Re: [RFC PATCH 0/4] softirq: Per vector threading v3
Linus Torvalds writes: (Summary) workqueues seem to use cond_resched_rcu_qs(), which does a cond_resched() (and a RCU quiescent note). cond_resched() (and a RCU quiescent note). But I wonder if the...
View ArticleRe: [PATCH v2 5/5] x86/pti: Do not enable PTI on fixed Intel proce ...
Linus Torvalds writes: (Summary) Whether it gets to a cache replacement or not is unclear. a cache replacement or not is unclear. So that naming is very misleading. So that naming is very misleading....
View ArticleRe: [GIT PULL] PCI fixes for v4.15
Linus Torvalds writes: (Summary) On Tue, Jan 23, 2018 at 11:56 AM, Bjorn Helgaas <helgaas@kernel.org> wrote: [...] (Christian K=C3=B6nig) Bjorn, I think you need to look at your email habits. I...
View ArticleRe: [GIT PULL] PCI fixes for v4.15
Linus Torvalds writes: (Summary) It happened before too, so there's three of them: git log --author=ckoenig.leichtzumerken@gmail.com git log --author=ckoenig.leichtzumerken@gmail.com it's also possible...
View ArticleRe: [GIT PULL] PCI fixes for v4.15
Linus Torvalds writes: (Summary) charset=3Dutf-8 only applies to the *body* of the email. only applies to the *body* of the email. So then the email handling tools have to handle that correctly, and as...
View ArticleRe: [GIT PULL] PCI fixes for v4.15
Linus Torvalds writes: (Summary) Git will auto-convert invalid utf-8 by assuming it is latin1, so it all ends up working, but Christian did something wrong in his mailer too. too. I suspect that the...
View ArticleRe: [tip:perf/urgent] perf/core: Fix lock inversion between perf,t ...
Linus Torvalds writes: (Summary) That's a subtle gotcha when you cut-and-paste things into the editor when editing a commit message (including the "git rebase -i" or "git commit --amend" kind of...
View ArticleRe: [PATCH] Revert "module: Add retpoline tag to VERMAGIC"
Linus Torvalds writes: On Wed, Jan 24, 2018 at 6:28 AM, Greg Kroah-Hartman <gregkh@linuxfoundation.org> wrote:[...] tree now so this doesn't get into 4.15? Applied. Applied. Linus Linus Linus
View ArticleRe: [PATCH] lib/strscpy: remove word-at-a-time optimization.
Linus Torvalds writes: (Summary) A big part of this all is branch mispredicts, you shouldn't just hand it the pattern on a plate. just hand it the pattern on a plate. Anyway, the reason I really...
View ArticleRe: [PATCH v6 3/4] vfs: Add timestamp_truncate() api
Linus Torvalds writes: (Summary) wrote: [...] greater than or equal to 1000 million. The thing is, we shouldn't check the standards, we should check what we actually _do_. we actually _do_. And what we...
View ArticleRe: [GIT PULL] PCI fixes for v4.15
Linus Torvalds writes: (Summary) And it lacks a number of the (admittedly rarer) European accented characters anyway. European accented characters anyway. So git basically first does a conversion...
View ArticleRe: [PATCH] lib/strscpy: remove word-at-a-time optimization.
Linus Torvalds writes: (Summary) */ ssize_t strscpy(char *dest, const char *src, size_t count) { - const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; -#ifdef...
View ArticleRe: [PATCH] x86/retpoline/entry: Disable the entire SYSCALL64 fast ...
Linus Torvalds writes: (Summary) - */ - cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) - jne 1f - - /* - * Called from fast path -- disable IRQs again, pop return address - * and jump to slow...
View ArticleRe: [PATCH] x86/retpoline/entry: Disable the entire SYSCALL64 fast ...
Linus Torvalds writes: (Summary) Together with just the extra level of 'call/ret' and the stack setup, I'm guessing we're talking maybe 20 cycles or so. cycles or so. So there's the extra register...
View ArticleRe: [PATCH] x86/retpoline/entry: Disable the entire SYSCALL64 fast ...
Linus Torvalds writes: (Summary) What _does_ show up a bit is this in prepare_exit_to_usermode(): What _does_ show up a bit is this in prepare_exit_to_usermode(): #ifdef CONFIG_COMPAT /* * Compat...
View ArticleRe: [PATCH] x86/retpoline/entry: Disable the entire SYSCALL64 fast ...
Linus Torvalds writes: (Summary) wrote: [...] Or I can grab it and send it to -tip. I'm not going to apply it for 4.15, I just wanted to see how it looked, and do some minimal profiling. looked, and do...
View ArticleRe: [PATCH] x86/retpoline/entry: Disable the entire SYSCALL64 fast ...
Linus Torvalds writes: (Summary) On Thu, Jan 25, 2018 at 1:08 PM, Andy Lutomirski <luto@kernel.org> wrote: [...] it, but it'll be kind of complicated. Ahh, I'd forgotten about that (and obviously...
View ArticleRe: [PATCH] x86/retpoline/entry: Disable the entire SYSCALL64 fast ...
Linus Torvalds writes: (Summary) On Thu, Jan 25, 2018 at 1:39 PM, Dan Williams <dan.j.williams@intel.com> You can just clear all of them. Sure, then do_syscall_64() will reload the six first...
View ArticleRe: [RFC 09/10] x86/enter: Create macros to restrict/unrestrict In ...
Linus Torvalds writes: (Summary) On Fri, Jan 26, 2018 at 1:11 AM, David Woodhouse <dwmw2@infradead.org> wrote: [...] stuffing for SMEP? Absolutely. SMEP helps make people a lot less worried about...
View ArticleRe: [PATCH] x86/retpoline/entry: Disable the entire SYSCALL64 fast ...
Linus Torvalds writes: (Summary) The ptreg version should be done the same way: don't make 'sys_xyz()' take a struct ptregs, instead make those SYSCALL_DEFINE*() macros create a _new_ function called...
View Article