search for: clac

Hello, I installed NUT on raspberry pi as a NUT-Server. It works fine so far with a Cyberpower OR600ELCDRM1U (used driver: usbhid-ups). The Pi recognizes power loss and shuts down itself and the ups as it should. Problem: The UPS comes up immediately after shutting down. This is a big issue because there is no power, the server (NUT-Slave) begins powering up and the battery will drain

Hi, thanks for your reply. >> The Unit is new, the battery drains because it went down to about 15 >> percent before NUT shuts it down. >> >> Yes, I can here a "clac". The problem is not the shutdown procedure, >> it works quite good. After the Unit reaches 20 percent the NUT-Server >> on the pi shuts down the system and the ups is turned off as well. The >> problem is, it starts up immediately even though the unit is still on >&gt...

...through kernel virtual >> address instead of copy_user() friends since they had too much >> overheads like checks, spec barriers or even hardware feature >> toggling. > Will review, thanks! > One questions that comes to mind is whether it's all about bypassing > stac/clac. Could you please include a performance comparison with > nosmap? > On machine without SMAP (Sandy Bridge): Before: 4.8Mpps After: 5.2Mpps On machine with SMAP (Broadwell): Before: 5.0Mpps After: 6.1Mpps No smap: 7.5Mpps Thanks

...through kernel virtual >> address instead of copy_user() friends since they had too much >> overheads like checks, spec barriers or even hardware feature >> toggling. > Will review, thanks! > One questions that comes to mind is whether it's all about bypassing > stac/clac. Could you please include a performance comparison with > nosmap? > On machine without SMAP (Sandy Bridge): Before: 4.8Mpps After: 5.2Mpps On machine with SMAP (Broadwell): Before: 5.0Mpps After: 6.1Mpps No smap: 7.5Mpps Thanks

...instead of copy_user() friends since they had too much >>>> overheads like checks, spec barriers or even hardware feature >>>> toggling. >>> Will review, thanks! >>> One questions that comes to mind is whether it's all about bypassing >>> stac/clac. Could you please include a performance comparison with >>> nosmap? >>> >> On machine without SMAP (Sandy Bridge): >> >> Before: 4.8Mpps >> >> After: 5.2Mpps > OK so would you say it's really unsafe versus safe accesses? > Or would you say...

...instead of copy_user() friends since they had too much >>>> overheads like checks, spec barriers or even hardware feature >>>> toggling. >>> Will review, thanks! >>> One questions that comes to mind is whether it's all about bypassing >>> stac/clac. Could you please include a performance comparison with >>> nosmap? >>> >> On machine without SMAP (Sandy Bridge): >> >> Before: 4.8Mpps >> >> After: 5.2Mpps > OK so would you say it's really unsafe versus safe accesses? > Or would you say...

On Sat, 26 Oct 2019, EP wrote: > The Unit is new, the battery drains because it went down to about 15 percent > before NUT shuts it down. > > Yes, I can here a "clac". The problem is not the shutdown procedure, it works > quite good. After the Unit reaches 20 percent the NUT-Server on the pi shuts > down the system and the ups is turned off as well. The problem is, it starts > up immediately even though the unit is still on battery. That means...

This appears to be the case in the recent messages in Debian bug #660425 [0] (thread starts at [1] and continues at [2]). SMAP uses EFLAGS.AC in kernel mode to indicate whether accesses to usermode pages should fault or not, which gets confused because under 64-bit Xen kernel == ring3. The obvious fix would be to clear SMAP from the cpuid features (probably in kernel as well as hypervosr) but

On Fri, Nov 02, 2018 at 11:46:36AM +0000, Mark Rutland wrote: > On Thu, Nov 01, 2018 at 04:06:19PM -0700, Linus Torvalds wrote: > > On Thu, Nov 1, 2018 at 4:00 PM Kees Cook <keescook at chromium.org> wrote: > > > > > > + memset(&rsp, 0, sizeof(rsp)); > > > + rsp.response = VIRTIO_SCSI_S_FUNCTION_REJECTED; > > > + resp =

On Fri, Nov 02, 2018 at 11:46:36AM +0000, Mark Rutland wrote: > On Thu, Nov 01, 2018 at 04:06:19PM -0700, Linus Torvalds wrote: > > On Thu, Nov 1, 2018 at 4:00 PM Kees Cook <keescook at chromium.org> wrote: > > > > > > + memset(&rsp, 0, sizeof(rsp)); > > > + rsp.response = VIRTIO_SCSI_S_FUNCTION_REJECTED; > > > + resp =

...BC","ROracle","rsprng","RWinEdt","taskPR") #rejected because I subjectively think we don't need them failPackages2 <- c("aaMI","AlgDesign","bim","caMassClass","CGIwithR","CDNmoney","clac","clim.pact","compositions","cyclones","hapassoc","haplo.score","haplo.stats","hapsim","httpRequest", "labdsv","kza","LMGene","Malmig","magic","negenes",&...

...ots of bugs because code bitrots. And no, the access_ok() checks aren't expensive, not even in a loop. They *used* to be somewhat expensive compared to the access, but that simply isn't true any more. The real expense in copy_to_user and friends are in the user access bit setting (STAC and CLAC on x86), which easily an order of magnitude more expensive than access_ok(). So just get rid of the double-underscore version. It's basically always a mis-optimization due to entirely historical reasons. I can pretty much guarantee that it's not visible in profiles. Linu...

...access virtqueue metadata through kernel virtual > address instead of copy_user() friends since they had too much > overheads like checks, spec barriers or even hardware feature > toggling. Will review, thanks! One questions that comes to mind is whether it's all about bypassing stac/clac. Could you please include a performance comparison with nosmap? > > Test shows about 24% improvement on TX PPS. It should benefit other > cases as well. > > Changes from V2: > - fix buggy range overlapping check > - tear down MMU notifier during vhost ioctl to make sure inva...

...> address instead of copy_user() friends since they had too much > > > overheads like checks, spec barriers or even hardware feature > > > toggling. > > Will review, thanks! > > One questions that comes to mind is whether it's all about bypassing > > stac/clac. Could you please include a performance comparison with > > nosmap? > > > > On machine without SMAP (Sandy Bridge): > > Before: 4.8Mpps > > After: 5.2Mpps OK so would you say it's really unsafe versus safe accesses? Or would you say it's just a better wri...

...they had too much > > > > > overheads like checks, spec barriers or even hardware feature > > > > > toggling. > > > > Will review, thanks! > > > > One questions that comes to mind is whether it's all about bypassing > > > > stac/clac. Could you please include a performance comparison with > > > > nosmap? > > > > > > > On machine without SMAP (Sandy Bridge): > > > > > > Before: 4.8Mpps > > > > > > After: 5.2Mpps > > OK so would you say it's really...

...; Signed-off-by: Jason Wang <jasowang at redhat.com> >> I don't hve a problem with this patch but do you have >> any idea how come removing what's supposed to be >> an optimization speeds things up? > With SMAP, the 2x vhost_put_user() will also mean an extra STAC/CLAC pair, > which is probably slower than the overhead of CALL+RET to whatever flavor > of copy_user_generic() gets used. CALL+RET is really the only overhead > since all variants of copy_user_generic() unroll accesses smaller than > 64 bytes, e.g. on a 64-bit system, __copy_to_user() will...

...to/from_user. > And no, the access_ok() checks aren't expensive, not even in a loop. > They *used* to be somewhat expensive compared to the access, but that > simply isn't true any more. The real expense in copy_to_user and > friends are in the user access bit setting (STAC and CLAC on x86), > which easily an order of magnitude more expensive than access_ok(). > > So just get rid of the double-underscore version. It's basically > always a mis-optimization due to entirely historical reasons. I can > pretty much guarantee that it's not visible in profiles...

...to/from_user. > And no, the access_ok() checks aren't expensive, not even in a loop. > They *used* to be somewhat expensive compared to the access, but that > simply isn't true any more. The real expense in copy_to_user and > friends are in the user access bit setting (STAC and CLAC on x86), > which easily an order of magnitude more expensive than access_ok(). > > So just get rid of the double-underscore version. It's basically > always a mis-optimization due to entirely historical reasons. I can > pretty much guarantee that it's not visible in profiles...

...t Cyclomatic Complexity 1 include/linux/slab.h:kmalloc_type Cyclomatic Complexity 28 include/linux/slab.h:kmalloc_index Cyclomatic Complexity 67 include/linux/slab.h:kmalloc_large Cyclomatic Complexity 4 include/linux/slab.h:kmalloc Cyclomatic Complexity 1 arch/x86/include/asm/smap.h:clac Cyclomatic Complexity 1 arch/x86/include/asm/smap.h:stac Cyclomatic Complexity 1 arch/x86/include/asm/uaccess.h:set_fs Cyclomatic Complexity 1 arch/x86/include/asm/uaccess_32.h:raw_copy_to_user Cyclomatic Complexity 5 arch/x86/include/asm/uaccess_32.h:raw_copy_from_user Cyclomatic Co...

...t;,"caMassClass","car","cat","caTools","catspec","cba","cclust","CDNmoney","cfa","CGIwithR","changeLOS","chplot","chron","CircStats","circular","clac","class","classInt","classPP","clim.pact","climatol","clines","clue","cluster","clusterRepro","clustvarsel","cmprsk","cobs","CoCo","CoCoCg","CoCoCore...