- 27 May, 2010 40 commits
-
-
Lee Schermerhorn authored
Example usage of generic "numa_mem_id()": The mainline slab code, since ~ 2.6.19, does not handle memoryless nodes well. Specifically, the "fast path"--____cache_alloc()--will never succeed as slab doesn't cache offnode object on the per cpu queues, and for memoryless nodes, all memory will be "off node" relative to numa_node_id(). This adds significant overhead to all kmem cache allocations, incurring a significant regression relative to earlier kernels [from before slab.c was reorganized]. This patch uses the generic topology function "numa_mem_id()" to return the "effective local memory node" for the calling context. This is the first node in the local node's generic fallback zonelist-- the same node that "local" mempolicy-based allocations would use. This lets slab cache these "local" allocations and avoid fallback/refill on every allocation. N.B.: Slab will need to handle node and memory hotplug events that could change the value returned by numa_mem_id() for any given node if recent changes to address memory hotplug don't already address this. E.g., flush all per cpu slab queues before rebuilding the zonelists while the "machine" is held in the stopped state. Performance impact on "hackbench 400 process 200" 2.6.34-rc3-mmotm-100405-1609 no-patch this-patch ia64 no memoryless nodes [avg of 10]: 11.713 11.637 ~0.65 diff ia64 cpus all on memless nodes [10]: 228.259 26.484 ~8.6x speedup The slowdown of the patched kernel from ~12 sec to ~28 seconds when configured with memoryless nodes is the result of all cpus allocating from a single node's mm pagepool. The cache lines of the single node are distributed/interleaved over the memory of the real physical nodes, but the zone lock, list heads, ... of the single node with memory still each live in a single cache line that is accessed from all processors. x86_64 [8x6 AMD] [avg of 40]: 2.883 2.845 Signed-off-by:
Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Tejun Heo <tj@kernel.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Nick Piggin <npiggin@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Eric Whitney <eric.whitney@hp.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: <linux-arch@vger.kernel.org> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Lee Schermerhorn authored
Enable 'HAVE_MEMORYLESS_NODES' by default when NUMA configured on ia64. Initialize percpu 'numa_mem' variable when starting secondary cpus. Generic initialization will handle the boot cpu. Nothing uses 'numa_mem_id()' yet. Subsequent patch with modify slab to use this. Signed-off-by:
-
Lee Schermerhorn authored
Introduce numa_mem_id(), based on generic percpu variable infrastructure to track "nearest node with memory" for archs that support memoryless nodes. Define API in <linux/topology.h> when CONFIG_HAVE_MEMORYLESS_NODES defined, else stubs. Architectures will define HAVE_MEMORYLESS_NODES if/when they support them. Archs can override definitions of: numa_mem_id() - returns node number of "local memory" node set_numa_mem() - initialize [this cpus'] per cpu variable 'numa_mem' cpu_to_mem() - return numa_mem for specified cpu; may be used as lvalue Generic initialization of 'numa_mem' occurs in __build_all_zonelists(). This will initialize the boot cpu at boot time, and all cpus on change of numa_zonelist_order, or when node or memory hot-plug requires zonelist rebuild. Archs that support memoryless nodes will need to initialize 'numa_mem' for secondary cpus as they're brought on-line. [akpm@linux-foundation.org: fix build] Signed-off-by:
Christoph Lameter <cl@linux-foundation.org> Cc: Tejun Heo <tj@kernel.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Nick Piggin <npiggin@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Eric Whitney <eric.whitney@hp.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: <linux-arch@vger.kernel.org> Signed-off-by:
-
Lee Schermerhorn authored
ia64: Use generic percpu implementation of numa_node_id() + intialize per cpu 'numa_node' + remove ia64 cpu_to_node() macro; use generic + define CONFIG_USE_PERCPU_NUMA_NODE_ID when NUMA configured Signed-off-by:
-
Lee Schermerhorn authored
x86 arch specific changes to use generic numa_node_id() based on generic percpu variable infrastructure. Back out x86's custom version of numa_node_id() Signed-off-by:
-
Lee Schermerhorn authored
Rework the generic version of the numa_node_id() function to use the new generic percpu variable infrastructure. Guard the new implementation with a new config option: CONFIG_USE_PERCPU_NUMA_NODE_ID. Archs which support this new implemention will default this option to 'y' when NUMA is configured. This config option could be removed if/when all archs switch over to the generic percpu implementation of numa_node_id(). Arch support involves: 1) converting any existing per cpu variable implementations to use this implementation. x86_64 is an instance of such an arch. 2) archs that don't use a per cpu variable for numa_node_id() will need to initialize the new per cpu variable "numa_node" as cpus are brought on-line. ia64 is an example. 3) Defining USE_PERCPU_NUMA_NODE_ID in arch dependent Kconfig--e.g., when NUMA is configured. This is required because I have retained the old implementation by default to allow archs to be modified incrementally, as desired. Subsequent patches will convert x86_64 and ia64 to use this implemenation. Signed-off-by: -
Jan Blunck authored
The inode's i_size is not protected by the big kernel lock. Therefore it does not make sense to recommend taking the BKL in filesystems llseek operations. Instead it should use the inode's mutex or use just use i_size_read() instead. Add a note that this is not protecting file->f_pos. Signed-off-by:
Jan Blunck <jblunck@suse.de> Acked-by:
Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Hellwig <hch@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Signed-off-by:
-
jan Blunck authored
Do not use the fallback default_llseek() if the readdir operation of the filesystem still uses the big kernel lock. Since llseek() modifies file->f_pos of the directory directly it may need locking to not confuse readdir which usually uses file->f_pos directly as well Since the special characteristics of the BKL (unlocked on schedule) are not necessary in this case, the inode mutex can be used for locking as provided by generic_file_llseek(). This is only possible since all filesystems, except reiserfs, either use a directory as a flat file or with disk address offsets. Reiserfs on the other hand uses a 32bit hash off the filename as the offset so generic_file_llseek() can get used as well since the hash is always smaller than sb->s_maxbytes (= (512 << 32) - blocksize). Signed-off-by:
Jan Kara <jack@suse.cz> Acked-by:
Anders Larsen <al@alarsen.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by:
-
Jan Blunck authored
st_open() suggests that llseek() doesn't work: "We really want to do nonseekable_open(inode, filp); here, but some versions of tar incorrectly call lseek on tapes and bail out if that fails. So we disallow pread() and pwrite(), but permit lseeks." Instead of using the fallback default_llseek() the driver should use noop_llseek() which leaves the file->f_pos untouched but succeeds. Signed-off-by:
-
Jan Blunck authored
__os_scsi_tape_open() suggests that llseek() doesn't work: "We really want to do nonseekable_open(inode, filp); here, but some versions of tar incorrectly call lseek on tapes and bail out if that fails. So we disallow pread() and pwrite(), but permit lseeks." Instead of using the fallback default_llseek() the driver should use noop_llseek() which leaves the file->f_pos untouched but succeeds. Signed-off-by:
-
jan Blunck authored
This is an implementation of ->llseek useable for the rare special case when userspace expects the seek to succeed but the (device) file is actually not able to perform the seek. In this case you use noop_llseek() instead of falling back to the default implementation of ->llseek. Signed-off-by:
-
Jan Blunck authored
Use nonseekable_open() for this since seeking is not supported anyway. Signed-off-by:
-
Jan Blunck authored
This test is not doing anything since it is always false if the mISDN_read() is called from vfs_read(). Besides that the driver uses nonseekable_open() and is not using off or file->f_pos anywhere. Signed-off-by:
-
Jan Blunck authored
Signed-off-by:
-
Jan Blunck authored
osst_read()/osst_write() modify file->f_pos directly instead of the ppos given to them. The VFS later updates the file->f_pos and overwrites it with the value of ppos. Signed-off-by:
-
FUJITA Tomonori authored
parisc uses iova and iova_length in scatterlist structure instead of dma_address and dma_length. However, the accessor are used so we can convert parisc to use asm-generic/scatterlist.h easily. Signed-off-by:
FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Helge Deller <deller@gmx.de> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
Haavard Skinnemoen <hskinnemoen@atmel.com> Signed-off-by:
-
FUJITA Tomonori authored
There are more architectures that don't support ARCH_HAS_SG_CHAIN than those that support it. This removes removes ARCH_HAS_SG_CHAIN in asm-generic/scatterlist.h and lets arhictectures to define it. It's clearer than defining ARCH_HAS_SG_CHAIN asm-generic/scatterlist.h and undefing it in arhictectures that don't support it. Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
Matt Turner <mattst88@gmail.com> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
-
Andrew Morton authored
Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by:
-
FUJITA Tomonori authored
There are only two ways to define sg_dma_len(); use sg->dma_length or sg->length. This patch introduces NEED_SG_DMA_LENGTH that enables architectures to choose sg->dma_length or sg->length. Signed-off-by:
-
FUJITA Tomonori authored
This is the first half of the attempt to use asm-generic/scatterlist.h on every architecture. There are only two ways to define scatterlist structure. So it's easy to convert every architecture to use asm-generic/scatterlist.h. This patch: The trick for ISA_DMA_THRESHOLD in asm-generic/scatterlist.h doesn't work for powerpc. This lets architectures defin ISA_DMA_THRESHOLD. Hopefully, we can remove ISA_DMA_THRESHOLD in the future; we can do better to decide if the bouncing is necessary or not. Signed-off-by:
-
Frederic Weisbecker authored
This adds three new types of kernel "crashes" in the lkdtm driver to trigger hardlockups, softlockups and task hung states at will. The first two are useful to test the new generic lockup detector and check its further regressions. The latter one is a bonus to check the hung task detector regressions even though it's not currently in rework. Signed-off-by:
Frederic Weisbecker <fweisbec@gmail.com> Cc: Simon Kagstrom <simon.kagstrom@netinsight.net> Cc: Ingo Molnar <mingo@elte.hu> Cc: Don Zickus <dzickus@redhat.com> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Signed-off-by:
-
Albin Tonnerre authored
Add the necessary parts to be enable the use of LZO-compressed initramfs build into the kernel. Signed-off-by:
Albin Tonnerre <albin.tonnerre@free-electrons.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Michal Marek <mmarek@suse.cz> Signed-off-by:
-
Cesar Eduardo Barros authored
radix_tree_prev_hole() used LONG_MAX to detect underflow; however, ULONG_MAX is clearly what was intended, both here and by its only user (count_history_pages at mm/readahead.c). Reviewed-by:
Wu Fengguang <fengguang.wu@intel.com> Signed-off-by:
Cesar Eduardo Barros <cesarb@cesarb.net> Signed-off-by:
-
Jeff Moyer authored
The aio compat code was not converting the struct iovecs from 32bit to 64bit pointers, causing either EINVAL to be returned from io_getevents, or EFAULT as the result of the I/O. This patch passes a compat flag to io_submit to signal that pointer conversion is necessary for a given iocb array. A variant of this was tested by Michael Tokarev. I have also updated the libaio test harness to exercise this code path with good success. Further, I grabbed a copy of ltp and ran the testcases/kernel/syscall/readv and writev tests there (compiled with -m32 on my 64bit system). All seems happy, but extra eyes on this would be welcome. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix CONFIG_COMPAT=n build] Signed-off-by:
Jeff Moyer <jmoyer@redhat.com> Reported-by:
Michael Tokarev <mjt@tls.msk.ru> Cc: Zach Brown <zach.brown@oracle.com> Cc: <stable@kernel.org> [2.6.35.1] Signed-off-by:
-
Jeff Moyer authored
It was reported in http://lkml.org/lkml/2010/3/8/309 that 32 bit readv and writev AIO operations were not functioning properly. It turns out that the code to convert the 32bit io vectors to 64 bits was never written. The results of that can be pretty bad, but in my testing, it mostly ended up in generating EFAULT as we walked off the list of I/O vectors provided. This patch set fixes the problem in my environment. are greatly appreciated. This patch: Factor out code that will be used by both compat_do_readv_writev and the compat aio submission code paths. Signed-off-by:
-
Anton Blanchard authored
Most distros turn the console verbosity down and that means a backtrace after a panic never makes it to the console. I assume we haven't seen this because a panic is often preceeded by an oops which will have called console_verbose. There are however a lot of places we call panic directly, and they are broken. Use console_verbose like we do in the oops path to ensure a directly called panic will print a backtrace. Signed-off-by:
Anton Blanchard <anton@samba.org> Acked-by:
Greg Kroah-Hartman <gregkh@suse.de> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by:
-
Julia Lawall authored
Use ERR_CAST(x) rather than ERR_PTR(PTR_ERR(x)). The former makes more clear what is the purpose of the operation, which otherwise looks like a no-op. The semantic patch that makes this change is as follows: (http://coccinelle.lip6.fr/) // <smpl> @@ type T; T x; identifier f; @@ T f (...) { <+... - ERR_PTR(PTR_ERR(x)) + x ...+> } @@ expression x; @@ - ERR_PTR(PTR_ERR(x)) + ERR_CAST(x) // </smpl> Signed-off-by:
Julia Lawall <julia@diku.dk> Signed-off-by:
-
FUJITA Tomonori authored
Add ARCH_KMALLOC_MINALIGN description in "Platform Issues" section. Signed-off-by:
-
