For small file block allocations, mballoc uses per cpu prealloc
space. Use goal block when searching for the right prealloc
space. Also make sure ext4_da_writepages tries to write
all the pages for small files in single attempt
ext4: Initialize writeback_index to 0 when allocating a new inode
The write_cache_pages() function uses the mapping->writeback_index as
the starting index to write out when range_cyclic is set. Properly
initialize writeback_index so that we start the writeout at index 0.
This was found when debugging the small file fragmentation on ext4.
Mingming Cao [Wed, 20 Aug 2008 02:15:58 +0000 (22:15 -0400)]
ext4: journal credit fix for the delayed allocation's writepages() function
Previous delalloc writepages implementation started a new transaction
outside of a loop which called get_block() to do the block allocation.
Since we didn't know exactly how many blocks would need to be allocated,
the estimated journal credits required was very conservative and caused
many issues.
With the reworked delayed allocation, a new transaction is created for
each get_block(), thus we don't need to guess how many credits for the
multiple chunk of allocation. We start every transaction with enough
credits for inserting a single exent. When estimate the credits for
indirect blocks to allocate a chunk of blocks, we need to know the
number of data blocks to allocate. We use the total number of reserved
delalloc datablocks; if that is too big, for non-extent files, we need
to limit the number of blocks to EXT4_MAX_TRANS_BLOCKS.
With the below changes we reserve credit needed to insert only one
extent resulting from a call to single get_block. This makes sure we
don't take too much journal credits during writeout. We also don't
limit the pages to write. That means we loop through the dirty pages
building largest possible contiguous block request. Then we issue a
single get_block request. We may get less block that we requested. If
so we would end up not mapping some of the buffer_heads. That means
those buffer_heads are still marked delay. Later in the writepage
callback via __mpage_writepage we redirty those pages.
We should also not limit/throttle wbc->nr_to_write in the filesystem
writepages callback. That cause wrong behaviour in
generic_sync_sb_inodes caused by wbc->nr_to_write being <= 0
Mingming Cao [Wed, 20 Aug 2008 02:16:03 +0000 (22:16 -0400)]
ext4: journal credits reservation fixes for DIO, fallocate
DIO and fallocate credit calculation is different than writepage, as
they do start a new journal right for each call to ext4_get_blocks_wrap().
This patch uses the helper function in DIO and fallocate case, passing
a flag indicating that the modified data are contigous thus could account
less indirect/index blocks.
This patch also fixed the journal credit reservation for direct I/O
(DIO). Previously the estimated credits for DIO only was calculated for
non-extent files, which was not enough if the file is extent-based.
Also fixed was fallocate double-counting credits for modifying the the
superblock.
Mingming Cao [Wed, 20 Aug 2008 02:16:05 +0000 (22:16 -0400)]
ext4: journal credits reservation fixes for extent file writepage
This patch modified the writepage/write_begin credit calculation for
extent files, to use the credits caculation helper function.
The current calculation of how many index/leaf blocks should be
accounted is too conservetive, it always considered the worse case,
where the tree level is 5, and in the case of multiple chunk
allocations, it always assumed no blocks were dirtied in common across
the allocations. This path uses the accurate depth of the inode with
some extras to calculate the index blocks, and also less conservative in
the case of multiple allocation accounting.
Mingming Cao [Wed, 20 Aug 2008 02:16:07 +0000 (22:16 -0400)]
ext4: journal credits calulation cleanup and fix for non-extent writepage
When considering how many journal credits are needed for modifying a
chunk of data, we need to account for the super block, inode block,
quota blocks and xattr block, indirect/index blocks, also, group bitmap
and group descriptor blocks for new allocation (including data and
indirect/index blocks). There are many places in ext4 do the calculation
on their own and often missed one or two meta blocks, and often they
assume single block allocation, and did not considering the multile
chunk of allocation case.
This patch is trying to cleanup current journal credit code, provides
some common helper funtion to calculate the journal credits, to be used
for writepage, writepages, DIO, fallocate, migration, defrag, and for
both nonextent and extent files.
This patch modified the writepage/write_begin credit caculation for
nonextent files, to use the new helper function. It also fixed the
problem that writepage on nonextent files did not consider the case
blocksize <pagesize, thus could possibelly need multiple block
allocation in a single transaction.
Eric Sandeen [Wed, 20 Aug 2008 02:19:50 +0000 (22:19 -0400)]
ext4: Fix bug where we return ENOSPC even though we have plenty of inodes
The find_group_flex() function starts with best_flex as the
parent_fbg_group, which happens to have 0 inodes free. Some of the
flex groups searched have free blocks and free inodes, but the
flex_freeb_ratio is < 10, so they're skipped. Then when a group is
compared to the current "best" flex group, it does not have more free
blocks than "best", so it is skipped as well.
This continues until no flex group with free inodes is found which has
a proper ratio or which has more free blocks than the "best" group,
and we're left with a "best" group that has 0 inodes free, and we
return -ENOSPC.
We fix this by changing the logic so that if the current "best" flex
group has no inodes free, and the current one does have room, it is
promoted to the next "best."
Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Josef Bacik [Wed, 20 Aug 2008 02:13:41 +0000 (22:13 -0400)]
ext4: don't try to resize if there are no reserved gdt blocks left
When trying to resize an ext4 fs and you run out of reserved gdt blocks,
you get an error that doesn't actually tell you what went wrong, it just
says that the gdb it picked is not correct, which is the case since you
don't have any reserved gdt blocks left. This patch adds a check to make
sure you have reserved gdt blocks to use, and if not prints out a more
relevant error.
Signed-off-by: Josef Bacik <jbacik@redhat.com> Cc: <linux-ext4@vger.kernel.org> Cc: Andreas Dilger <adilger@sun.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Theodore Ts'o [Sat, 16 Aug 2008 11:57:35 +0000 (07:57 -0400)]
ext4: Use ext4_discard_reservations instead of mballoc-specific call
In ext4_ext_truncate(), we should use the more generic
ext4_discard_reservations() call so we do the right thing when the
filesystem is mounted with the nomballoc option.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Mingming Cao <cmm@us.ibm.com>
Mingming Cao [Wed, 20 Aug 2008 02:16:59 +0000 (22:16 -0400)]
ext4: Fix delalloc release block reservation for truncate
Ext4 will release the reserved blocks for delayed allocations when
inode is truncated/unlinked. If there is no reserved block at all, we
shouldn't need to do so. But current code still tries to release the
reserved blocks regardless whether the counters's value is 0.
Continue to do that causes the later calculation to go wrong and a
kernel BUG_ON() caught that. This doesn't happen for extent-based
files, as the calculation for 0 reserved blocks was right for extent
based file.
This patch fixed the kernel BUG() due to above reason. It adds checks
for 0 to avoid unnecessary release and fix calculation for non-extent
files.
Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Theodore Ts'o [Thu, 14 Aug 2008 01:44:34 +0000 (21:44 -0400)]
ext4: Fix potential truncate BUG due to i_prealloc_list being non-empty
We need to call ext4_discard_reservation() earlier in ext4_truncate(),
to avoid a BUG() in ext4_mb_return_to_preallocation(), which is called
(ultimately) by ext4_free_blocks(). So we must ditch the blocks on
i_prealloc_list before we start freeing the data blocks.
ext4: Handle unwritten extent properly with delayed allocation
When using fallocate the buffer_heads are marked unwritten and unmapped.
We need to map them in the writepages after a get_block. Otherwise we
split the uninit extents, but never write the content to disk.
Linus Torvalds [Tue, 12 Aug 2008 23:38:45 +0000 (16:38 -0700)]
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
IB/ehca: Discard double CQE for one WR
IB/ehca: Check idr_find() return value
IB/ehca: Repoll CQ on invalid opcode
IB/ehca: Rename goto label in ehca_poll_cq_one()
IB/ehca: Update qp_state on cached modify_qp()
IPoIB/cm: Use vmalloc() to allocate rx_rings
Linus Torvalds [Tue, 12 Aug 2008 23:07:48 +0000 (16:07 -0700)]
Merge branch 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6
* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6:
[IA64] use bcd2bin/bin2bcd
[IA64] Ensure cpu0 can access per-cpu variables in early boot code
Bernhard Walle [Tue, 12 Aug 2008 22:09:14 +0000 (15:09 -0700)]
firmware/memmap: cleanup
Various cleanup the drivers/firmware/memmap (after review by AKPM):
- fix kdoc to conform to the standard
- move kdoc from header to implementation files
- remove superfluous WARN_ON() after kmalloc()
- WARN_ON(x); if (!x) -> if(!WARN_ON(x))
- improve some comments
Signed-off-by: Bernhard Walle <bwalle@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michael Abbott [Tue, 12 Aug 2008 22:09:11 +0000 (15:09 -0700)]
Make ioctl.h compatible with userland
The attached patch seems to already exist in a number of branches -- it
keeps popping up on Google for me, and is certainly already in Debian --
but is strangely absent from mainstream.
The problem appears to be that the patched file ends up as part of the
target toolchain, but unfortunately the gcc constant folding doesn't
appear to eliminate the __invalid_size_argument_for_IOC value early
enough. Certainly compiling C++ programs which use _IO... macros as
constants fails without this patch.
Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Randy Dunlap [Tue, 12 Aug 2008 22:09:10 +0000 (15:09 -0700)]
docsrc: fix getdelays printk formats
Fix printf format type warnings (seen on alpha & ia64):
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 6 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 7 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 8 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 9 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 12 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 13 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 16 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 17 has type '__u64'
Documentation/accounting/getdelays.c:214: warning: format '%15llu' expects type 'long long unsigned int', but argument 4 has type '__u64'
Documentation/accounting/getdelays.c:214: warning: format '%15llu' expects type 'long long unsigned int', but argument 5 has type '__u64'
Documentation/accounting/getdelays.c:221: warning: format '%llu' expects type 'long long unsigned int', but argument 2 has type '__u64'
Documentation/accounting/getdelays.c:221: warning: format '%llu' expects type 'long long unsigned int', but argument 3 has type '__u64'
Documentation/accounting/getdelays.c:221: warning: format '%llu' expects type 'long long unsigned int', but argument 4 has type '__u64'
Documentation/accounting/getdelays.c:221: warning: format '%llu' expects type 'long long unsigned int', but argument 5 has type '__u64'
Documentation/accounting/getdelays.c:221: warning: format '%llu' expects type 'long long unsigned int', but argument 6 has type '__u64'
Documentation/accounting/getdelays.c:236: warning: 'cmd_type' may be used uninitialized in this function
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Randy Dunlap [Tue, 12 Aug 2008 22:09:06 +0000 (15:09 -0700)]
docsrc: fix procfs example
Add MODULE_LICENSE() to DocBook/procfs_example.c since modpost complained
about a missing license there.
Remove tty procfs removal since the creation was deleted long ago
(http://git.kernel.org/?p=linux/kernel/git/tglx/history.git;a=commitdiff;h=5ad9cb65e9b15e5b83e2dd1c10a4bcaccc4ec644).
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: <J.A.K.Mouw@its.tudelft.nl> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Randy Dunlap [Tue, 12 Aug 2008 22:09:06 +0000 (15:09 -0700)]
docsrc: build Documentation/ sources
Currently source files in the Documentation/ sub-dir can easily bit-rot
since they are not generally buildable, either because they are hidden in
text files or because there are no Makefile rules for them. This needs to
be fixed so that the source files remain usable and good examples of code
instead of bad examples.
Add the ability to build source files that are in the Documentation/ dir.
Add to Kconfig as "BUILD_DOCSRC" config symbol.
Use "CONFIG_BUILD_DOCSRC=1 make ..." to build objects from the
Documentation/ sources. Or enable BUILD_DOCSRC in the *config system.
However, this symbol depends on HEADERS_CHECK since the header files need
to be installed (for userspace builds).
Built (using cross-tools) for x86-64, i386, alpha, ia64, sparc32,
sparc64, powerpc, sh, m68k, & mips.
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Reviewed-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Harvey Harrison [Tue, 12 Aug 2008 22:09:04 +0000 (15:09 -0700)]
byteorder: add a new include/linux/swab.h to define byteswapping functions
Collect the implementations from include/linux/byteorder/swab.h, swabb.h
in swab.h
The functionality provided covers:
u16 swab16(u16 val) - return a byteswapped 16 bit value
u32 swab32(u32 val) - return a byteswapped 32 bit value
u64 swab64(u64 val) - return a byteswapped 64 bit value
u32 swahw32(u32 val) - return a wordswapped 32 bit value
u32 swahb32(u32 val) - return a high/low byteswapped 32 bit value
Similar to above, but return swapped value from a naturally-aligned pointer
u16 swab16p(u16 *p)
u32 swab32p(u32 *p)
u64 swab64p(u64 *p)
u32 swahw32p(u32 *p)
u32 swahb32p(u32 *p)
Similar to above, but swap the value in-place (in-situ)
void swab16s(u16 *p)
void swab32s(u32 *p)
void swab64s(u64 *p)
void swahw32s(u32 *p)
void swahb32s(u32 *p)
Arches can override any of these with an optimized version by defining an
inline in their asm/byteorder.h (example given for swab16()):
Alexey Dobriyan [Tue, 12 Aug 2008 22:09:02 +0000 (15:09 -0700)]
seq_file: add seq_cpumask(), seq_nodemask()
Short enough reads from /proc/irq/*/smp_affinity return -EINVAL for no
good reason.
This became noticed with NR_CPUS=4096 patches, when length of printed
representation of cpumask becase 1152, but cat(1) continued to read with
1024-byte chunks. bitmap_scnprintf() in good faith fills buffer, returns
1023, check returns -EINVAL.
Fix it by switching to seq_file, so handler will just fill buffer and
doesn't care about offsets, length, filling EOF and all this crap.
For that add seq_bitmap(), and wrappers around it -- seq_cpumask() and
seq_nodemask().
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Reviewed-by: Paul Jackson <pj@sgi.com> Cc: Mike Travis <travis@sgi.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Krzysztof Helt [Tue, 12 Aug 2008 22:08:57 +0000 (15:08 -0700)]
fbcon: prevent cursor disappearance after switching to 512 character font
Adjust and honor the vc_scrl_erase_char for 256 and 512 character fonts.
It fixes the issue with disappearing cursor during scrolling
(http://bugzilla.kernel.org/show_bug.cgi?id=11258). The issue was
reported and tracked by Peter Hanzel.
Signed-off-by: Krzysztof Helt <krzysztof.h1@wp.pl> Reported-by: Peter Hanzel <hanzelpeter@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Specify how much physically continuous, DMA capable memory will be
allocated at driver initialization time. This allow to create framebuffer
device with larger virtual resolution. Combine with y-panning this can be
used to implement double buffering acceleration method.
Signed-off-by: Stanislaw Gruszka <stf_xl@wp.pl> Acked-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com> Acked-by: Krzysztof Helt <krzysztof.h1@wp.pl> Cc: Nicolas Ferre <nicolas.ferre@atmel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
atmel_lcdfb: set ypanstep to 1 and enable y-panning on AT91
Panning in the y-direction can be done by simply changing the DMA base
address. This code is already in place, but FBIOPAN_DISPLAY will
currently fail because ypanstep is 0.
Set ypanstep to 1 to indicate that we do support y-panning and also set
the necessary acceleration flags on AT91 (AVR32 already have them.)
Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com> Acked-by: Krzysztof Helt <krzysztof.h1@wp.pl> Cc: Nicolas Ferre <nicolas.ferre@atmel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Jean Delvare [Tue, 12 Aug 2008 22:08:55 +0000 (15:08 -0700)]
matrox maven: convert to a new-style i2c driver
The legacy i2c model is going away soon, so switch to the new model.
Signed-off-by: Jean Delvare <khali@linux-fr.org> Acked-by: Krzysztof Helt <krzysztof.h1@wp.pl> Cc: Petr Vandrovec <VANDROVE@vc.cvut.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Jean Delvare [Tue, 12 Aug 2008 22:08:54 +0000 (15:08 -0700)]
matroxfb: i2c structure templates clean-up
Clean up the use of structure templates in i2c-matroxfb. In this case
it's more efficient to initialize the few fields we need individually.
This makes i2c-matroxfb.ko 16% smaller on my system.
Signed-off-by: Jean Delvare <khali@linux-fr.org> Acked-by: Krzysztof Helt <krzysztof.h1@wp.pl> Cc: Petr Vandrovec <VANDROVE@vc.cvut.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The machine will crash if the i2c_attach_client() or maven_init_client()
calls fail, although nobody has yet reported this happening.
Signed-off-by: Jean Delvare <khali@linux-fr.org> Acked-by: Krzysztof Helt <krzysztof.h1@wp.pl> Cc: Petr Vandrovec <VANDROVE@vc.cvut.cz> Cc: <stable@kernel.org> [2.6.25.x, 2.6.26.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
David Miller [Tue, 12 Aug 2008 22:08:51 +0000 (15:08 -0700)]
radeonfb: fix accel engine hangs
Some chips appear to have the 2D engine hang during screen redraw,
typically in a sequence of copyarea operations. This appear to be
solved by adding a flush of the engine destination pixel cache
and waiting for the engine to be idle before issuing the accel
operation. The performance impact seems to be fairly small.
Here is a trace on an RV370 (PCI device ID 0x5b64), it records the
RBBM_STATUS register, then the source x/y, destination x/y, and
width/height used for the copy:
When things are going fine the copies complete before the next ROP is
even issued, but all of a sudden the 2D unit becomes active (bit 17 in
RBBM_STATUS) and the FIFO retry (bit 13) and FIFO pipeline busy (bit
14) are set as well. The FIFO begins to backup until it becomes full.
What happens next is the radeon_fifo_wait() times out, and we access
the chip illegally leading to a bus error which usually wedges the
box. None of this makes it to the console screen, of course :-)
radeon_fifo_wait() should be modified to reset the accelerator when
this timeout happens instead of programming the chip anyways.
Another quirk is that these copyarea calls will not happen until the
first drivers/char/vt.c:redraw_screen() occurs. This will only happen
if you 1) VC switch or 2) run "consolechars" or 3) unblank the screen.
This seems to happen because until a redraw_screen() the screen scrolling
method used by fbcon is not finalized yet. I've seen this with other fb
drivers too.
So if all you do is boot straight into X you will never see this bug on
the relevant chips.
Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: <stable@kernel.org> [2.6.25.x, 2.6.26.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Andy Whitcroft [Tue, 12 Aug 2008 22:08:49 +0000 (15:08 -0700)]
allocate structures for reservation tracking in hugetlbfs outside of spinlocks v2
[Andrew this should replace the previous version which did not check
the returns from the region prepare for errors. This has been tested by
us and Gerald and it looks good.
Bah, while reviewing the locking based on your previous email I spotted
that we need to check the return from the vma_needs_reservation call for
allocation errors. Here is an updated patch to correct this. This passes
testing here.]
Signed-off-by: Andy Whitcroft <apw@shadowen.org> Tested-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Andy Whitcroft [Tue, 12 Aug 2008 22:08:47 +0000 (15:08 -0700)]
hugetlbfs: allocate structures for reservation tracking outside of spinlocks
In the normal case, hugetlbfs reserves hugepages at map time so that the
pages exist for future faults. A struct file_region is used to track when
reservations have been consumed and where. These file_regions are
allocated as necessary with kmalloc() which can sleep with the
mm->page_table_lock held. This is wrong and triggers may-sleep warning
when PREEMPT is enabled.
Updates to the underlying file_region are done in two phases. The first
phase prepares the region for the change, allocating any necessary memory,
without actually making the change. The second phase actually commits the
change. This patch makes use of this by checking the reservations before
the page_table_lock is taken; triggering any necessary allocations. This
may then be safely repeated within the locks without any allocations being
required.
Credit to Mel Gorman for diagnosing this failure and initial versions of
the patch.
Signed-off-by: Andy Whitcroft <apw@shadowen.org> Tested-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Rabin Vincent [Tue, 12 Aug 2008 22:08:45 +0000 (15:08 -0700)]
cpuidle: make sysfs attributes sysdev class attributes
These attributes are really sysdev class attributes. The incorrect
definition leads to an oops because of recent changes which make sysdev
attributes use a different prototype.
Yoshinori Sato [Tue, 12 Aug 2008 22:08:43 +0000 (15:08 -0700)]
h8300: fix section mismatches
WARNING: vmlinux.o(.text+0x2fdf): Section mismatch in reference from the variable .LM3 to the variable .init.text:___alloc_bootmem
The function .LM3() references
the variable __init ___alloc_bootmem.
This is often because .LM3 lacks a __init
annotation or the annotation of ___alloc_bootmem is wrong.
WARNING: vmlinux.o(.text+0x2ff5): Section mismatch in reference from the variable .LM4 to the variable .init.text:___alloc_bootmem
The function .LM4() references
the variable __init ___alloc_bootmem.
This is often because .LM4 lacks a __init
annotation or the annotation of ___alloc_bootmem is wrong.
WARNING: vmlinux.o(.text+0x300b): Section mismatch in reference from the variable .LM5 to the variable .init.text:___alloc_bootmem
The function .LM5() references
the variable __init ___alloc_bootmem.
This is often because .LM5 lacks a __init
annotation or the annotation of ___alloc_bootmem is wrong.
WARNING: vmlinux.o(.text+0x304b): Section mismatch in reference from the variable .LM10 to the variable .init.text:_free_area_init
The function .LM10() references
the variable __init _free_area_init.
This is often because .LM10 lacks a __init
annotation or the annotation of _free_area_init is wrong.
WARNING: vmlinux.o(.text+0x30a3): Section mismatch in reference from the variable .LM17 to the variable .init.text:_free_all_bootmem
The function .LM17() references
the variable __init _free_all_bootmem.
This is often because .LM17 lacks a __init
annotation or the annotation of _free_all_bootmem is wrong.
Signed-off-by: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Jan Beulich [Tue, 12 Aug 2008 22:08:39 +0000 (15:08 -0700)]
page allocator: use no-panic variant of alloc_bootmem() in alloc_large_system_hash()
.. since a failed allocation is being (initially) handled gracefully, and
panic()-ed upon failure explicitly in the function if retries with smaller
sizes failed.
Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Jan Kara [Tue, 12 Aug 2008 22:08:39 +0000 (15:08 -0700)]
quota: documentation for sending "below quota" messages via netlink and tiny doc update
Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Gerald Schaefer [Tue, 12 Aug 2008 22:08:38 +0000 (15:08 -0700)]
hugetlb: call arch_prepare_hugepage() for surplus pages
The s390 software large page emulation implements shared page tables by
using page->index of the first tail page from a compound large page to
store page table information. This is set up in arch_prepare_hugepage(),
which is called from alloc_fresh_huge_page_node().
A similar call to arch_prepare_hugepage() is missing for surplus large
pages that are allocated in alloc_buddy_huge_page(), which breaks the
software emulation mode for (surplus) large pages on s390. This patch
adds the missing call to arch_prepare_hugepage(). It will have no effect
on other architectures where arch_prepare_hugepage() is a nop.
Also, use the correct order in the error path in alloc_fresh_huge_page_node().
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Acked-by: Nick Piggin <npiggin@suse.de> Acked-by: Adam Litke <agl@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Adrian Bunk [Tue, 12 Aug 2008 22:08:37 +0000 (15:08 -0700)]
feature-removal-schedule.txt: remove the NCR53C9x entry
Now that the driver is removed we should also remove the entry in
Documentation/feature-removal-schedule.txt
Signed-off-by: Adrian Bunk <bunk@kernel.org> Acked-by: Christoph Hellwig <hch@lst.de> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Under rare circumstances, the ehca hardware might erroneously generate
two CQEs for the same WQE, which is not compliant to the IB spec and
will cause unpredictable errors like memory being freed twice. To
avoid this problem, the driver needs to detect the second CQE and
discard it.
For this purpose, introduce an array holding as many elements as the
SQ of the QP, called sq_map. Each sq_map entry stores a "reported"
flag for one WQE in the SQ. When a work request is posted to the SQ,
the respective "reported" flag is set to zero. After the arrival of a
CQE, the flag is set to 1, which allows to detect the occurence of a
second CQE.
The mapping between WQE / CQE and the corresponding sq_map element is
implemented by replacing the lowest 16 Bits of the wr_id with the
index in the queue map. The original 16 Bits are stored in the sq_map
entry and are restored when the CQE is passed to the application.
Signed-off-by: Alexander Schmidt <alexs@linux.vnet.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
The idr_find() function may fail when trying to get the QP that is
associated with a CQE, e.g. when a QP has been destroyed between the
generation of a CQE and the poll request for it. In consequence, the
return value of idr_find() must be checked and the CQE must be
discarded when the QP cannot be found.
Signed-off-by: Alexander Schmidt <alexs@linux.vnet.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
When the ehca driver detects an invalid opcode in a CQE, it currently
passes the CQE to the application and returns with success. This patch
changes the CQE handling to discard CQEs with invalid opcodes and to
continue reading the next CQE from the CQ.
Signed-off-by: Alexander Schmidt <alexs@linux.vnet.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
Since the introduction of the port auto-detect mode for ehca, calls to
modify_qp() may be cached in the device driver when the ports are not
activated yet. When a modify_qp() call is cached, the qp state remains
untouched until the port is activated, which will leave the qp in the
reset state. In the reset state, however, it is not allowed to post SQ
WQEs, which confuses applications like ib_mad.
The solution for this problem is to immediately set the qp state as
requested by modify_qp(), even when the call is cached.
Signed-off-by: Alexander Schmidt <alexs@linux.vnet.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
Tony Luck [Tue, 12 Aug 2008 17:34:20 +0000 (10:34 -0700)]
[IA64] Ensure cpu0 can access per-cpu variables in early boot code
ia64 handles per-cpu variables a litle differently from other architectures
in that it maps the physical memory allocated for each cpu at a constant
virtual address (0xffffffffffff0000). This mapping is not enabled until
the architecture specific cpu_init() function is run, which causes problems
since some generic code is run before this point. In particular when
CONFIG_PRINTK_TIME is enabled, the boot cpu will trap on the access to
per-cpu memory at the first printk() call so the boot will fail without
the kernel printing anything to the console.
Fix this by allocating percpu memory for cpu0 in the kernel data section
and doing all initialization to enable percpu access in head.S before
calling any generic code.
Other cpus must take care not to access per-cpu variables too early, but
their code path from start_secondary() to cpu_init() is all in arch/ia64
Linus Torvalds [Tue, 12 Aug 2008 15:49:53 +0000 (08:49 -0700)]
Merge branch 'core-fixes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'core-fixes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
generic-ipi: fix stack and rcu interaction bug in smp_call_function_mask(), fix
* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus:
fix spinlock recursion in hvc_console
stop_machine: remove unused variable
modules: extend initcall_debug functionality to the module loader
export virtio_rng.h
lguest: use get_user_pages_fast() instead of get_user_pages()
mm: Make generic weak get_user_pages_fast and EXPORT_GPL it
lguest: don't set MAC address for guest unless specified
Linus Torvalds [Tue, 12 Aug 2008 15:28:32 +0000 (08:28 -0700)]
Merge branch 'agp-patches' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/agp-2.6
* 'agp-patches' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/agp-2.6:
agp: fix SIS 5591/5592 wrong PCI id
intel/agp: rewrite GTT on resume
agp: use dev_printk when possible
amd64-agp: run fallback when no bridges found, not when driver registration fails
intel_agp: official name for GM45 chipset
Nick Piggin [Tue, 12 Aug 2008 08:05:13 +0000 (18:05 +1000)]
generic-ipi: fix stack and rcu interaction bug in smp_call_function_mask(), fix
> > Nick Piggin (1):
> > generic-ipi: fix stack and rcu interaction bug in
> > smp_call_function_mask()
>
> I'm still not 100% sure that I have this patch right... I might have seen
> a lockup trace implicating the smp call function path... which may have
> been due to some other problem or a different bug in the new call function
> code, but if some more people can take a look at it before merging?
OK indeed it did have a couple of bugs. Firstly, I wasn't freeing the
data properly in the alloc && wait case. Secondly, I wasn't resetting
CSD_FLAG_WAIT in the for each cpu loop (so only the first CPU would
wait).
After those fixes, the patch boots and runs with the kmalloc commented
out (so it always executes the slowpath).
commit 611e097d7707741a336a0677d9d69bec40f29f3d
Author: Christian Borntraeger <borntraeger@de.ibm.com>
hvc_console: rework setup to replace irq functions with callbacks
introduced a spinlock recursion problem.
request_irq tries to call the handler if the IRQ is shared.
The irq handler of hvc_console calls hvc_poll and hvc_kill
which might take the hvc_struct spinlock. Therefore, we have
to call request_irq outside the spinlock.
We can move the notifier_add safely outside the spinlock as ->data must
not be changed by the backend. Otherwise, tty_hangup would fail anyway.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Arjan van de Ven [Wed, 30 Jul 2008 19:49:02 +0000 (12:49 -0700)]
modules: extend initcall_debug functionality to the module loader
The kernel has this really nice facility where if you put "initcall_debug"
on the kernel commandline, it'll print which function it's going to
execute just before calling an initcall, and then after the call completes
it will
1) print if it had an error code
2) checks for a few simple bugs (like leaving irqs off)
and
3) print how long the init call took in milliseconds.
While trying to optimize the boot speed of my laptop, I have been loving
number 3 to figure out what to optimize... ... and then I wished that
the same thing was done for module loading.
This patch makes the module loader use this exact same functionality; it's
a logical extension in my view (since modules are just sort of late
binding initcalls anyway) and so far I've found it quite useful in finding
where things are too slow in my boot.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Rusty Russell [Tue, 12 Aug 2008 22:52:53 +0000 (17:52 -0500)]
lguest: use get_user_pages_fast() instead of get_user_pages()
Using a simple page table thrashing program I measure a slight
improvement. The program creates five processes. Each touches 1000
pages then schedules the next process. We repeat this 1000 times. As
lguest only caches 4 cr3 values, this rebuilds a lot of shadow page
tables requiring virt->phys mappings.
Before: 5.93 seconds
After: 5.40 seconds
(Counts of slow vs fastpath in this usage are 6092 and 2852462 respectively.)
And more importantly for lguest, the code is simpler.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Krzysztof Helt [Wed, 6 Aug 2008 16:48:45 +0000 (18:48 +0200)]
agp: fix SIS 5591/5592 wrong PCI id
The correct id is the id of the main host (5591) not
the id of the PCI-to-PCI bridge AGP (0001).
Output from "lspci -nv" shows that only the former
has AGP capabilities flag set:
00:00.0 0600: 1039:5591 (rev 02)
Flags: bus master, medium devsel, latency 64
Memory at ec000000 (32-bit, non-prefetchable) [size=32M]
Capabilities: [c0] AGP version 1.0
Keith Packard [Thu, 31 Jul 2008 05:48:07 +0000 (15:48 +1000)]
intel/agp: rewrite GTT on resume
On my Intel chipset (965GM), the GTT is entirely erased across
suspend/resume. This patch simply re-plays the current mapping at resume
time to restore the table.=20
I noticed this once I started relying on persistent GTT mappings across VT
switch in our GEM work -- the old X server and DRM code carefully unbind
all memory from the GTT on VT switch, but GEM does not bother.
I placed the list management and rewrite code in the generic layer on the
assumption that it will be needed on other hardware, but I did not add the
rewrite call to anything other than the Intel resume function.
Keep a list of current GATT mappings. At resume time, rewrite them into
the GATT. This is needed on Intel (at least) as the entire GATT is
cleared across suspend/resume.
[akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Keith Packard <keithp@keithp.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Dave Airlie <airlied@redhat.com>
amd64-agp: run fallback when no bridges found, not when driver registration fails
I think the intent was that if no bridges matched agp_amd64_pci_table[],
we would fall back to checking for any bridge with the AGP capability.
But in the current code, we execute the fallback path only when
pci_register_driver() itself fails, which is unrelated to whether any
matching devices were found.
This patch counts the AGP bridges found in the probe() method and executes
the fallback path when none is found.
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Dave Airlie <airlied@redhat.com>
Zhenyu Wang [Wed, 30 Jul 2008 19:26:50 +0000 (12:26 -0700)]
intel_agp: official name for GM45 chipset
Signed-off-by: Zhenyu Wang <zhenyu.z.wang@intel.com> Cc: Dave Airlie <airlied@linux.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Dave Airlie <airlied@redhat.com>
Linus Torvalds [Mon, 11 Aug 2008 23:46:31 +0000 (16:46 -0700)]
Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
sched, cpu hotplug: fix set_cpus_allowed() use in hotplug callbacks
sched: fix mysql+oltp regression
sched_clock: delay using sched_clock()
sched clock: couple local and remote clocks
sched clock: simplify __update_sched_clock()
sched: eliminate scd->prev_raw
sched clock: clean up sched_clock_cpu()
sched clock: revert various sched_clock() changes
sched: move sched_clock before first use
sched: test runtime rather than period in global_rt_runtime()
sched: fix SCHED_HRTICK dependency
sched: fix warning in hrtick_start_fair()
Linus Torvalds [Mon, 11 Aug 2008 23:46:11 +0000 (16:46 -0700)]
Merge branch 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
posix-timers: fix posix_timer_event() vs dequeue_signal() race
posix-timers: do_schedule_next_timer: fix the setting of ->si_overrun
Linus Torvalds [Mon, 11 Aug 2008 23:44:35 +0000 (16:44 -0700)]
Merge branch 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: fix 2.6.27rc1 cannot boot more than 8CPUs
x86: make "apic" an early_param() on 32-bit, NULL check
EFI, x86: fix function prototype
x86, pci-calgary: fix function declaration
x86: work around gcc 3.4.x bug
x86: make "apic" an early_param() on 32-bit
x86, debug: tone down arch/x86/kernel/mpparse.c debugging printk
x86_64: restore the proper NR_IRQS define so larger systems work.
x86: Restore proper vector locking during cpu hotplug
x86: Fix broken VMI in 2.6.27-rc..
x86: fdiv bug detection fix
Peter Zijlstra [Mon, 11 Aug 2008 20:45:51 +0000 (22:45 +0200)]
lockdep: fix debug_lock_alloc
When we enable DEBUG_LOCK_ALLOC but do not enable PROVE_LOCKING and or
LOCK_STAT, lock_alloc() and lock_release() turn into nops, even though
we should be doing hlock checking (check=1).
This causes a false warning and a lockdep self-disable.
Rectify this.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Linus Torvalds [Mon, 11 Aug 2008 17:44:43 +0000 (10:44 -0700)]
Merge branch 'for-linus' of git://git.o-hand.com/linux-mfd
* 'for-linus' of git://git.o-hand.com/linux-mfd:
mfd: tc6393 cleanup and update
mfd: have TMIO drivers and subdevices depend on ARM
mfd: TMIO MMC driver
mfd: driver for the TMIO NAND controller
mfd: t7l66 MMC platform data
mfd: tc6387 MMC platform data
mfd: Fix 7l66 and 6387 according to the new mfd-core API
mfd: Fix tc6393 according to the new tmio.h
mfd: driver for the TC6387XB TMIO controller.
mfd: driver for the T7L66XB TMIO SoC
mfd: TMIO MMC structures and accessors.
Linus Torvalds [Mon, 11 Aug 2008 17:44:13 +0000 (10:44 -0700)]
Merge branch 'i2c-for-linus' of git://jdelvare.pck.nerim.net/jdelvare-2.6
* 'i2c-for-linus' of git://jdelvare.pck.nerim.net/jdelvare-2.6:
hwmon: (lm75) Drop legacy i2c driver
i2c: correct some size_t printk formats
i2c: Check for address business before creating clients
i2c: Let users select algorithm drivers manually again
i2c: Fix NULL pointer dereference in i2c_new_probed_device
i2c: Fix oops on bus multiplexer driver loading
projects / linux-2.6 / log