Found 75 matching messages (0.064 seconds). Page 1 of 4.
# HG changeset patch
# User Andrea Arcangeli
linux-kernel - Andrea Arcangeli - May 2 2008 - 11:05
# HG changeset patch
# User Andrea Arcangeli
linux-kernel - Andrea Arcangeli - May 7 2008 - 10:35
On Wed, May 07, 2008 at 08:10:33PM -0700, Christoph Lameter wrote: ... we can live with the 512 vmas cap that guarantees sort won't ... is the only thing that the anon vma bitflag can achieve and it ... linux-kernel" in the body of a message to majordomo@vger.kernel ...
linux-kernel - Andrea Arcangeli - May 7 2008 - 23:41
... ->vm_file->f_mapping->i_mmap_lock); > } > spin_unlock(&global_lock); Multiple vmas may share the same mapping or refer to the same anonymous vma. The above code will deadlock since ... linux-kernel" in the body of a message to majordomo@vger.kernel ...
linux-kernel - Christoph Lameter - May 7 2008 - 19:39
... > way that I have seen of temporarily holding off reclaim from an ... vmas so the ram wasted on anon-vmas wouldn't save more than ... After that we remove the 512 vma cap and mm_lock is free to ... unsubscribe linux-kernel" in the body of a message to majordomo@vger. ...
linux-kernel - Andrea Arcangeli - May 7 2008 - 22:56
... ordering for that case: one type of lock goes before the other kind. ... vma->vm_file->f_mapping) spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); } spin_unlock(&global_lock); and now ... linux-kernel" in the body of a message to majordomo@vger. ...
linux-kernel - Linus Torvalds - May 7 2008 - 19:19
... have mmap_sem held. I think for anon > > pages it is always called with ... zap_page_range calls unmap_vmas which walks to vma->next. Are you saying > that can ... holding mmap_sem. > I feel my understanding of list management and locking completely > ...
linux-kernel - Nick Piggin - May 15 2008 - 03:57
On Thu, May 08, 2008 at 08:30:20AM +0300, Pekka Enberg wrote: > On Thu, ... on the list */ + struct rw_semaphore sem;/* Serialize access to vma list */ struct list_head head; /* List of private "related" vmas */ }; not sure if it'll grow in size ...
linux-kernel - Andrea Arcangeli - May 8 2008 - 01:49
... May 14, 2008 at 06:11:22AM +0200, Nick Piggin wrote: ... mmap_sem held. I think for anon > pages it is always called ... calls unmap_vmas which walks to vma->next. Are you saying that ... be reworked into other types of locks. Thanks, Robin -- To unsubscribe ...
linux-kernel - Robin Holt - May 14 2008 - 07:26
... > later it would become a rwsem when XPMEM is selected making the ... before taking *two or more* of the per-vma locks. I really wish I'd thought of that. -- To unsubscribe from this list ... linux-kernel" in the body of a message to majordomo@vger.kernel ...
linux-kernel - Andrew Morton - May 7 2008 - 18:31
... wrote: > > On Thu, 2008-05-08 at 00:44 +0200, Andrea ... to be in the middle of > > zap_page_range while mmu_notifier_register runs. > > You ... time + a cap of vmas. It's not important if it ... allocations needed anyway, any one of them can fail, so this ...
linux-kernel - Andrea Arcangeli - May 7 2008 - 19:45
... 2008, Christoph Lameter wrote: > > > > Multiple vmas may share the same mapping ... refer to the same anonymous > > vma. The above code will deadlock ... rare, maybe Ben's > suggestion of just using stop-machine is ... we're not running out of vm flags yet, and if ...
linux-kernel - Christoph Lameter - May 7 2008 - 20:56
... struct address_space), not in the > vma itself. My bad. So the ... related to that brain-fart of mine, that obviously also means ... a cap on the number of vmas to min(1024,max_map_count) ... time. kvm runs with 127 vmas allocated... -- To unsubscribe from this ...
linux-kernel - Andrea Arcangeli - May 7 2008 - 21:52
... ^^^ 2.6.26-rc1 + below patch diff --git a/include/linux/rmap. ... { spinlock_t lock; /* Serialize access to vma list */ struct list_head head; /* List of private "related" vmas */ + int flag:1; ... sort and run O(N) instead of current O(N*log(N)) ...
linux-kernel - Andrea Arcangeli - May 8 2008 - 01:20
... looks bad, in fact. Lack of authorship, bad single-line Glad ... complained myself to various of those patches and I'll take ... making the conversion from spinlock->rwsem only if CONFIG_XPMEM=y as ... but ia64. Please ignore all patches but mmu-notifier-core. I ...
linux-kernel - Andrea Arcangeli - May 7 2008 - 17:26
... mm_lock() is an unbelievable piece of utter and > horrible CRAP. > > There ... later it would become a rwsem when XPMEM is selected making ... have been > in a separate patch. I'll happily apply that ... you say, it's order of magnitude safer even if entirely ...
linux-kernel - Andrea Arcangeli - May 7 2008 - 18:22
... 2008, Christoph Lameter wrote: > > Multiple vmas may share the same mapping ... refer to the same anonymous > vma. The above code will deadlock ... rare, maybe Ben's suggestion of just using stop-machine is ... we're not running out of vm flags yet, and if ...
linux-kernel - Linus Torvalds - May 7 2008 - 20:03
... 7 May 2008, Christoph Lameter wrote: > > > > Multiple vmas may share the same mapping or refer to the same anonymous > > vma. The above code will deadlock since ... really rare, maybe Ben's > suggestion of just using stop-machine is actually ...
linux-kernel - Robin Holt - May 7 2008 - 20:52
... I don't see a problem in making the conversion from > spinlock->rwsem only if CONFIG_XPMEM=y as I doubt XPMEM works on > ... this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at ...
linux-kernel - Jack Steiner - May 7 2008 - 18:42
... looks like a simple bit-per-vma. > > Andrea's mm_lock could have ... > way that I have seen of temporarily holding off reclaim from ... easily generate thousands and thousands of vma's in a process. ... linux-kernel" in the body of a message to majordomo@vger. ...
linux-kernel - Linus Torvalds - May 7 2008 - 21:32
| jmerkey | [ANNOUNCE] Merkey's Kernel Debugger |
| Bart Van Assche | Integration of SCST in the mainstream Linux kernel |
| Linus Torvalds | Linux 2.6.27-rc8 |
| Harald Dunkel | 2.6.25.3: su gets stuck for root |
git: | |
| Peter Stahlir | Git as a filesystem |
| Linus Torvalds | Help with a tcl/tk gui thing.. |
| Jon Smirl | ! [rejected] master -> master (non-fast forward) |
| Wink Saville | Resolving conflicts |
| Kevin Neff | Patching a SSH 'Weakness' |
| Mayuresh Kathe | Re: What is our ultimate goal?? |
| Doug Fordham | Re: Real men don't attack straw men |
| GVG GVG | ssh_exchange_identification: Connection closed by remote host |
| David Miller | [GIT]: Networking |
| Jarek Poplawski | [PATCH] pkt_sched: Destroy gen estimators under rtnl_lock(). |
| Eric Dumazet | Re: [PATCH] net: implement emergency route cache rebulds when gc_elasticity is exc... |
| Arnaldo Carvalho de Melo | Re: [PATCH 2/6] Phonet: connected sockets glue |
