also handle
user mms, which are converted only by a later patch, for now they have to lock
differently according to whether or not it's init_mm.
If sources get muddled, there's a danger that an arch source taking
init_mm.page_table_lock will be mixed with common source also taking it (or
neither take it). So break the rules and make another change, which should
break the build for such a mismatch: remove the redundant mm arg from
pte_alloc_kernel (ppc64 scrapped its distinct ioremap_mm in 2.6.13).
Exceptions: arm26 used pte_alloc_kernel on user mm, now pte_alloc_map; ia64
used pte_alloc_map on init_mm, now pte_alloc_kernel; parisc had bad args to
pmd_alloc and pte_alloc_kernel in unused USE_HPPA_IOREMAP code; ppc64
map_io_page forgot to unlock on failure; ppc mmu_mapin_ram and ppc64 im_free
took page_table_lock for no good reason.
Hugh Dickins [Sun, 30 Oct 2005 01:16:20 +0000 (18:16 -0700)]
[PATCH] mm: ia64 use expand_upwards
ia64 has expand_backing_store function for growing its Register Backing Store
vma upwards. But more complete code for this purpose is found in the
CONFIG_STACK_GROWSUP part of mm/mmap.c. Uglify its #ifdefs further to provide
expand_upwards for ia64 as well as expand_stack for parisc.
The Register Backing Store vma should be marked VM_ACCOUNT. Implement the
intention of growing it only a page at a time, instead of passing an address
outside of the vma to handle_mm_fault, with unknown consequences.
Hugh Dickins [Sun, 30 Oct 2005 01:16:19 +0000 (18:16 -0700)]
[PATCH] mm: mm_struct hiwaters moved
Slight and timid rearrangement of mm_struct: hiwater_rss and hiwater_vm were
tacked on the end, but it seems better to keep them near _file_rss, _anon_rss
and total_vm, in the same cacheline on those arches verified.
There are likely to be more profitable rearrangements, but less obvious (is it
good or bad that saved_auxv[AT_VECTOR_SIZE] isolates cpu_vm_mask and context
from many others?), needing serious instrumentation.
Hugh Dickins [Sun, 30 Oct 2005 01:16:18 +0000 (18:16 -0700)]
[PATCH] mm: update_hiwaters just in time
update_mem_hiwater has attracted various criticisms, in particular from those
concerned with mm scalability. Originally it was called whenever rss or
total_vm got raised. Then many of those callsites were replaced by a timer
tick call from account_system_time. Now Frank van Maarseveen reports that to
be found inadequate. How about this? Works for Frank.
Replace update_mem_hiwater, a poor combination of two unrelated ops, by macros
update_hiwater_rss and update_hiwater_vm. Don't attempt to keep
mm->hiwater_rss up to date at timer tick, nor every time we raise rss (usually
by 1): those are hot paths. Do the opposite, update only when about to lower
rss (usually by many), or just before final accounting in do_exit. Handle
mm->hiwater_vm in the same way, though it's much less of an issue. Demand
that whoever collects these hiwater statistics do the work of taking the
maximum with rss or total_vm.
And there has been no collector of these hiwater statistics in the tree. The
new convention needs an example, so match Frank's usage by adding a VmPeak
line above VmSize to /proc/<pid>/status, and also a VmHWM line above VmRSS
(High-Water-Mark or High-Water-Memory).
There was a particular anomaly during mremap move, that hiwater_vm might be
captured too high. A fleeting such anomaly remains, but it's quickly
corrected now, whereas before it would stick.
What locking? None: if the app is racy then these statistics will be racy,
it's not worth any overhead to make them exact. But whenever it suits,
hiwater_vm is updated under exclusive mmap_sem, and hiwater_rss under
page_table_lock (for now) or with preemption disabled (later on): without
going to any trouble, minimize the time between reading current values and
updating, to minimize those occasions when a racing thread bumps a count up
and back down in between.
Hugh Dickins [Sun, 30 Oct 2005 01:16:17 +0000 (18:16 -0700)]
[PATCH] mm: zap_pte out of line
There used to be just one call to zap_pte, but it shouldn't be inline now
there are two. Check for the common case pte_none before calling, and move
its rss accounting up into install_page or install_file_pte - which helps the
next patch.
Hugh Dickins [Sun, 30 Oct 2005 01:16:15 +0000 (18:16 -0700)]
[PATCH] mm: do_swap_page race major
Small adjustment: do_swap_page should report its !pte_same race as a major
fault if it had to read into swap cache, because whatever raced with it will
have found page already in cache and reported minor fault.
Hugh Dickins [Sun, 30 Oct 2005 01:16:13 +0000 (18:16 -0700)]
[PATCH] mm: copy_one_pte inc rss
Small adjustment, following Nick's suggestion: it's more straightforward for
copy_pte_range to let copy_one_pte do the rss incrementation, than use an
index it passed back. Saves a #define, and 16 bytes of .text.
Nick Piggin [Sun, 30 Oct 2005 01:16:12 +0000 (18:16 -0700)]
[PATCH] core remove PageReserved
Remove PageReserved() calls from core code by tightening VM_RESERVED
handling in mm/ to cover PageReserved functionality.
PageReserved special casing is removed from get_page and put_page.
All setting and clearing of PageReserved is retained, and it is now flagged
in the page_alloc checks to help ensure we don't introduce any refcount
based freeing of Reserved pages.
MAP_PRIVATE, PROT_WRITE of VM_RESERVED regions is tentatively being
deprecated. We never completely handled it correctly anyway, and is be
reintroduced in future if required (Hugh has a proof of concept).
Once PageReserved() calls are removed from kernel/power/swsusp.c, and all
arch/ and driver code, the Set and Clear calls, and the PG_reserved bit can
be trivially removed.
Last real user of PageReserved is swsusp, which uses PageReserved to
determine whether a struct page points to valid memory or not. This still
needs to be addressed (a generic page_is_ram() should work).
A last caveat: the ZERO_PAGE is now refcounted and managed with rmap (and
thus mapcounted and count towards shared rss). These writes to the struct
page could cause excessive cacheline bouncing on big systems. There are a
number of ways this could be addressed if it is an issue.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Refcount bug fix for filemap_xip.c
Hugh Dickins [Sun, 30 Oct 2005 01:16:10 +0000 (18:16 -0700)]
[PATCH] mm: m68k kill stram swap
Please, please now delete the Atari CONFIG_STRAM_SWAP code. It may be
excellent and ingenious code, but its reference to swap_vfsmnt betrays that it
hasn't been built since 2.5.1 (four years old come December), it's delving
deep into matters which are the preserve of core mm code, its only purpose is
to give the more conscientious mm guys an anxiety attack from time to time;
yet we keep on breaking it more and more.
If you want to use RAM for swap, then if the MTD driver does not already
provide just what you need, I'm sure David could be persuaded to add the
extra. But you'd also like to be able to allocate extents of that swap for
other use: we can give you a core interface for that if you need. But unbuilt
for four years suggests to me that there's no need at all.
I cannot swear the patch below won't break your build, but believe so.
Hugh Dickins [Sun, 30 Oct 2005 01:16:09 +0000 (18:16 -0700)]
[PATCH] mm: sh64 hugetlbpage.c
The sh64 hugetlbpage.c seems to be erroneous, left over from a bygone age,
clashing with the common hugetlb.c. Replace it by a copy of the sh
hugetlbpage.c. Except, delete that mk_pte_huge macro neither uses.
Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Hugh Dickins [Sun, 30 Oct 2005 01:16:08 +0000 (18:16 -0700)]
[PATCH] mm: dup_mmap down new mmap_sem
One anomaly remains from when Andrea rationalized the responsibilities of
mmap_sem and page_table_lock: in dup_mmap we add vmas to the child holding its
page_table_lock, but not the mmap_sem which normally guards the vma list and
rbtree. Which could be an issue for unuse_mm: though since it just walks down
the list (today with page_table_lock, tomorrow not), it's probably okay. Will
need a memory barrier? Oh, keep it simple, Nick and I agreed, no harm in
taking child's mmap_sem here.
Hugh Dickins [Sun, 30 Oct 2005 01:16:06 +0000 (18:16 -0700)]
[PATCH] mm: dup_mmap use oldmm more
Use the parent's oldmm throughout dup_mmap, instead of perversely going back
to current->mm. (Can you hear the sigh of relief from those mpnts? Usually I
squash them, but not today.)
Hugh Dickins [Sun, 30 Oct 2005 01:16:05 +0000 (18:16 -0700)]
[PATCH] mm: batch updating mm_counters
tlb_finish_mmu used to batch zap_pte_range's update of mm rss, which may be
worthwhile if the mm is contended, and would reduce atomic operations if the
counts were atomic. Let zap_pte_range now batch its updates to file_rss and
anon_rss, per page-table in case we drop the lock outside; and copy_pte_range
batch them too.
Hugh Dickins [Sun, 30 Oct 2005 01:16:05 +0000 (18:16 -0700)]
[PATCH] mm: rss = file_rss + anon_rss
I was lazy when we added anon_rss, and chose to change as few places as
possible. So currently each anonymous page has to be counted twice, in rss
and in anon_rss. Which won't be so good if those are atomic counts in some
configurations.
Change that around: keep file_rss and anon_rss separately, and add them
together (with get_mm_rss macro) when the total is needed - reading two
atomics is much cheaper than updating two atomics. And update anon_rss
upfront, typically in memory.c, not tucked away in page_add_anon_rmap.
Hugh Dickins [Sun, 30 Oct 2005 01:16:04 +0000 (18:16 -0700)]
[PATCH] mm: mm_init set_mm_counters
How is anon_rss initialized? In dup_mmap, and by mm_alloc's memset; but
that's not so good if an mm_counter_t is a special type. And how is rss
initialized? By set_mm_counter, all over the place. Come on, we just need to
initialize them both at once by set_mm_counter in mm_init (which follows the
memcpy when forking).
Hugh Dickins [Sun, 30 Oct 2005 01:16:03 +0000 (18:16 -0700)]
[PATCH] mm: tlb_finish_mmu forget rss
zap_pte_range has been counting the pages it frees in tlb->freed, then
tlb_finish_mmu has used that to update the mm's rss. That got stranger when I
added anon_rss, yet updated it by a different route; and stranger when rss and
anon_rss became mm_counters with special access macros. And it would no
longer be viable if we're relying on page_table_lock to stabilize the
mm_counter, but calling tlb_finish_mmu outside that lock.
Remove the mmu_gather's freed field, let tlb_finish_mmu stick to its own
business, just decrement the rss mm_counter in zap_pte_range (yes, there was
some point to batching the update, and a subsequent patch restores that). And
forget the anal paranoia of first reading the counter to avoid going negative
- if rss does go negative, just fix that bug.
Remove the mmu_gather's flushes and avoided_flushes from arm and arm26: no use
was being made of them. But arm26 alone was actually using the freed, in the
way some others use need_flush: give it a need_flush. arm26 seems to prefer
spaces to tabs here: respect that.
Hugh Dickins [Sun, 30 Oct 2005 01:16:02 +0000 (18:16 -0700)]
[PATCH] mm: tlb_is_full_mm was obscure
tlb_is_full_mm? What does that mean? The TLB is full? No, it means that the
mm's last user has gone and the whole mm is being torn down. And it's an
inline function because sparc64 uses a different (slightly better)
"tlb_frozen" name for the flag others call "fullmm".
And now the ptep_get_and_clear_full macro used in zap_pte_range refers
directly to tlb->fullmm, which would be wrong for sparc64. Rather than
correct that, I'd prefer to scrap tlb_is_full_mm altogether, and change
sparc64 to just use the same poor name as everyone else - is that okay?
Hugh Dickins [Sun, 30 Oct 2005 01:16:01 +0000 (18:16 -0700)]
[PATCH] mm: tlb_gather_mmu get_cpu_var
tlb_gather_mmu dates from before kernel preemption was allowed, and uses
smp_processor_id or __get_cpu_var to find its per-cpu mmu_gather. That works
because it's currently only called after getting page_table_lock, which is not
dropped until after the matching tlb_finish_mmu. But don't rely on that, it
will soon change: now disable preemption internally by proper get_cpu_var in
tlb_gather_mmu, put_cpu_var in tlb_finish_mmu.
Hugh Dickins [Sun, 30 Oct 2005 01:16:00 +0000 (18:16 -0700)]
[PATCH] mm: move_page_tables by extents
Speeding up mremap's moving of ptes has never been a priority, but the locking
will get more complicated shortly, and is already too baroque.
Scrap the current one-by-one moving, do an extent at a time: curtailed by end
of src and dst pmds (have to use PMD_SIZE: the way pmd_addr_end gets elided
doesn't match this usage), and by latency considerations.
One nice property of the old method is lost: it never allocated a page table
unless absolutely necessary, so you could free empty page tables by mremapping
to and fro. Whereas this way, it allocates a dst table wherever there was a
src table. I keep diving in to reinstate the old behaviour, then come out
preferring not to clutter how it now is.
Hugh Dickins [Sun, 30 Oct 2005 01:15:59 +0000 (18:15 -0700)]
[PATCH] mm: page fault handlers tidyup
Impose a little more consistency on the page fault handlers do_wp_page,
do_swap_page, do_anonymous_page, do_no_page, do_file_page: why not pass their
arguments in the same order, called the same names?
break_cow is all very well, but what it did was inlined elsewhere: easier to
compare if it's brought back into do_wp_page.
do_file_page's fallback to do_no_page dates from a time when we were testing
pte_file by using it wherever possible: currently it's peculiar to nonlinear
vmas, so just check that. BUG_ON if not? Better not, it's probably page
table corruption, so just show the pte: hmm, there's a pte_ERROR macro, let's
use that for do_wp_page's invalid pfn too.
Hah! Someone in the ppc64 world noticed pte_ERROR was unused so removed it:
restored (and say "pud" not "pmd" in its pud_ERROR).
Hugh Dickins [Sun, 30 Oct 2005 01:15:57 +0000 (18:15 -0700)]
[PATCH] mm: unlink_file_vma, remove_vma
Divide remove_vm_struct into two parts: first anon_vma_unlink plus
unlink_file_vma, to unlink the vma from the list and tree by which rmap or
vmtruncate might find it; then remove_vma to close, fput and free.
The intention here is to do the anon_vma_unlink and unlink_file_vma earlier,
in free_pgtables before freeing any page tables: so we can be sure that any
page tables traversed by rmap and vmtruncate are stable (and other, ordinary
cases are stabilized by holding mmap_sem).
This will be crucial to traversing pgd,pud,pmd without page_table_lock. But
testing the split-out patch showed that lifting the page_table_lock is
symbiotically necessary to make this change - the lock ordering is wrong to
move those unlinks into free_pgtables while it's under ptlock.
Hugh Dickins [Sun, 30 Oct 2005 01:15:56 +0000 (18:15 -0700)]
[PATCH] mm: remove_vma_list consolidation
unmap_vma doesn't amount to much, let's put it inside unmap_vma_list. Except
it doesn't unmap anything, unmap_region just did the unmapping: rename it to
remove_vma_list.
Hugh Dickins [Sun, 30 Oct 2005 01:15:56 +0000 (18:15 -0700)]
[PATCH] mm: vm_stat_account unshackled
The original vm_stat_account has fallen into disuse, with only one user, and
only one user of vm_stat_unaccount. It's easier to keep track if we convert
them all to __vm_stat_account, then free it from its __shackles.
Hugh Dickins [Sun, 30 Oct 2005 01:15:55 +0000 (18:15 -0700)]
[PATCH] mm: anon is already wrprotected
do_anonymous_page's pte_wrprotect causes some confusion: in such a case,
vm_page_prot must already be forcing COW, so must omit write permission, and
so the pte_wrprotect is redundant. Replace it by a comment to that effect,
and reword the comment on unuse_pte which also caused confusion.
Hugh Dickins [Sun, 30 Oct 2005 01:15:54 +0000 (18:15 -0700)]
[PATCH] mm: zap_pte_range dont dirty anon
zap_pte_range already avoids wasting time to mark_page_accessed on anon pages:
it can also skip anon set_page_dirty - the page only needs to be marked dirty
if shared with another mm, but that will say pte_dirty too.
Hugh Dickins [Sun, 30 Oct 2005 01:15:53 +0000 (18:15 -0700)]
[PATCH] mm: copy_pte_range progress fix
My latency breaking in copy_pte_range didn't work as intended: instead of
checking at regularish intervals, after the first interval it checked every
time around the loop, too impatient to be preempted. Fix that.
[PATCH] slab: add additional debugging to detect slabs from the wrong node
This patch adds some stack dumps if the slab logic is processing slab
blocks from the wrong node. This is necessary in order to detect
situations as encountered by Petr.
Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Lee Schermerhorn [Sun, 30 Oct 2005 01:15:51 +0000 (18:15 -0700)]
[PATCH] shrink_list(): skip anon pages if not may_swap
Martin Hicks' page cache reclaim patch added the 'may_swap' flag to the
scan_control struct; and modified shrink_list() not to add anon pages to
the swap cache if may_swap is not asserted.
However, further down, if the page is mapped, shrink_list() calls
try_to_unmap() which will call try_to_unmap_one() via try_to_unmap_anon ().
try_to_unmap_one() will BUG_ON() an anon page that is NOT in the swap
cache. Martin says he never encountered this path in his testing, but
agrees that it might happen.
This patch modifies shrink_list() to skip anon pages that are not already
in the swap cache when !may_swap, rather than just not adding them to the
cache.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Andi Kleen [Sun, 30 Oct 2005 01:15:48 +0000 (18:15 -0700)]
[PATCH] Convert mempolicies to nodemask_t
The NUMA policy code predated nodemask_t so it used open coded bitmaps.
Convert everything to nodemask_t. Big patch, but shouldn't have any actual
behaviour changes (except I removed one unnecessary check against
node_online_map and one unnecessary BUG_ON)
Seth, Rohit [Sun, 30 Oct 2005 01:15:48 +0000 (18:15 -0700)]
[PATCH] mm: set per-cpu-pages lower threshold to zero
Set the low water mark for hot pages in pcp to zero.
(akpm: for the life of me I cannot remember why we created pcp->low. Neither
can Martin and the changelog is silent. Maybe it was just a brainfart, but I
have this feeling that there was a reason. If not, we should remove the
fields completely. We'll see.)
Seth, Rohit [Sun, 30 Oct 2005 01:15:47 +0000 (18:15 -0700)]
[PATCH] mm: page_alloc: increase size of per-cpu-pages
Increase the page allocator's per-cpu magazines from 1/4MB to 1/2MB.
Over 100+ runs for a workload, the difference in mean is about 2%. The best
results for both are almost same. Though the max variation in results with
1/2MB is only 2.2%, whereas with 1/4MB it is 12%.
Rik Van Riel [Sun, 30 Oct 2005 01:15:46 +0000 (18:15 -0700)]
[PATCH] swaptoken tuning
It turns out that the original swap token implementation, by Song Jiang, only
enforced the swap token while the task holding the token is handling a page
fault. This patch approximates that, without adding an additional flag to the
mm_struct, by checking whether the mm->mmap_sem is held for reading, like the
page fault code does.
This patch has the effect of automatically, and gradually, disabling the
enforcement of the swap token when there is little or no paging going on, and
"turning up" the intensity of the swap token code the more the task holding
the token is thrashing.
Thanks to Song Jiang for pointing out this aspect of the token based thrashing
control concept.
The new code shows a slight degradation over the old swap token code, but
still a big win over running without the swap token.
Rik Van Riel [Sun, 30 Oct 2005 01:15:44 +0000 (18:15 -0700)]
[PATCH] add sem_is_read/write_locked()
Add sem_is_read/write_locked functions to the read/write semaphores, along the
same lines of the *_is_locked spinlock functions. The swap token tuning patch
uses sem_is_read_locked; sem_is_write_locked is added for completeness.
Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Nicolas Pitre [Sat, 29 Oct 2005 20:44:56 +0000 (21:44 +0100)]
[ARM] 3061/1: cleanup the XIP link address mess
Patch from Nicolas Pitre
Since vmlinux.lds.S is preprocessed, we can use the defines already
present in asm/memory.h (allowed by patch #3060) for the XIP kernel link
address instead of relying on a duplicated Makefile hardcoded value, and
also get rid of its dependency on awk to handle it at the same time.
While at it let's clean XIP stuff even further and make things clearer
in head.S with a nice code reduction.
Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Nicolas Pitre [Sat, 29 Oct 2005 20:44:55 +0000 (21:44 +0100)]
[ARM] 3060/1: allow constants found in asm/memory.h to be used in asm code
Patch from Nicolas Pitre
This patch allows for assorted type of cleanups by letting assembly code
use the same set of defines for constant values and avoid duplicated
definitions that might not always be in sync, or that might simply be
confusing due to the different names for the same thing.
Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Ralf Baechle [Thu, 20 Oct 2005 21:55:26 +0000 (22:55 +0100)]
Hack to resolve longstanding prefetch issue
Prefetching may be fatal on some systems if we're prefetching beyond the
end of memory on some systems. It's also a seriously bad idea on non
dma-coherent systems.
Andrew Isaacson [Thu, 20 Oct 2005 06:59:46 +0000 (23:59 -0700)]
pci-expmem-hack
CFE 1.2.5 and earlier fails to turn on the ExpMemEn bit in the
PCIFeatureControl register, which means that DMA does not work
beyond physical address 01_0000_0000, ergo to DRAM beyond 1GB.
With ExpMemEn turned on, 01_0000_0000-0f_ffff_ffff is mapped,
so DMA works for up to 61 GB of DRAM.
Will be fixed in CFE 1.2.6 (yet to be released).
Signed-Off-By: Andy Isaacson <adi@broadcom.com> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Atsushi Nemoto [Wed, 19 Oct 2005 10:57:14 +0000 (19:57 +0900)]
Fix zero length sys_cacheflush
Cacheflush(0, 0, 0) was crashing the system. This is because
flush_icache_range(start, end) tries to flushing whole address space
(0 - ~0UL) if both start and end are zero.
projects / linux-2.6-omap-h63xx.git / log