Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1602792
| From | "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH 7/7] x86/mm: Switch to generic get_user_page_fast() implementation |
| Date | 2017-03-16 20:20 +0100 |
| Message-ID | <tlJ6h-2QJ-17@gated-at.bofh.it> (permalink) |
| References | <tlFvH-gv-3@gated-at.bofh.it> <tlFvJ-gv-59@gated-at.bofh.it> <tlHnQ-1ze-7@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
On Thu, Mar 16, 2017 at 06:20:46PM +0100, Peter Zijlstra wrote: > On Thu, Mar 16, 2017 at 06:26:55PM +0300, Kirill A. Shutemov wrote: > > +config HAVE_GENERIC_RCU_GUP > > + def_bool y > > + > > Nothing immediately jumped out to me; except that this option might be > misnamed. > > AFAICT that code does not in fact rely on HAVE_RCU_TABLE_FREE; it will > happily work with the (x86) broadcast IPI invalidate model, as you show > here. > > Architectures that do not do that obviously need HAVE_RCU_TABLE_FREE, > but that is not the point I feel. > > Also, this code hard relies on IRQ-disable delaying grace periods, which > is mostly true I think, but has always been something Paul didn't really > want to commit too firmly to. That is quite true! The only case where IRQ-disable is guaranteed to delay grace periods is when you are using RCU-sched, in other words synchronize_sched() and call_rcu_sched(). And even then, the CPU cannot be in the idle loop, cannot be offline, and cannot be a nohz_full CPU on its way to/from userspace execution. Thanx, Paul
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH 0/7] Switch x86 to generic get_user_pages_fast() implementation "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2017-03-16 16:30 +0100
[PATCH 3/7] mm/gup: Move page table entry dereference into helper "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2017-03-16 16:30 +0100
[tip:x86/mm] mm/gup: Move page table entry dereference into helper function "tip-bot for Kirill A. Shutemov" <tipbot@zytor.com> - 2017-03-18 11:00 +0100
[PATCH 4/7] mm/gup: Make pages referenced during generic get_user_pages_fast() "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2017-03-16 16:30 +0100
[tip:x86/mm] mm/gup: Mark all pages PageReferenced in generic get_user_pages_fast() "tip-bot for Kirill A. Shutemov" <tipbot@zytor.com> - 2017-03-18 11:00 +0100
[PATCH 7/7] x86/mm: Switch to generic get_user_page_fast() implementation "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2017-03-16 16:30 +0100
Re: [PATCH 7/7] x86/mm: Switch to generic get_user_page_fast() implementation Peter Zijlstra <peterz@infradead.org> - 2017-03-16 18:30 +0100
Re: [PATCH 7/7] x86/mm: Switch to generic get_user_page_fast() implementation "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-03-16 20:20 +0100
[PATCHv2 7/7] x86/mm: Switch to generic get_user_page_fast() implementation "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2017-03-16 22:40 +0100
Re: [PATCHv2 7/7] x86/mm: Switch to generic get_user_page_fast() implementation "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2017-03-17 18:40 +0100
[tip:x86/mm] x86/mm/gup: Switch GUP to the generic get_user_page_fast() implementation "tip-bot for Kirill A. Shutemov" <tipbot@zytor.com> - 2017-03-18 12:50 +0100
[PATCH 1/7] mm: Drop arch_pte_access_permitted() mmu hook "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2017-03-16 16:40 +0100
[tip:x86/mm] mm/gup: Drop the arch_pte_access_permitted() MMU callback "tip-bot for Kirill A. Shutemov" <tipbot@zytor.com> - 2017-03-18 11:00 +0100
Re: [PATCH 0/7] Switch x86 to generic get_user_pages_fast() implementation Linus Torvalds <torvalds@linux-foundation.org> - 2017-03-16 19:10 +0100
Re: [PATCH 0/7] Switch x86 to generic get_user_pages_fast() implementation Ingo Molnar <mingo@kernel.org> - 2017-03-17 09:40 +0100
csiph-web