search for: preemptibl

I recently sent off a fix for lazy vmalloc faults which can happen under = paravirt when lazy mode is enabled. Unfortunately, I jumped the gun a = bit on fixing this. I neglected to notice that since the new call to = flush the MMU update queue is called from the page fault handler, it can = be pre-empted. Both VMI and Xen use per-cpu variables to track lazy = mode state, as all previous

I recently sent off a fix for lazy vmalloc faults which can happen under = paravirt when lazy mode is enabled. Unfortunately, I jumped the gun a = bit on fixing this. I neglected to notice that since the new call to = flush the MMU update queue is called from the page fault handler, it can = be pre-empted. Both VMI and Xen use per-cpu variables to track lazy = mode state, as all previous

As a follow up to https://reviews.llvm.org/D20217 I would like to use lto/thinlto to refine when a symbol is marked as local/preemptable. I'm not very familiar with lto though so would appreciate some guidance about how best to go about this. Regards Sean Fertile

From: David Vrabel <david.vrabel@citrix.com> get_balloon_scratch_page() disables preemption so we cannot call alloc_page() in between get/put_balloon_scratch_page(). Shuffle bits around in decrease_reservation() to avoid this. Signed-off-by: David Vrabel <david.vrabel@citrix.com> --- drivers/xen/balloon.c | 23 +++++++++++------------ 1 files changed, 11 insertions(+), 12

...quence counts are "lock" constructs where you need to make sure that writers are serialized. In turn, this means that we mustn't run two try_fill_recv concurrently. Which of course we don't. We do run try_fill_recv sometimes from a softirq napi context, and sometimes from a fully preemptible context, but the later always runs with napi disabled. However, when it comes to the seqcount, lockdep is trying to enforce the rule that the same lock isn't accessed from preemptible and softirq context - it doesn't know about napi being enabled/disabled. This causes a false-positive war...

I know this isn''t a shorewall question, but I hope somebody might be able to point me the right direction. here''s the error: Apr 10 18:19:07 trinity kernel: BUG: using smp_processor_id() in preemptible [00000001] code: modprobe/11068 Apr 10 18:19:07 trinity kernel: caller is ip_conntrack_init+0x255/0x369 [ip_conntrack] Apr 10 18:19:07 trinity kernel: [<c02ec398>] smp_processor_id+0xa8/0xc0 Apr 10 18:19:07 trinity kernel: [<f0cdb275>] ip_conntrack_init+0x255/0x369 [ip_conntrack] Apr...

...iff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c index 8bff7e7..1b2b73f 100644 --- a/arch/x86/xen/multicalls.c +++ b/arch/x86/xen/multicalls.c @@ -189,10 +189,10 @@ struct multicall_space __xen_mc_entry(size_t args) unsigned argidx = roundup(b->argidx, sizeof(u64)); BUG_ON(preemptible()); - BUG_ON(b->argidx > MC_ARGS); + BUG_ON(b->argidx >= MC_ARGS); if (b->mcidx == MC_BATCH || - (argidx + args) > MC_ARGS) { + (argidx + args) >= MC_ARGS) { mc_stats_flush(b->mcidx == MC_BATCH ? FL_SLOTS : FL_ARGS); xen_mc_flush(); argidx = roundup(b-&...

...iff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c index 8bff7e7..1b2b73f 100644 --- a/arch/x86/xen/multicalls.c +++ b/arch/x86/xen/multicalls.c @@ -189,10 +189,10 @@ struct multicall_space __xen_mc_entry(size_t args) unsigned argidx = roundup(b->argidx, sizeof(u64)); BUG_ON(preemptible()); - BUG_ON(b->argidx > MC_ARGS); + BUG_ON(b->argidx >= MC_ARGS); if (b->mcidx == MC_BATCH || - (argidx + args) > MC_ARGS) { + (argidx + args) >= MC_ARGS) { mc_stats_flush(b->mcidx == MC_BATCH ? FL_SLOTS : FL_ARGS); xen_mc_flush(); argidx = roundup(b-&...

...iff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c index 8bff7e7..1b2b73f 100644 --- a/arch/x86/xen/multicalls.c +++ b/arch/x86/xen/multicalls.c @@ -189,10 +189,10 @@ struct multicall_space __xen_mc_entry(size_t args) unsigned argidx = roundup(b->argidx, sizeof(u64)); BUG_ON(preemptible()); - BUG_ON(b->argidx > MC_ARGS); + BUG_ON(b->argidx >= MC_ARGS); if (b->mcidx == MC_BATCH || - (argidx + args) > MC_ARGS) { + (argidx + args) >= MC_ARGS) { mc_stats_flush(b->mcidx == MC_BATCH ? FL_SLOTS : FL_ARGS); xen_mc_flush(); argidx = roundup(b-&...

...on a 32 bit kernel that uses a seqcount. sequence counts are "lock" constructs where you need to make sure that writers are serialized. In turn, this means that we mustn't run two try_fill_recv concurrently. Which of course we don't. We do run try_fill_recv sometimes from a fully preemptible context and sometimes from a softirq (napi) context. However, when it comes to the seqcount, lockdep is trying to enforce the rule that the same lock isn't accessed from preemptible and softirq context. This causes a false-positive warning: WARNING: inconsistent lock state ... inconsistent {...

Now that the kmap atomic index is stored in task struct provide a preemptible variant. On context switch the maps of an outgoing task are removed and the map of the incoming task are restored. That's obviously slow, but highmem is slow anyway. The kmap_local.*() functions can be invoked from both preemptible and atomic context. kmap local sections disable migration to...

On 6 March 2014 18:09, Mark Seaborn <mseaborn at chromium.org> wrote: > LowerAtomic "lowers atomic intrinsics to non-atomic form for use in a > known non-preemptible environment". LowerInvoke strips out exception > handling by converting invokes to calls, so that landingpads, resumes, etc. > become dead and can be removed by a later pass. > > (As an aside, LowerInvoke has an option for using SJLJ exception handling, > but that option appea...

..._disable_iospace(void) } return ret; +} + +static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LAZY_NONE; + +static void enter_lazy(enum paravirt_lazy_mode mode, struct pv_lazy_ops *ops) +{ + BUG_ON(x86_read_percpu(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE); + BUG_ON(preemptible()); + + x86_write_percpu(paravirt_lazy_mode, mode); + (*ops->enter)(); +} + +static void leave_lazy(enum paravirt_lazy_mode mode, struct pv_lazy_ops *ops) +{ + BUG_ON(x86_read_percpu(paravirt_lazy_mode) != mode); + BUG_ON(preemptible()); + + x86_write_percpu(paravirt_lazy_mode, PARAVIRT_LAZY_NO...

..._disable_iospace(void) } return ret; +} + +static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LAZY_NONE; + +static void enter_lazy(enum paravirt_lazy_mode mode, struct pv_lazy_ops *ops) +{ + BUG_ON(x86_read_percpu(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE); + BUG_ON(preemptible()); + + x86_write_percpu(paravirt_lazy_mode, mode); + (*ops->enter)(); +} + +static void leave_lazy(enum paravirt_lazy_mode mode, struct pv_lazy_ops *ops) +{ + BUG_ON(x86_read_percpu(paravirt_lazy_mode) != mode); + BUG_ON(preemptible()); + + x86_write_percpu(paravirt_lazy_mode, PARAVIRT_LAZY_NO...

Hi, when creating a bigger (> 50 GB) HVM guest with maxmem > memory we get softlockups from time to time. kernel: [ 802.084335] BUG: soft lockup - CPU#1 stuck for 22s! [xend:31351] I tracked this down to the call of xc_domain_set_pod_target() and further p2m_pod_set_mem_target(). Unfortunately I can this check only with xen-4.2.2 as I don''t have a machine with enough memory for

...I'm going to continue to experiment given this information. Thanks, Justin > On Nov 4, 2020, at 2:35 PM, Fangrui Song <maskray at google.com> wrote: > > On 2020-11-04, Justin Cady wrote: >> Thank you both for your replies, the links to the source, and the details about preemptible symbols. >> >>> If you are using an older linker (either GNU ld or LLD), it may not have such a diagnostic. >> >> Thank you for this concise example. The linker does in fact have this diagnostic, but it is being ignored. >> >> So, for: >> >> ....

Jeremy Fitzhardinge wrote: > Andrew Morton wrote: > > On Thu, 15 Feb 2007 22:14:45 -0800 Dan Hecht > <dhecht@vmware.com> wrote: > > > > > >>> config PREEMPT > >>> bool "Preemptible Kernel (Low-Latency Desktop)" > >>> + depends on !XEN > >>> help > >>> This option reduces the latency of the kernel by making > >>> all kernel code (that is not executing in a critical section) > >>> > >>>...

Jeremy Fitzhardinge wrote: > Andrew Morton wrote: > > On Thu, 15 Feb 2007 22:14:45 -0800 Dan Hecht > <dhecht@vmware.com> wrote: > > > > > >>> config PREEMPT > >>> bool "Preemptible Kernel (Low-Latency Desktop)" > >>> + depends on !XEN > >>> help > >>> This option reduces the latency of the kernel by making > >>> all kernel code (that is not executing in a critical section) > >>> > >>>...

Jeremy Fitzhardinge wrote: > Andrew Morton wrote: > > On Thu, 15 Feb 2007 22:14:45 -0800 Dan Hecht > <dhecht@vmware.com> wrote: > > > > > >>> config PREEMPT > >>> bool "Preemptible Kernel (Low-Latency Desktop)" > >>> + depends on !XEN > >>> help > >>> This option reduces the latency of the kernel by making > >>> all kernel code (that is not executing in a critical section) > >>> > >>>...

...wall installed). Any ideas? Which kernel options are required for Asterisk to function properly. Any recommendations on that? Several options do come to mind like, also to prevent timing problems like: - HPET Timer Support (CONFIG_HPET_TIMER) - Provide RTC interrupt (CONFIG_HPET_EMULATE_RTC) - Preemptible Kernel (CONFIG_PREEMPT) (even though the info in kernel describes this for desktop) - Message Signaled Interrupts (MSI and MSI-X) (CONFIG_PCI_MSI) - Enhanced Real Time Clock Support (CONFIG_RTC) - HPET - High Precision Event Timer (CONFIG_HPET) For general Astrisk with ISDN operation: Is telep...