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.
Ralf Baechle [Sat, 1 Oct 2005 19:22:39 +0000 (20:22 +0100)]
Don't copy SB1 cache error handler to uncached memory.
This may have made sense on a paranoid day with pass 1 BCM1250 processors
that were throwing cache error exception left and right for no good
reason. On modern silicion that hardly makes sense and the code had
gotten just an obscurity ...
tx39_flush_cache_range() does nothing if !cpu_has_dc_aliases. It should
flush d-cache and invalidate i-cache since the TX39(H2) has separate I/D
cache.
projects / linux-2.6 / log