Re: [GIT PULL REQUEST] watchdog - v4.16 merge window
Linus Torvalds writes: (Summary) On Mon, Feb 5, 2018 at 2:20 AM, Wim Van Sebroeck <wim@iguana.be> wrote: [...] git://www.linux-watchdog.org/linux-watchdog.git Hmm. I really want to know why I...
View ArticleRe: [RFC][PATCH] : fix end_name_hash() for 64b ...
Linus Torvalds writes: (Summary) And that takes the _high_ bits of the hash, so unlike a lot of other hash functions, the name hashing doesn't need to try to spread the bits down to the low bits. The...
View ArticleRe: [RFC][PATCH] : fix end_name_hash() for 64b ...
Linus Torvalds writes: (Summary) On Mon, Feb 5, 2018 at 10:35 AM, Amir Goldstein <amir73il@gmail.com> wrote: [...] But my patch doesn't add any __hash_32() call. My bad. It was indeed there...
View ArticleRe: [PATCH for 4.16 00/11] membarrier updates for 4.16
Linus Torvalds writes: (Summary) On Mon, Feb 5, 2018 at 10:53 AM, Mathieu Desnoyers<mathieu.desnoyers@efficios.com> wrote:[...] morning. Yeah, too much email, so I hadn't gotten to that yet......
View ArticleRe: [PATCH v2 1/3] x86/entry: Clear extra registers beyond syscall ...
Linus Torvalds writes: (Summary) wrote: [...] per cycle: Ugh. Ugh. A "xor %reg/reg" is two bytes (three for the high regs due to REX prefix). I suspect that a bigger win would be if you try to...
View ArticleRe: [PATCH v2 1/3] x86/entry: Clear extra registers beyond syscall ...
Linus Torvalds writes: (Summary) On Mon, Feb 5, 2018 at 2:10 PM, Andy Lutomirski <luto@kernel.org> wrote: [...] surprised if the CPU can't hide that. Ugh. xor really is nice because it breaks all...
View ArticleRe: [PATCH v2 1/3] x86/entry: Clear extra registers beyond syscall ...
Linus Torvalds writes: (Summary) i++) asm(".rept 16384\n" "subq $128,%rsp\n\t" "pushq %rbx\n\t" "pushq %r10\n\t" "pushq %r11\n\t" "pushq %r12\n\t" "pushq %r13\n\t" "pushq %r14\n\t" "pushq %r15\n\t"...
View ArticleRe: [PATCH v4 07/10] x86: narrow out of bounds syscalls to sys_rea ...
Linus Torvalds writes: (Summary) That said, looking at 2fbd7af5af86, I do note that the code generation is horribly stupid. is horribly stupid. It's due to two different issues: It's due to two...
View ArticleRe: [PATCH v4 07/10] x86: narrow out of bounds syscalls to sys_rea ...
Linus Torvalds writes: (Summary) On Tue, Feb 6, 2018 at 12:37 PM, Dan Williams <dan.j.williams@intel.com> wrote: [...] That might be a way to improve the assembly. Sadly, that is *very* easy to...
View ArticleRe: [PATCH v4 07/10] x86: narrow out of bounds syscalls to sys_rea ...
Linus Torvalds writes: On Tue, Feb 6, 2018 at 12:42 PM, Linus Torvalds<torvalds@linux-foundation.org> wrote:[...] Sadly, that is *very* easy to miscompile. Side note: don't read email, go watch...
View ArticleRe: [PATCH v4 07/10] x86: narrow out of bounds syscalls to sys_rea ...
Linus Torvalds writes: (Summary) On Tue, Feb 6, 2018 at 12:49 PM, Andy Lutomirski <luto@kernel.org> Although I'd actually suggest just using an "asm goto" if we really want to optimize this. Give...
View ArticleRe: [GIT PULL for v4.16-rc1] media updates
Linus Torvalds writes: On Tue, Feb 6, 2018 at 2:16 PM, Stephen Rothwell <sfr@canb.auug.org.au> wrote: [...] Looks like you missed this when doing the merge :-( Gaah. I noticed the actual...
View ArticleRe: [PATCH tip-pti 2/2] x86/entry: interleave XOR register clearin ...
Linus Torvalds writes: (Summary) wrote:[...] clearing. Side note: I would _really_ like to see Side note: I would _really_ like to see (a) SAVE_{C,EXTRA}_REGS go away entirely, to be replaced by just...
View ArticleRe: [PATCH tip-pti 2/2] x86/entry: interleave XOR register clearin ...
Linus Torvalds writes: (Summary) [...] not very optimized. Actually, only the argument reloading _really_ annoys me in do_syscall(). And I do think we should be able to fix that fairly easily by moving...
View ArticleRe: [PATCH tip-pti 2/2] x86/entry: interleave XOR register clearin ...
Linus Torvalds writes: (Summary) I realize that nobody is supposed to care about performance for KASAN, but still... performance for KASAN, but still... So one of the issues with do_syscall() is simply...
View ArticleRe: [PATCH 6/6] s390: introduce execute-trampolines for branches
Linus Torvalds writes: (Summary) We now have about a million of these crazy things, where we have config options that simply depend on which compiler we have, and we have no sane way to show them at...
View ArticleRe: [linus:master] BUILD REGRESSION a2e5790d841658485d642196dbb092 ...
Linus Torvalds writes: (Summary) But I guess they can be interpreted as modrm bytes, and somebody started doing that. somebody started doing that. That said, intel only _documents_ UD2 (0f 0b). That...
View ArticleRe: [linus:master] BUILD REGRESSION a2e5790d841658485d642196dbb092 ...
Linus Torvalds writes: (Summary) wrote: [...] Section A.2.5, Table A-1, says: Ahh, I had an older version. Ahh, I had an older version. Looking at the latest one I can find (325462-065US), it does...
View ArticleRe: [linus:master] BUILD REGRESSION a2e5790d841658485d642196dbb092 ...
Linus Torvalds writes: (Summary) Both UD0 and UD1 are documented to have modrm in the latest Intel SDM I can find (Order number 325462-065US, December 2017): I can find (Order number 325462-065US,...
View ArticleRe: [linus:master] BUILD REGRESSION a2e5790d841658485d642196dbb092 ...
Linus Torvalds writes: (Summary) It might still be a page-crossing instruction, but we won't take a page fault in kernel space (due to it being at the end of some text sectoin or whatever that changes...
View Article