- 09 Oct, 2012 40 commits
-
-
Sebastian Ott authored
Make sure that exported headers are save to be included by userspace exploiting /dev/chsc. Reported-by:
Michael Holzheu <holzheu@linux.vnet.ibm.com> Signed-off-by:
Sebastian Ott <sebott@linux.vnet.ibm.com> Signed-off-by:
Martin Schwidefsky <schwidefsky@de.ibm.com>
-
Heiko Carstens authored
Let the kernel text section always begin at 1MB. This allows to always have a large frame in the identity mapping of the kernel image for beginning of the text section, if the machine has EDAT1 support. Moving the beginning from 64K to 1MB doesn't cost any memory, since we make the memory between 64K and 1MB available for the page allocator. Signed-off-by:
Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by:
-
Heiko Carstens authored
Within the identity mapping the kernel text section is mapped read-only. However when mapping the first and last page of the text section we must round upwards and downwards respectively, if only parts of a page belong to the section. Otherwise potential rw data can be mapped read-only. So the rounding must be done just the other way we have it right now. Signed-off-by:
-
Heiko Carstens authored
This is more or less the same as the x86 page table dumper which was merged four years ago: 926e5392 "x86: add code to dump the (kernel) page tables for visual inspection by kernel developers". We add a file at /sys/kernel/debug/kernel_page_tables for debugging purposes so it's quite easy to see the kernel page table layout and possible odd mappings: ---[ Identity Mapping ]--- 0x0000000000000000-0x0000000000100000 1M PTE RW ---[ Kernel Image Start ]--- 0x0000000000100000-0x0000000000800000 7M PMD RO 0x0000000000800000-0x00000000008a9000 676K PTE RO 0x00000000008a9000-0x0000000000900000 348K PTE RW 0x0000000000900000-0x0000000001500000 12M PMD RW ---[ Kernel Image End ]--- 0x0000000001500000-0x0000000280000000 10219M PMD RW 0x0000000280000000-0x000003d280000000 3904G PUD I ---[ vmemmap Area ]--- 0x000003d280000000-0x000003d288c00000 140M PTE RW 0x000003d288c00000-0x000003d300000000 1908M PMD I 0x000003d300000000-0x000003e000000000 52G PUD I ---[ vmalloc Area ]--- 0x000003e000000000-0x000003e000009000 36K PTE RW 0x000003e000009000-0x000003e0000ee000 916K PTE I 0x000003e0000ee000-0x000003e000146000 352K PTE RW 0x000003e000146000-0x000003e000200000 744K PTE I 0x000003e000200000-0x000003e080000000 2046M PMD I 0x000003e080000000-0x0000040000000000 126G PUD I This usually makes only sense for kernel developers. The output with CONFIG_DEBUG_PAGEALLOC is not very helpful, because of the huge number of mapped out pages, however I decided for the time being to not add a !DEBUG_PAGEALLOC dependency. Maybe it's helpful for somebody even with that option. Signed-off-by:
-
Martin Schwidefsky authored
Do the switch to z/Architecture (alias 64 bit) mode early in head.S. If the machine is already running in 64 bit mode the sigp turns into a nop. With this change it doesn't matter in which mode the kernel is started. Reviewd-by:
-
Heiko Carstens authored
Remove some EXPORT_SYMBOLs. There is no module code anywhere which calls these pageattr functions. Signed-off-by:
-
Heiko Carstens authored
The current page table walk code in pageattr.c only checks for large pages while walking the kernel page table, but happily assumes that everything else is just fine. Add more checks so we never access invalid memory regions. Reviewed-by:
Gerald Schaefer <gerald.schaefer@de.ibm.com> Signed-off-by:
-
Heiko Carstens authored
pmd_huge() will always return 0 on !HUGETLBFS, however we use that helper function when walking the kernel page tables to decide if we have a 1MB page frame or not. Since we create 1MB frames for the kernel 1:1 mapping independently of HUGETLBFS this can lead to incorrect storage accesses since the code can assume that we have a pointer to a page table instead of a pointer to a 1MB frame. Fix this by adding a pmd_large() primitive like other architectures have it already and remove all references to HUGETLBFS/HUGETLBPAGE from the code that walks kernel page tables. Reviewed-by:
-
Sebastian Ott authored
Let the driver core handle device attribute creation and removal. This will simplify the code and eliminates races between attribute availability and userspace notification via uevents. Signed-off-by:
-
Heiko Carstens authored
Make use of the pfmf instruction, if available, to initialize storage keys of whole 1MB or 2GB frames instead of initializing every single page with the sske instruction. Signed-off-by:
-
Heiko Carstens authored
MACHINE_HAS_PFMF and MACHINE_HAS_HPAGE actually have the same semantics: the cpu has the EDAT1 facility installed in zArch mode. So remove one of the feature flags in machine_flags and rename the other one to EDAT1. The two old macros simply get mapped to MACHINE_HAS_EDAT1. Signed-off-by:
-
Linus Torvalds authored
Merge patches from Andrew Morton: "A few misc things and very nearly all of the MM tree. A tremendous amount of stuff (again), including a significant rbtree library rework." * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (160 commits) sparc64: Support transparent huge pages. mm: thp: Use more portable PMD clearing sequenece in zap_huge_pmd(). mm: Add and use update_mmu_cache_pmd() in transparent huge page code. sparc64: Document PGD and PMD layout. sparc64: Eliminate PTE table memory wastage. sparc64: Halve the size of PTE tables sparc64: Only support 4MB huge pages and 8KB base pages. memory-hotplug: suppress "Trying to free nonexistent resource <XXXXXXXXXXXXXXXX-YYYYYYYYYYYYYYYY>" warning mm: memcg: clean up mm_match_cgroup() signature mm: document PageHuge somewhat mm: use %pK for /proc/vmallocinfo mm, thp: fix mlock statistics mm, thp: fix mapped pages avoiding unevictable list on mlock memory-hotplug: update memory block's state and notify userspace memory-hotplug: preparation to notify memory block's state at memory hot remove mm: avoid section mismatch warning for memblock_type_name make GFP_NOTRACK definition unconditional cma: decrease cc.nr_migratepages after reclaiming pagelist CMA: migrate mlocked pages kpageflags: fix wrong KPF_THP on non-huge compound pages ...
-
David Miller authored
This is relatively easy since PMD's now cover exactly 4MB of memory. Our PMD entries are 32-bits each, so we use a special encoding. The lowest bit, PMD_ISHUGE, determines the interpretation. This is possible because sparc64's page tables are purely software entities so we can use whatever encoding scheme we want. We just have to make the TLB miss assembler page table walkers aware of the layout. set_pmd_at() works much like set_pte_at() but it has to operate in two page from a table of non-huge PTEs, so we have to queue up TLB flushes based upon what mappings are valid in the PTE table. In the second regime we are going from huge-page to non-huge-page, and in that case we need only queue up a single TLB flush to push out the huge page mapping. We still have 5 bits remaining in the huge PMD encoding so we can very likely support any new pieces of THP state tracking that might get added in the future. With lots of help from Johannes Weiner. Signed-off-by:
David S. Miller <davem@davemloft.net> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
David Miller authored
Invalidation sequences are handled in various ways on various architectures. One way, which sparc64 uses, is to let the set_*_at() functions accumulate pending flushes into a per-cpu array. Then the flush_tlb_range() et al. calls process the pending TLB flushes. In this regime, the __tlb_remove_*tlb_entry() implementations are essentially NOPs. The canonical PTE zap in mm/memory.c is: ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); With a subsequent tlb_flush_mmu() if needed. Mirror this in the THP PMD zapping using: orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd); page = pmd_page(orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); And we properly accomodate TLB flush mechanims like the one described above. Signed-off-by:
-
David Miller authored
The transparent huge page code passes a PMD pointer in as the third argument of update_mmu_cache(), which expects a PTE pointer. This never got noticed because X86 implements update_mmu_cache() as a macro and thus we don't get any type checking, and X86 is the only architecture which supports transparent huge pages currently. Before other architectures can support transparent huge pages properly we need to add a new interface which will take a PMD pointer as the third argument rather than a PTE pointer. [akpm@linux-foundation.org: implement update_mm_cache_pmd() for s390] Signed-off-by:
-
David Miller authored
We're going to be messing around with the PMD interpretation and layout for the sake of transparent huge pages, so we better clearly document what we're starting with. Signed-off-by:
-
David Miller authored
We've split up the PTE tables so that they take up half a page instead of a full page. This is in order to facilitate transparent huge page support, which works much better if our PMDs cover 4MB instead of 8MB. What we do is have a one-behind cache for PTE table allocations in the mm struct. This logic triggers only on allocations. For example, we don't try to keep track of free'd up page table blocks in the style that the s390 port does. There were only two slightly annoying aspects to this change: 1) Changing pgtable_t to be a "pte_t *". There's all of this special logic in the TLB free paths that needed adjustments, as did the PMD populate interfaces. 2) init_new_context() needs to zap the pointer, since the mm struct just gets copied from the parent on fork. Signed-off-by:
-
David Miller authored
The reason we want to do this is to facilitate transparent huge page support. Right now PMD's cover 8MB of address space, and our huge page size is 4MB. The current transparent hugepage support is not able to handle HPAGE_SIZE != PMD_SIZE. So make PTE tables be sized to half of a page instead of a full page. We can still map properly the whole supported virtual address range which on sparc64 requires 44 bits. Add a compile time CPP test which ensures that this requirement is always met. There is a minor inefficiency added by this change. We only use half of the page for PTE tables. It's not trivial to use only half of the page yet still get all of the pgtable_page_{ctor,dtor}() stuff working properly. It is doable, and that will come in a subsequent change. Signed-off-by: -
David Miller authored
Narrowing the scope of the page size configurations will make the transparent hugepage changes much simpler. In the end what we really want to do is have the kernel support multiple huge page sizes and use whatever is appropriate as the context dictactes. Signed-off-by:
-
Yasuaki Ishimatsu authored
memory-hotplug: suppress "Trying to free nonexistent resource <XXXXXXXXXXXXXXXX-YYYYYYYYYYYYYYYY>" warning When our x86 box calls __remove_pages(), release_mem_region() shows many warnings. And x86 box cannot unregister iomem_resource. "Trying to free nonexistent resource <XXXXXXXXXXXXXXXX-YYYYYYYYYYYYYYYY>" release_mem_region() has been changed to be called in each PAGES_PER_SECTION by commit de7f0cba ("memory hotplug: release memory regions in PAGES_PER_SECTION chunks"). Because powerpc registers iomem_resource in each PAGES_PER_SECTION chunk. But when I hot add memory on x86 box, iomem_resource is register in each _CRS not PAGES_PER_SECTION chunk. So x86 box unregisters iomem_resource. The patch fixes the problem. Signed-off-by:
Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Jiang Liu <liuj97@gmail.com> Cc: Len Brown <len.brown@intel.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Christoph Lameter <cl@linux.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Nathan Fontenot <nfont@austin.ibm.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by:
-
Johannes Weiner authored
It really should return a boolean for match/no match. And since it takes a memcg, not a cgroup, fix that parameter name as well. [akpm@linux-foundation.org: mm_match_cgroup() is not a macro] Signed-off-by:
Johannes Weiner <hannes@cmpxchg.org> Acked-by:
Michal Hocko <mhocko@suse.cz> Signed-off-by:
-
Andrew Morton authored
Acked-by:
David Rientjes <rientjes@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by:
-
Kees Cook authored
In the paranoid case of sysctl kernel.kptr_restrict=2, mask the kernel virtual addresses in /proc/vmallocinfo too. Signed-off-by:
Kees Cook <keescook@chromium.org> Reported-by:
Brad Spengler <spender@grsecurity.net> Acked-by:
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by:
-
David Rientjes authored
NR_MLOCK is only accounted in single page units: there's no logic to handle transparent hugepages. This patch checks the appropriate number of pages to adjust the statistics by so that the correct amount of memory is reflected. Currently: $ grep Mlocked /proc/meminfo Mlocked: 19636 kB #define MAP_SIZE (4 << 30) /* 4GB */ void *ptr = mmap(NULL, MAP_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); mlock(ptr, MAP_SIZE); $ grep Mlocked /proc/meminfo Mlocked: 29844 kB munlock(ptr, MAP_SIZE); $ grep Mlocked /proc/meminfo Mlocked: 19636 kB And with this patch: $ grep Mlock /proc/meminfo Mlocked: 19636 kB mlock(ptr, MAP_SIZE); $ grep Mlock /proc/meminfo Mlocked: 4213664 kB munlock(ptr, MAP_SIZE); $ grep Mlock /proc/meminfo Mlocked: 19636 kB Signed-off-by:
Hugh Dickens <hughd@google.com> Acked-by:
Andrea Arcangeli <aarcange@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by:
Michel Lespinasse <walken@google.com> Signed-off-by:
-
David Rientjes authored
When a transparent hugepage is mapped and it is included in an mlock() range, follow_page() incorrectly avoids setting the page's mlock bit and moving it to the unevictable lru. This is evident if you try to mlock(), munlock(), and then mlock() a range again. Currently: #define MAP_SIZE (4 << 30) /* 4GB */ void *ptr = mmap(NULL, MAP_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); mlock(ptr, MAP_SIZE); $ grep -E "Unevictable|Inactive\(anon" /proc/meminfo Inactive(anon): 6304 kB Unevictable: 4213924 kB munlock(ptr, MAP_SIZE); Inactive(anon): 4186252 kB Unevictable: 19652 kB mlock(ptr, MAP_SIZE); Inactive(anon): 4198556 kB Unevictable: 21684 kB Notice that less than 2MB was added to the unevictable list; this is because these pages in the range are not transparent hugepages since the 4GB range was allocated with mmap() and has no specific alignment. If posix_memalign() were used instead, unevictable would not have grown at all on the second mlock(). The fix is to call mlock_vma_page() so that the mlock bit is set and the page is added to the unevictable list. With this patch: mlock(ptr, MAP_SIZE); Inactive(anon): 4056 kB Unevictable: 4213940 kB munlock(ptr, MAP_SIZE); Inactive(anon): 4198268 kB Unevictable: 19636 kB mlock(ptr, MAP_SIZE); Inactive(anon): 4008 kB Unevictable: 4213940 kB Signed-off-by:
-
Wen Congyang authored
remove_memory() will be called when hot removing a memory device. But even if offlining memory, we cannot notice it. So the patch updates the memory block's state and sends notification to userspace. Additionally, the memory device may contain more than one memory block. If the memory block has been offlined, __offline_pages() will fail. So we should try to offline one memory block at a time. Thus remove_memory() also check each memory block's state. So there is no need to check the memory block's state before calling remove_memory(). Signed-off-by:
Wen Congyang <wency@cn.fujitsu.com> Signed-off-by:
-
Wen Congyang authored
remove_memory() is called in two cases: 1. echo offline >/sys/devices/system/memory/memoryXX/state 2. hot remove a memory device In the 1st case, the memory block's state is changed and the notification that memory block's state changed is sent to userland after calling remove_memory(). So user can notice memory block is changed. But in the 2nd case, the memory block's state is not changed and the notification is not also sent to userspcae even if calling remove_memory(). So user cannot notice memory block is changed. For adding the notification at memory hot remove, the patch just prepare as follows: 1st case uses offline_pages() for offlining memory. 2nd case uses remove_memory() for offlining memory and changing memory block's state and notifing the information. The patch does not implement notification to remove_memory(). Signed-off-by: -
Raghavendra D Prabhu authored
Following section mismatch warning is thrown during build; WARNING: vmlinux.o(.text+0x32408f): Section mismatch in reference from the function memblock_type_name() to the variable .meminit.data:memblock The function memblock_type_name() references the variable __meminitdata memblock. This is often because memblock_type_name lacks a __meminitdata annotation or the annotation of memblock is wrong. This is because memblock_type_name makes reference to memblock variable with attribute __meminitdata. Hence, the warning (even if the function is inline). [akpm@linux-foundation.org: remove inline] Signed-off-by:Raghavendra D Prabhu <rprabhu@wnohang.net> Cc: Tejun Heo <tj@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by:
-
Glauber Costa authored
There was a general sentiment in a recent discussion (See https://lkml.org/lkml/2012/9/18/258) that the __GFP flags should be defined unconditionally. Currently, the only offender is GFP_NOTRACK, which is conditional to KMEMCHECK. Signed-off-by:
Glauber Costa <glommer@parallels.com> Acked-by:
Christoph Lameter <cl@linux.com> Cc: Mel Gorman <mgorman@suse.de> Acked-by:
-
Minchan Kim authored
reclaim_clean_pages_from_list() reclaims clean pages before migration so cc.nr_migratepages should be updated. Currently, there is no problem but it can be wrong if we try to use the value in future. Signed-off-by:
Minchan Kim <minchan@kernel.org> Acked-by:
Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Signed-off-by:
-
Minchan Kim authored
Presently CMA cannot migrate mlocked pages so it ends up failing to allocate contiguous memory space. This patch makes mlocked pages be migrated out. Of course, it can affect realtime processes but in CMA usecase, contiguous memory allocation failing is far worse than access latency to an mlocked page being variable while CMA is running. If someone wants to make the system realtime, he shouldn't enable CMA because stalls can still happen at random times. [akpm@linux-foundation.org: tweak comment text, per Mel] Signed-off-by:
-
Naoya Horiguchi authored
KPF_THP can be set on non-huge compound pages (like slab pages or pages allocated by drivers with __GFP_COMP) because PageTransCompound only checks PG_head and PG_tail. Obviously this is a bug and breaks user space applications which look for thp via /proc/kpageflags. This patch rules out setting KPF_THP wrongly by additionally checking PageLRU on the head pages. Signed-off-by:
Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by:
Fengguang Wu <fengguang.wu@intel.com> Cc: <stable@vger.kernel.org> Signed-off-by:
-
Yan Hong authored
The parameter 'wb' is never used in this function. Signed-off-by:
Yan Hong <clouds.yan@gmail.com> Acked-by:
-
Robert P. J. Day authored
Signed-off-by:
Robert P. J. Day <rpjday@crashcourse.ca> Signed-off-by:
-
Hugh Dickins authored
Simply remove UNEVICTABLE_MLOCKFREED and unevictable_pgs_mlockfreed line from /proc/vmstat: Johannes and Mel point out that it was very unlikely to have been used by any tool, and of course we can restore it easily enough if that turns out to be wrong. Signed-off-by:
-
Minchan Kim authored
During memory-hotplug, I found NR_ISOLATED_[ANON|FILE] are increasing, causing the kernel to hang. When the system doesn't have enough free pages, it enters reclaim but never reclaim any pages due to too_many_isolated()==true and loops forever. The cause is that when we do memory-hotadd after memory-remove, __zone_pcp_update() clears a zone's ZONE_STAT_ITEMS in setup_pageset() although the vm_stat_diff of all CPUs still have values. In addtion, when we offline all pages of the zone, we reset them in zone_pcp_reset without draining so we loss some zone stat item. Reviewed-by:
-
Minchan Kim authored
Revert commit 0def08e3 because check_range can't fail in migrate_to_node with considering current usecases. Quote from Johannes : I think it makes sense to revert. Not because of the semantics, but I : just don't see how check_range() could even fail for this callsite: : : 1. we pass mm->mmap->vm_start in there, so we should not fail due to : find_vma() : : 2. we pass MPOL_MF_DISCONTIG_OK, so the discontig checks do not apply : and so can not fail : : 3. we pass MPOL_MF_MOVE | MPOL_MF_MOVE_ALL, the page table loops will : continue until addr == end, so we never fail with -EIO And I added a new VM_BUG_ON for checking migrate_to_node's future usecase which might pass to MPOL_MF_STRICT. Suggested-by:
-
Haggai Eran authored
In order to allow sleeping during invalidate_page mmu notifier calls, we need to avoid calling when holding the PT lock. In addition to its direct calls, invalidate_page can also be called as a substitute for a change_pte call, in case the notifier client hasn't implemented change_pte. This patch drops the invalidate_page call from change_pte, and instead wraps all calls to change_pte with invalidate_range_start and invalidate_range_end calls. Note that change_pte still cannot sleep after this patch, and that clients implementing change_pte should not take action on it in case the number of outstanding invalidate_range_start calls is larger than one, otherwise they might miss a later invalidation. Signed-off-by:
Haggai Eran <haggaie@mellanox.com> Cc: Andrea Arcangeli <andrea@qumranet.com> Cc: Sagi Grimberg <sagig@mellanox.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> Cc: Or Gerlitz <ogerlitz@mellanox.com> Cc: Haggai Eran <haggaie@mellanox.com> Cc: Shachar Raindel <raindel@mellanox.com> Cc: Liran Liss <liranl@mellanox.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Avi Kivity <avi@redhat.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by:
-
Sagi Grimberg authored
In order to allow sleeping during mmu notifier calls, we need to avoid invoking them under the page table spinlock. This patch solves the problem by calling invalidate_page notification after releasing the lock (but before freeing the page itself), or by wrapping the page invalidation with calls to invalidate_range_begin and invalidate_range_end. To prevent accidental changes to the invalidate_range_end arguments after the call to invalidate_range_begin, the patch introduces a convention of saving the arguments in consistently named locals: unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ ... mmun_start = ... mmun_end = ... mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); ... mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); The patch changes code to use this convention for all calls to mmu_notifier_invalidate_range_start/end, except those where the calls are close enough so that anyone who glances at the code can see the values aren't changing. This patchset is a preliminary step towards on-demand paging design to be added to the RDMA stack. Why do we want on-demand paging for Infiniband? Applications register memory with an RDMA adapter using system calls, and subsequently post IO operations that refer to the corresponding virtual addresses directly to HW. Until now, this was achieved by pinning the memory during the registration calls. The goal of on demand paging is to avoid pinning the pages of registered memory regions (MRs). This will allow users the same flexibility they get when swapping any other part of their processes address spaces. Instead of requiring the entire MR to fit in physical memory, we can allow the MR to be larger, and only fit the current working set in physical memory. Why should anyone care? What problems are users currently experiencing? This can make programming with RDMA much simpler. Today, developers that are working with more data than their RAM can hold need either to deregister and reregister memory regions throughout their process's life, or keep a single memory region and copy the data to it. On demand paging will allow these developers to register a single MR at the beginning of their process's life, and let the operating system manage which pages needs to be fetched at a given time. In the future, we might be able to provide a single memory access key for each process that would provide the entire process's address as one large memory region, and the developers wouldn't need to register memory regions at all. Is there any prospect that any other subsystems will utilise these infrastructural changes? If so, which and how, etc? As for other subsystems, I understand that XPMEM wanted to sleep in MMU notifiers, as Christoph Lameter wrote at http://lkml.indiana.edu/hypermail/linux/kernel/0802.1/0460.html and perhaps Andrea knows about other use cases. Scheduling in mmu notifications is required since we need to sync the hardware with the secondary page tables change. A TLB flush of an IO device is inherently slower than a CPU TLB flush, so our design works by sending the invalidation request to the device, and waiting for an interrupt before exiting the mmu notifier handler. Avi said: kvm may be a buyer. kvm::mmu_lock, which serializes guest page faults, also protects long operations such as destroying large ranges. It would be good to convert it into a spinlock, but as it is used inside mmu notifiers, this cannot be done. (there are alternatives, such as keeping the spinlock and using a generation counter to do the teardown in O(1), which is what the "may" is doing up there). [akpm@linux-foundation.orgpossible speed tweak in hugetlb_cow(), cleanups] Signed-off-by:
Andrea Arcangeli <andrea@qumranet.com> Signed-off-by:
Sagi Grimberg <sagig@mellanox.com> Signed-off-by:
-
Michal Hocko authored
Commit 0c176d52 ("mm: hugetlb: fix pgoff computation when unmapping page from vma") fixed pgoff calculation but it has replaced it by vma_hugecache_offset() which is not approapriate for offsets used for vma_prio_tree_foreach() because that one expects index in page units rather than in huge_page_shift. Johannes said: : The resulting index may not be too big, but it can be too small: assume : hpage size of 2M and the address to unmap to be 0x200000. This is regular : page index 512 and hpage index 1. If you have a VMA that maps the file : only starting at the second huge page, that VMAs vm_pgoff will be 512 but : you ask for offset 1 and miss it even though it does map the page of : interest. hugetlb_cow() will try to unmap, miss the vma, and retry the : cow until the allocation succeeds or the skipped vma(s) go away. Signed-off-by:
Hillf Danton <dhillf@gmail.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: David Rientjes <rientjes@google.com> Acked-by:
-
