- 17 Feb, 2011 40 commits
-
-
NeilBrown authored
commit 6c987910 upstream. commit 589a594b (2.6.37-rc4) fixed a problem were md_thread would sometimes call the ->run function at a bad time. If an error is detected during array start up after the md_thread has been started, the md_thread is killed. This resulted in the ->run function being called once. However the array may not be in a state that it is safe to call ->run. However the fix imposed meant that ->run was not called on a timeout. This means that when an array goes idle, bitmap bits do not get cleared promptly. While the array is busy the bits will still be cleared when appropriate so this is not very serious. There is no risk to data. Change the test so that we only avoid calling ->run when the thread is being stopped. This more explicitly addresses the problem situation. This is suitable for 2.6.37-stable and any -stable kernel to which 589a594b was applied. Signed-off-by:
NeilBrown <neilb@suse.de> Signed-off-by:
Greg Kroah-Hartman <gregkh@suse.de>
-
NeilBrown authored
commit bf572541 upstream. Commit 1a855a06 (2.6.37-rc4) fixed a problem where devices were re-added when they shouldn't be but caused a regression in a less common case that means sometimes devices cannot be re-added when they should be. In particular, when re-adding a device to an array without metadata we should always access the device, but after the above commit we didn't. This patch sets the In_sync flag in that case so that the re-add succeeds. This patch is suitable for any -stable kernel to which 1a855a06 was applied. Signed-off-by:
-
Stanislaw Gruszka authored
commit 4e5518ca upstream. pcmcia_request_irq() and pcmcia_enable_device() are intended to be called from process context (first function allocate memory with GFP_KERNEL, second take a mutex). We can not take spin lock and call them. It's safe to move spin lock after pcmcia_enable_device() as we still hold off IRQ until dev->base_addr is 0 and driver will not proceed with interrupts when is not ready. Patch resolves: https://bugzilla.redhat.com/show_bug.cgi?id=643758 Reported-and-tested-by: rbugz@biobind.com Signed-off-by:
Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by:
John W. Linville <linville@tuxdriver.com> Signed-off-by:
-
Anton Blanchard authored
commit 6dc19899 upstream. I noticed a failure where we hit the following WARN_ON in generic_smp_call_function_interrupt: if (!cpumask_test_and_clear_cpu(cpu, data->cpumask)) continue; data->csd.func(data->csd.info); refs = atomic_dec_return(&data->refs); WARN_ON(refs < 0); <------------------------- We atomically tested and cleared our bit in the cpumask, and yet the number of cpus left (ie refs) was 0. How can this be? It turns out commit 54fdade1 ("generic-ipi: make struct call_function_data lockless") is at fault. It removes locking from smp_call_function_many and in doing so creates a rather complicated race. The problem comes about because: - The smp_call_function_many interrupt handler walks call_function.queue without any locking. - We reuse a percpu data structure in smp_call_function_many. - We do not wait for any RCU grace period before starting the next smp_call_function_many. Imagine a scenario where CPU A does two smp_call_functions back to back, and CPU B does an smp_call_function in between. We concentrate on how CPU C handles the calls: CPU A CPU B CPU C CPU D smp_call_function smp_call_function_interrupt walks call_function.queue sees data from CPU A on list smp_call_function smp_call_function_interrupt walks call_function.queue sees (stale) CPU A on list smp_call_function int clears last ref on A list_del_rcu, unlock smp_call_function reuses percpu *data A data->cpumask sees and clears bit in cpumask might be using old or new fn! decrements refs below 0 set data->refs (too late!) The important thing to note is since the interrupt handler walks a potentially stale call_function.queue without any locking, then another cpu can view the percpu *data structure at any time, even when the owner is in the process of initialising it. The following test case hits the WARN_ON 100% of the time on my PowerPC box (having 128 threads does help :) #include <linux/module.h> #include <linux/init.h> #define ITERATIONS 100 static void do_nothing_ipi(void *dummy) { } static void do_ipis(struct work_struct *dummy) { int i; for (i = 0; i < ITERATIONS; i++) smp_call_function(do_nothing_ipi, NULL, 1); printk(KERN_DEBUG "cpu %d finished\n", smp_processor_id()); } static struct work_struct work[NR_CPUS]; static int __init testcase_init(void) { int cpu; for_each_online_cpu(cpu) { INIT_WORK(&work[cpu], do_ipis); schedule_work_on(cpu, &work[cpu]); } return 0; } static void __exit testcase_exit(void) { } module_init(testcase_init) module_exit(testcase_exit) MODULE_LICENSE("GPL"); MODULE_AUTHOR("Anton Blanchard"); I tried to fix it by ordering the read and the write of ->cpumask and ->refs. In doing so I missed a critical case but Paul McKenney was able to spot my bug thankfully :) To ensure we arent viewing previous iterations the interrupt handler needs to read ->refs then ->cpumask then ->refs _again_. Thanks to Milton Miller and Paul McKenney for helping to debug this issue. [miltonm@bga.com: add WARN_ON and BUG_ON, remove extra read of refs before initial read of mask that doesn't help (also noted by Peter Zijlstra), adjust comments, hopefully clarify scenario ] [miltonm@bga.com: remove excess tests] Signed-off-by:
Anton Blanchard <anton@samba.org> Signed-off-by:
Milton Miller <miltonm@bga.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by:
-
David Dillow authored
commit 20d9600c upstream. When using devices that support max_segments > BIO_MAX_PAGES (256), direct IO tries to allocate a bio with more pages than allowed, which leads to an oops in dio_bio_alloc(). Clamp the request to the supported maximum, and change dio_bio_alloc() to reflect that bio_alloc() will always return a bio when called with __GFP_WAIT and a valid number of vectors. [akpm@linux-foundation.org: remove redundant BUG_ON()] Signed-off-by:
David Dillow <dillowda@ornl.gov> Reviewed-by:
Jeff Moyer <jmoyer@redhat.com> Signed-off-by:
-
Randy Dunlap authored
commit 2550326a upstream. Fix collision with kernel-supplied #define: drivers/video/backlight/88pm860x_bl.c:24:1: warning: "CURRENT_MASK" redefined arch/x86/include/asm/page_64_types.h:6:1: warning: this is the location of the previous definition Signed-off-by:
Randy Dunlap <randy.dunlap@oracle.com> Cc: Haojian Zhuang <haojian.zhuang@marvell.com> Cc: Richard Purdie <rpurdie@rpsys.net> Signed-off-by:
-
KAMEZAWA Hiroyuki authored
commit 925268a0 upstream. Now, memory_hotplug_(un)lock() is used for add/remove/offline pages for avoiding races with hibernation. But this should be held in online_pages(), too. It seems asymmetric. There are cases where one has to avoid a race with memory hotplug notifier and his own local code, and hotplug v.s. hotplug. This will add a generic solution for avoiding races. In other view, having lock here has no big impacts. online pages is tend to be done by udev script at el against each memory section one by one. Then, it's better to have lock here, too. Reviewed-by:
Christoph Lameter <cl@linux.com> Acked-by:
David Rientjes <rientjes@google.com> Signed-off-by:
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by:
Pekka Enberg <penberg@kernel.org> Signed-off-by:
-
Soren Hansen authored
commit de1f016f upstream. Commit 2a48fc0a ("block: autoconvert trivial BKL users to private mutex") replaced uses of the BKL in the nbd driver with mutex operations. Since then, I've been been seeing these lock ups: INFO: task qemu-nbd:16115 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. qemu-nbd D 0000000000000001 0 16115 16114 0x00000004 ffff88007d775d98 0000000000000082 ffff88007d775fd8 ffff88007d774000 0000000000013a80 ffff8800020347e0 ffff88007d775fd8 0000000000013a80 ffff880133730000 ffff880002034440 ffffea0004333db8 ffffffffa071c020 Call Trace: [<ffffffff815b9997>] __mutex_lock_slowpath+0xf7/0x180 [<ffffffff815b93eb>] mutex_lock+0x2b/0x50 [<ffffffffa071a21c>] nbd_ioctl+0x6c/0x1c0 [nbd] [<ffffffff812cb970>] blkdev_ioctl+0x230/0x730 [<ffffffff811967a1>] block_ioctl+0x41/0x50 [<ffffffff81175c03>] do_vfs_ioctl+0x93/0x370 [<ffffffff81175f61>] sys_ioctl+0x81/0xa0 [<ffffffff8100c0c2>] system_call_fastpath+0x16/0x1b Instrumenting the nbd module's ioctl handler with some extra logging clearly shows the NBD_DO_IT ioctl being invoked which is a long-lived ioctl in the sense that it doesn't return until another ioctl asks the driver to disconnect. However, that other ioctl blocks, waiting for the module-level mutex that replaced the BKL, and then we're stuck. This patch removes the module-level mutex altogether. It's clearly wrong, and as far as I can see, it's entirely unnecessary, since the nbd driver maintains per-device mutexes, and I don't see anything that would require a module-level (or kernel-level, for that matter) mutex. Signed-off-by:
Soren Hansen <soren@linux2go.dk> Acked-by:
Serge Hallyn <serge.hallyn@canonical.com> Acked-by:
Paul Clements <paul.clements@steeleye.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by:
-
Michael Büsch authored
commit dd3cb633 upstream. This fixes parsing of the device invariants (MAC address) for PCMCIA SSB devices. ssb_pcmcia_do_get_invariants expects an iv pointer as data argument. Tested-by:
dylan cristiani <d.cristiani@idem-tech.it> Signed-off-by:
Michael Buesch <mb@bu3sch.de> Signed-off-by:
-
Corey Minyard authored
commit d2478521 upstream. This patch fixes an OOPS triggered when calling modprobe ipmi_si a second time after the first modprobe returned without finding any ipmi devices. This can happen if you reload the module after having the first module load fail. The driver was not deregistering from PNP in that case. Peter Huewe originally reported this patch and supplied a fix, I have a different patch based on Linus' suggestion that cleans things up a bit more. Cc: openipmi-developer@lists.sourceforge.net Reviewed-by:
Peter Huewe <peterhuewe@gmx.de> Cc: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by:
Corey Minyard <cminyard@mvista.com> Signed-off-by:
-
Oleg Nesterov authored
commit 66832eb4 upstream. Starting from perf_event_alloc()->perf_init_event(), the kernel assumes that event->cpu is either -1 or the valid CPU number. Change perf_event_alloc() to validate this argument early. This also means we can remove the similar check in find_get_context(). Signed-off-by:
Oleg Nesterov <oleg@redhat.com> Acked-by:
Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Prasad <prasad@linux.vnet.ibm.com> Cc: Roland McGrath <roland@redhat.com> LKML-Reference: <20110118161032.GC693@redhat.com> Signed-off-by:
Ingo Molnar <mingo@elte.hu> Signed-off-by:
-
Oleg Nesterov authored
commit 22a4ec72 upstream. If task == NULL, find_get_context() should always check that cpu is correct. Afaics, the bug was introduced by 38a81da2 "perf events: Clean up pid passing", but even before that commit "&& cpu != -1" was not exactly right, -ESRCH from find_task_by_vpid() is not accurate. Signed-off-by:
-
Eric Dumazet authored
commit 88d4f0db upstream. Commit 927c7a9e ("perf: Fix race in callchains") introduced a mismatch in the sizing of struct callchain_cpus_entries. nr_cpu_ids must be used instead of num_possible_cpus(), or we might get out of bound memory accesses on some machines. Signed-off-by:
Eric Dumazet <eric.dumazet@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1295980851.3588.351.camel@edumazet-laptop> Signed-off-by:
-
Michal Hocko authored
commit fceda1bf upstream. __setup based kernel command line parameters handlers which are handled in obsolete_checksetup are provided with the parameter value including = (more precisely everything right after the parameter name). This means that the current implementation of swapaccount[=1|0] doesn't work at all because if there is a value for the parameter then we are testing for "0" resp. "1" but we are getting "=0" resp. "=1" and if there is no parameter value we are getting an empty string rather than NULL. The original noswapccount parameter, which doesn't care about the value, works correctly. Signed-off-by:
Michal Hocko <mhocko@suse.cz> Acked-by:
-
Marcin Slusarz authored
commit 9ffdc6c3 upstream. Signed-off-by:
Marcin Slusarz <marcin.slusarz@gmail.com> [ add {}'s to fix a warning ] Signed-off-by:
Don Zickus <dzickus@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1296230433-6261-3-git-send-email-dzickus@redhat.com> Signed-off-by:
-
Marcin Slusarz authored
commit 39735766 upstream. If it was not possible to enable watchdog for any cpu, switch watchdog_enabled back to 0, because it's visible via kernel.watchdog sysctl. Signed-off-by:
-
Guy Martin authored
commit fbea6684 upstream. Remove the broken line wrapping handling in pdc_iodc_print(). It is broken in 3 ways : - It doesn't keep track of the current screen position, it just assumes that the new buffer will be printed at the begining of the screen. - It doesn't take in account that non printable characters won't increase the current position on the screen. - And last but not least, it triggers a kernel panic if a backspace is the first char in the provided buffer : Backtrace: [<0000000040128ec4>] pdc_console_write+0x44/0x78 [<0000000040128f18>] pdc_console_tty_write+0x20/0x38 [<000000004032f1ac>] n_tty_write+0x2a4/0x550 [<000000004032b158>] tty_write+0x1e0/0x2d8 [<00000000401bb420>] vfs_write+0xb8/0x188 [<00000000401bb630>] sys_write+0x68/0xb8 [<0000000040104eb8>] syscall_exit+0x0/0x14 Most terminals handle the line wrapping just fine. I've confirmed that it works correctly on a C8000 with both vga and serial output. Signed-off-by:
Guy Martin <gmsoft@tuxicoman.be> Signed-off-by:
James Bottomley <James.Bottomley@suse.de> Signed-off-by:
-
Shirish Pargaonkar authored
commit 540b2e37 upstream. NTLM response length was changed to 16 bytes instead of 24 bytes that are sent in Tree Connection Request during share-level security share mounts. Revert it back to 24 bytes. Reported-and-Tested-by:
Grzegorz Ozanski <grzegorz.ozanski@intel.com> Acked-by:
Jeff Layton <jlayton@redhat.com> Signed-off-by:
Shirish Pargaonkar <shirishpargaonkar@gmail.com> Acked-by:
Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by:
Steve French <sfrench@us.ibm.com> Signed-off-by:
-
Pavel Shilovsky authored
commit 12fed00d upstream. When we get oplock break notification we should set the appropriate value of OplockLevel field in oplock break acknowledge according to the oplock level held by the client in this time. As we only can have level II oplock or no oplock in the case of oplock break, we should be aware only about clientCanCacheRead field in cifsInodeInfo structure. Also fix bug connected with wrong interpretation of OplockLevel field during oplock break notification processing. Signed-off-by:
Pavel Shilovsky <piastryyy@gmail.com> Signed-off-by:
-
Russell King authored
commit e98ff0f5 upstream. Allow non-ARM SMP processors to use the SMP_ON_UP feature. CPUs supporting SMP must have the new CPU ID format, so check for this first. Then check for ARM11MPCore, which fails the MPIDR check. Lastly check the MPIDR reports multiprocessing extensions and that the CPU is part of a multiprocessing system. Reported-and-Tested-by:
Stephen Boyd <sboyd@codeaurora.org> Acked-by:
Will Deacon <will.deacon@arm.com> Signed-off-by:
Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by:
-
Russell King authored
commit 0eb0511d upstream. Use r0,r3-r6 rather than r0,r3,r4,r6,r7, which makes it easier to understand which registers can be modified. Also document which registers hold values which must be preserved. Signed-off-by:
-
Tejun Heo authored
commit e159489b upstream. Currently, the lockdep annotation in flush_work() requires exclusive access on the workqueue the target work is queued on and triggers warning if a work is trying to flush another work on the same workqueue; however, this is no longer true as workqueues can now execute multiple works concurrently. This patch adds lock_map_acquire_read() and make process_one_work() hold read access to the workqueue while executing a work and start_flush_work() check for write access if concurrnecy level is one or the workqueue has a rescuer (as only one execution resource - the rescuer - is guaranteed to be available under memory pressure), and read access if higher. This better represents what's going on and removes spurious lockdep warnings which are triggered by fake dependency chain created through flush_work(). * Peter pointed out that flushing another work from a WQ_MEM_RECLAIM wq breaks forward progress guarantee under memory pressure. Condition check accordingly updated. Signed-off-by:
Tejun Heo <tj@kernel.org> Reported-by:
"Rafael J. Wysocki" <rjw@sisk.pl> Tested-by:
-
Stefan Richter authored
commit 6044565a upstream. Regression since commit 10389536, "firewire: core: check for 1394a compliant IRM, fix inaccessibility of Sony camcorder": The camcorder Canon MV5i generates lots of bus resets when asynchronous requests are sent to it (e.g. Config ROM read requests or FCP Command write requests) if the camcorder is not root node. This causes drop- outs in videos or makes the camcorder entirely inaccessible. https://bugzilla.redhat.com/show_bug.cgi?id=633260 Fix this by allowing any Canon device, even if it is a pre-1394a IRM like MV5i are, to remain root node (if it is at least Cycle Master capable). With the FireWire controller cards that I tested, MV5i always becomes root node when plugged in and left to its own devices. Reported-by: Ralf Lange Signed-off-by:
Stefan Richter <stefanr@s5r6.in-berlin.de> Signed-off-by:
-
Ken Mills authored
commit 91f78f36 upstream. This field is settable but did not get copied. Signed-off-by:
Ken Mills <ken.k.mills@intel.com> Signed-off-by:
Alan Cox <alan@linux.intel.com> Signed-off-by:
-
Benjamin Herrenschmidt authored
commit 1f1936ff upstream. Some of those functions try to adjust the CPU features, for example to remove NAP support on some revisions. However, they seem to use r5 as an index into the CPU table entry, which might have been right a long time ago but no longer is. r4 is the right register to use. This probably caused some off behaviours on some PowerMac variants using 750cx or 7455 processor revisions. Signed-off-by:
Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by:
-
Anton Blanchard authored
commit 429f4d8d upstream. When converting to the new cpumask code I screwed up: - if (cpu_isset(cpu, numa_cpumask_lookup_table[node])) { - cpu_clear(cpu, numa_cpumask_lookup_table[node]); + if (cpumask_test_cpu(cpu, node_to_cpumask_map[node])) { + cpumask_set_cpu(cpu, node_to_cpumask_map[node]); This was introduced in commit 25863de0 (powerpc/cpumask: Convert NUMA code to new cpumask API) Fix it. Signed-off-by:
-
Anton Blanchard authored
commit 57cdfdf8 upstream. Spinlocks on shared processor partitions use H_YIELD to notify the hypervisor we are waiting on another virtual CPU. Unfortunately this means the hcall tracepoints can recurse. The patch below adds a percpu depth and checks it on both the entry and exit hcall tracepoints. Signed-off-by:
Steven Rostedt <rostedt@goodmis.org> Signed-off-by:
-
Timur Tabi authored
commit b2e0861e upstream. In order to prevent the fsl_dma driver from claiming the DMA channels that the P1022DS audio driver needs, the compatible properties for those nodes must say "fsl,ssi-dma-channel" instead of "fsl,eloplus-dma-channel". Signed-off-by:
Timur Tabi <timur@freescale.com> Signed-off-by:
Kumar Gala <galak@kernel.crashing.org> Signed-off-by:
-
Justin TerAvest authored
commit 02a8f01b upstream. Commit 7667aa06 added logic to wait for the last queue of the group to become busy (have at least one request), so that the group does not lose out for not being continuously backlogged. The commit did not check for the condition that the last queue already has some requests. As a result, if the queue already has requests, wait_busy is set. Later on, cfq_select_queue() checks the flag, and decides that since the queue has a request now and wait_busy is set, the queue is expired. This results in early expiration of the queue. This patch fixes the problem by adding a check to see if queue already has requests. If it does, wait_busy is not set. As a result, time slices do not expire early. The queues with more than one request are usually buffered writers. Testing shows improvement in isolation between buffered writers. Signed-off-by:
Justin TerAvest <teravest@google.com> Reviewed-by:
Gui Jianfeng <guijianfeng@cn.fujitsu.com> Acked-by:
Vivek Goyal <vgoyal@redhat.com> Signed-off-by:
Jens Axboe <jaxboe@fusionio.com> Signed-off-by:
-
Peter Zijlstra authored
commit 06c3bc65 upstream. cpu_stopper_thread() migration_cpu_stop() __migrate_task() deactivate_task() dequeue_task() dequeue_task_rq() update_curr_rt() Will call update_curr_rt() on rq->curr, which at that time is rq->stop. The problem is that rq->stop.prio matches an RT prio and thus falsely assumes its a rt_sched_class task. Reported-Debuged-Tested-Acked-by:
Thomas Gleixner <tglx@linutronix.de> Signed-off-by:
-
Peter Zijlstra authored
commit 068c5cc5 upstream. By not notifying the controller of the on-exit move back to init_css_set, we fail to move the task out of the previous cgroup's cfs_rq. This leads to an opportunity for a cgroup-destroy to come in and free the cgroup (there are no active tasks left in it after all) to which the not-quite dead task is still enqueued. Reported-by:
Miklos Vajna <vmiklos@frugalware.org> Fixed-by:
Mike Galbraith <efault@gmx.de> Signed-off-by:
-
NeilBrown authored
commit 6bf41237 upstream. wait_for_completion_*_timeout() can return: 0: if the wait timed out -ve: if the wait was interrupted +ve: if the completion was completed. As they currently return an 'unsigned long', the last two cases are not easily distinguished which can easily result in buggy code, as is the case for the recently added wait_for_completion_interruptible_timeout() call in net/sunrpc/cache.c So change them both to return 'long'. As MAX_SCHEDULE_TIMEOUT is LONG_MAX, a large +ve return value should never overflow. Signed-off-by:
-
Eric Dumazet authored
commit 0781b909 upstream. commit 95aac7b1 ("epoll: make epoll_wait() use the hrtimer range feature") added a performance regression because it uses timespec_add_ns() with potential very large 'ns' values. [akpm@linux-foundation.org: s/epoll_set_mstimeout/ep_set_mstimeout/, per Davide] Reported-by:
Simon Kirby <sim@hostway.ca> Signed-off-by:
Davide Libenzi <davidel@xmailserver.org> Signed-off-by:
-
David Miller authored
commit 795abaf1 upstream. Commit c0e69a5b ("klist.c: bit 0 in pointer can't be used as flag") intended to make sure that all klist objects were at least pointer size aligned, but used the constant "4" which only works on 32-bit. Use "sizeof(void *)" which is correct in all cases. Signed-off-by:
David S. Miller <davem@davemloft.net> Acked-by:
Jesper Nilsson <jesper.nilsson@axis.com> Signed-off-by:
-
Mel Gorman authored
commit 88f5acf8 upstream. Commit aa454840 ("calculate a better estimate of NR_FREE_PAGES when memory is low") noted that watermarks were based on the vmstat NR_FREE_PAGES. To avoid synchronization overhead, these counters are maintained on a per-cpu basis and drained both periodically and when a threshold is above a threshold. On large CPU systems, the difference between the estimate and real value of NR_FREE_PAGES can be very high. The system can get into a case where pages are allocated far below the min watermark potentially causing livelock issues. The commit solved the problem by taking a better reading of NR_FREE_PAGES when memory was low. Unfortately, as reported by Shaohua Li this accurate reading can consume a large amount of CPU time on systems with many sockets due to cache line bouncing. This patch takes a different approach. For large machines where counter drift might be unsafe and while kswapd is awake, the per-cpu thresholds for the target pgdat are reduced to limit the level of drift to what should be a safe level. This incurs a performance penalty in heavy memory pressure by a factor that depends on the workload and the machine but the machine should function correctly without accidentally exhausting all memory on a node. There is an additional cost when kswapd wakes and sleeps but the event is not expected to be frequent - in Shaohua's test case, there was one recorded sleep and wake event at least. To ensure that kswapd wakes up, a safe version of zone_watermark_ok() is introduced that takes a more accurate reading of NR_FREE_PAGES when called from wakeup_kswapd, when deciding whether it is really safe to go back to sleep in sleeping_prematurely() and when deciding if a zone is really balanced or not in balance_pgdat(). We are still using an expensive function but limiting how often it is called. When the test case is reproduced, the time spent in the watermark functions is reduced. The following report is on the percentage of time spent cumulatively spent in the functions zone_nr_free_pages(), zone_watermark_ok(), __zone_watermark_ok(), zone_watermark_ok_safe(), zone_page_state_snapshot(), zone_page_state(). vanilla 11.6615% disable-threshold 0.2584% David said: : We had to pull aa454840 "mm: page allocator: calculate a better estimate : of NR_FREE_PAGES when memory is low and kswapd is awake" from 2.6.36 : internally because tests showed that it would cause the machine to stall : as the result of heavy kswapd activity. I merged it back with this fix as : it is pending in the -mm tree and it solves the issue we were seeing, so I : definitely think this should be pushed to -stable (and I would seriously : consider it for 2.6.37 inclusion even at this late date). Signed-off-by:
Mel Gorman <mel@csn.ul.ie> Reported-by:
Shaohua Li <shaohua.li@intel.com> Reviewed-by:
Nicolas Bareil <nico@chdir.org> Cc: David Rientjes <rientjes@google.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by:
-
Ian Campbell authored
commit 00f28e40 upstream. This is the correct interface to use and something has broken the use of the previous incorrect interface (which fails because the request conflicts with the resources assigned for the PCI device itself instead of nesting like the PCI interfaces do). Signed-off-by:
Ian Campbell <ian.campbell@citrix.com> Signed-off-by:
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by:
-
Kees Cook authored
commit 5b919f83 upstream. Commit fe10ae53 adds a memset() to clear the structure being sent back to userspace, but accidentally used the wrong size. Reported-by:
Brad Spengler <spender@grsecurity.net> Signed-off-by:
Kees Cook <kees.cook@canonical.com> Signed-off-by:
-
H. Peter Anvin authored
commit 76d1f7bf upstream. OLPC uses select for OLPC_OPENFIRMWARE, which means OLPC has to enforce the dependencies for OLPC_OPENFIRMWARE. Make sure it does so. Signed-off-by:
H. Peter Anvin <hpa@linux.intel.com> Cc: Daniel Drake <dsd@laptop.org> Cc: Andres Salomon <dilinger@queued.net> Cc: Grant Likely <grant.likely@secretlab.ca> LKML-Reference: <20100923162846.D8D409D401B@zog.reactivated.net> Signed-off-by:
-
Christoph Lameter authored
commit 04d94879 upstream. The purpose of the locking is to prevent removal and additions of nodes when statistics are gathered for a slab cache. So we need to avoid racing with memory hotplug functionality. It is enough to take the memory hotplug locks there instead of the slub_lock. online_pages() currently does not acquire the memory_hotplug lock. Another patch will be submitted by the memory hotplug authors to take the memory hotplug lock and describe the uses of the memory hotplug lock to protect against adding and removal of nodes from non hotplug data structures. Reported-and-tested-by:
Bart Van Assche <bvanassche@acm.org> Acked-by:
-
Boaz Harrosh authored
commit 0b0abeaf upstream. This reverts commit 115e19c5. Apparently setting inode->bdi to one's own sb->s_bdi stops VFS from sending *read-aheads*. This problem was bisected to this commit. A revert fixes it. I'll investigate farther why is this happening for the next Kernel, but for now a revert. I'm sending to stable@kernel.org as well, since it exists also in 2.6.37. 2.6.36 is good and does not have this patch. Signed-off-by:
Boaz Harrosh <bharrosh@panasas.com> Signed-off-by:
-
