summaryrefslogtreecommitdiffstats
path: root/include
Commit message (Collapse)AuthorAgeFilesLines
* mm, page_isolation: make set/unset_migratetype_isolate() file-localNaoya Horiguchi2015-09-081-5/+0
| | | | | | | | | | | | | Nowaday, set/unset_migratetype_isolate() is defined and used only in mm/page_isolation, so let's limit the scope within the file. Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: David Rientjes <rientjes@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mem-hotplug: handle node hole when initializing numa_meminfo.Tang Chen2015-09-081-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When parsing SRAT, all memory ranges are added into numa_meminfo. In numa_init(), before entering numa_cleanup_meminfo(), all possible memory ranges are in numa_meminfo. And numa_cleanup_meminfo() removes all ranges over max_pfn or empty. But, this only works if the nodes are continuous. Let's have a look at the following example: We have an SRAT like this: SRAT: Node 0 PXM 0 [mem 0x00000000-0x5fffffff] SRAT: Node 0 PXM 0 [mem 0x100000000-0x1ffffffffff] SRAT: Node 1 PXM 1 [mem 0x20000000000-0x3ffffffffff] SRAT: Node 4 PXM 2 [mem 0x40000000000-0x5ffffffffff] hotplug SRAT: Node 5 PXM 3 [mem 0x60000000000-0x7ffffffffff] hotplug SRAT: Node 2 PXM 4 [mem 0x80000000000-0x9ffffffffff] hotplug SRAT: Node 3 PXM 5 [mem 0xa0000000000-0xbffffffffff] hotplug SRAT: Node 6 PXM 6 [mem 0xc0000000000-0xdffffffffff] hotplug SRAT: Node 7 PXM 7 [mem 0xe0000000000-0xfffffffffff] hotplug On boot, only node 0,1,2,3 exist. And the numa_meminfo will look like this: numa_meminfo.nr_blks = 9 1. on node 0: [0, 60000000] 2. on node 0: [100000000, 20000000000] 3. on node 1: [20000000000, 40000000000] 4. on node 4: [40000000000, 60000000000] 5. on node 5: [60000000000, 80000000000] 6. on node 2: [80000000000, a0000000000] 7. on node 3: [a0000000000, a0800000000] 8. on node 6: [c0000000000, a0800000000] 9. on node 7: [e0000000000, a0800000000] And numa_cleanup_meminfo() will merge 1 and 2, and remove 8,9 because the end address is over max_pfn, which is a0800000000. But 4 and 5 are not removed because their end addresses are less then max_pfn. But in fact, node 4 and 5 don't exist. In a word, numa_cleanup_meminfo() is not able to handle holes between nodes. Since memory ranges in node 4 and 5 are in numa_meminfo, in numa_register_memblks(), node 4 and 5 will be mistakenly set to online. If you run lscpu, it will show: NUMA node0 CPU(s): 0-14,128-142 NUMA node1 CPU(s): 15-29,143-157 NUMA node2 CPU(s): NUMA node3 CPU(s): NUMA node4 CPU(s): 62-76,190-204 NUMA node5 CPU(s): 78-92,206-220 In this patch, we use memblock_overlaps_region() to check if ranges in numa_meminfo overlap with ranges in memory_block. Since memory_block contains all available memory at boot time, if they overlap, it means the ranges exist. If not, then remove them from numa_meminfo. After this patch, lscpu will show: NUMA node0 CPU(s): 0-14,128-142 NUMA node1 CPU(s): 15-29,143-157 NUMA node4 CPU(s): 62-76,190-204 NUMA node5 CPU(s): 78-92,206-220 Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tejun Heo <tj@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Vladimir Murzin <vladimir.murzin@arm.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Alexander Kuleshov <kuleshovmail@gmail.com> Cc: Baoquan He <bhe@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm/memblock.c: make memblock_overlaps_region() return bool.Tang Chen2015-09-081-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | memblock_overlaps_region() checks if the given memblock region intersects a region in memblock. If so, it returns the index of the intersected region. But its only caller is memblock_is_region_reserved(), and it returns 0 if false, non-zero if true. Both of these should return bool. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tejun Heo <tj@kernel.org> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Vladimir Murzin <vladimir.murzin@arm.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Alexander Kuleshov <kuleshovmail@gmail.com> Cc: Baoquan He <bhe@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* hugetlbfs: add hugetlbfs_fallocate()Mike Kravetz2015-09-081-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is based on the shmem version, but it has diverged quite a bit. We have no swap to worry about, nor the new file sealing. Add synchronication via the fault mutex table to coordinate page faults, fallocate allocation and fallocate hole punch. What this allows us to do is move physical memory in and out of a hugetlbfs file without having it mapped. This also gives us the ability to support MADV_REMOVE since it is currently implemented using fallocate(). MADV_REMOVE lets madvise() remove pages from the middle of a hugetlbfs file, which wasn't possible before. hugetlbfs fallocate only operates on whole huge pages. Based on code by Dave Hansen. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* hugetlbfs: New huge_add_to_page_cache helper routineMike Kravetz2015-09-081-0/+2
| | | | | | | | | | | | | | | | | | | Currently, there is only a single place where hugetlbfs pages are added to the page cache. The new fallocate code be adding a second one, so break the functionality out into its own helper. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* hugetlbfs: truncate_hugepages() takes a range of pagesMike Kravetz2015-09-081-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm/hugetlb: expose hugetlb fault mutex for use by fallocateMike Kravetz2015-09-081-0/+5
| | | | | | | | | | | | | | | | | | | | | | hugetlb page faults are currently synchronized by the table of mutexes (htlb_fault_mutex_table). fallocate code will need to synchronize with the page fault code when it allocates or deletes pages. Expose interfaces so that fallocate operations can be synchronized with page faults. Minor name changes to be more consistent with other global hugetlb symbols. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm/hugetlb: add cache of descriptors to resv_map for region_addMike Kravetz2015-09-081-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | hugetlbfs is used today by applications that want a high degree of control over huge page usage. Often, large hugetlbfs files are used to map a large number huge pages into the application processes. The applications know when page ranges within these large files will no longer be used, and ideally would like to release them back to the subpool or global pools for other uses. The fallocate() system call provides an interface for preallocation and hole punching within files. This patch set adds fallocate functionality to hugetlbfs. fallocate hole punch will want to remove a specific range of pages. When pages are removed, their associated entries in the region/reserve map will also be removed. This will break an assumption in the region_chg/region_add calling sequence. If a new region descriptor must be allocated, it is done as part of the region_chg processing. In this way, region_add can not fail because it does not need to attempt an allocation. To prepare for fallocate hole punch, create a "cache" of descriptors that can be used by region_add if necessary. region_chg will ensure there are sufficient entries in the cache. It will be necessary to track the number of in progress add operations to know a sufficient number of descriptors reside in the cache. A new routine region_abort is added to adjust this in progress count when add operations are aborted. vma_abort_reservation is also added for callers creating reservations with vma_needs_reservation/vma_commit_reservation. [akpm@linux-foundation.org: fix typo in comment, use more cols] Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm: rename and move get/set_freepage_migratetypeVlastimil Babka2015-09-081-12/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The pair of get/set_freepage_migratetype() functions are used to cache pageblock migratetype for a page put on a pcplist, so that it does not have to be retrieved again when the page is put on a free list (e.g. when pcplists become full). Historically it was also assumed that the value is accurate for pages on freelists (as the functions' names unfortunately suggest), but that cannot be guaranteed without affecting various allocator fast paths. It is in fact not needed and all such uses have been removed. The last remaining (but pointless) usage related to pages of freelists is in move_freepages(), which this patch removes. To prevent further confusion, rename the functions to get/set_pcppage_migratetype() and expand their description. Since all the users are now in mm/page_alloc.c, move the functions there from the shared header. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: David Rientjes <rientjes@google.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Acked-by: Michal Nazarewicz <mina86@mina86.com> Cc: Laura Abbott <lauraa@codeaurora.org> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Seungho Park <seungho1.park@lge.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* memcg: move memcg_proto_active from sock.hMichal Hocko2015-09-081-5/+0
| | | | | | | | | | | | | The only user is sock_update_memcg which is living in memcontrol.c so it doesn't make much sense to pollute sock.h by this inline helper. Move it to memcontrol.c and open code it into its only caller. Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Vladimir Davydov <vdavydov@parallels.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* memcg: get rid of extern for functions in memcontrol.hMichal Hocko2015-09-081-8/+8
| | | | | | | | | | | | Most of the exported functions in this header are not marked extern so change the rest to follow the same style. Signed-off-by: Michal Hocko <mhocko@suse.cz> Reviewed-by: Vladimir Davydov <vdavydov@parallels.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* memcg: get rid of mem_cgroup_root_css for !CONFIG_MEMCGMichal Hocko2015-09-081-2/+0
| | | | | | | | | | | | | | | The only user is cgwb_bdi_init and that one depends on CONFIG_CGROUP_WRITEBACK which in turn depends on CONFIG_MEMCG so it doesn't make much sense to definte an empty stub for !CONFIG_MEMCG. Moreover ERR_PTR(-EINVAL) is ugly and would lead to runtime crashes if used in unguarded code paths. Better fail during compilation. Signed-off-by: Michal Hocko <mhocko@suse.cz> Reviewed-by: Vladimir Davydov <vdavydov@parallels.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* memcg: export struct mem_cgroupMichal Hocko2015-09-083-62/+346
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | mem_cgroup structure is defined in mm/memcontrol.c currently which means that the code outside of this file has to use external API even for trivial access stuff. This patch exports mm_struct with its dependencies and makes some of the exported functions inlines. This even helps to reduce the code size a bit (make defconfig + CONFIG_MEMCG=y) text data bss dec hex filename 12355346 1823792 1089536 15268674 e8fb42 vmlinux.before 12354970 1823792 1089536 15268298 e8f9ca vmlinux.after This is not much (370B) but better than nothing. We also save a function call in some hot paths like callers of mem_cgroup_count_vm_event which is used for accounting. The patch doesn't introduce any functional changes. [vdavykov@parallels.com: inline memcg_kmem_is_active] [vdavykov@parallels.com: do not expose type outside of CONFIG_MEMCG] [akpm@linux-foundation.org: memcontrol.h needs eventfd.h for eventfd_ctx] [akpm@linux-foundation.org: export mem_cgroup_from_task() to modules] Signed-off-by: Michal Hocko <mhocko@suse.cz> Reviewed-by: Vladimir Davydov <vdavydov@parallels.com> Suggested-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm, oom: add description of struct oom_controlDavid Rientjes2015-09-081-3/+17
| | | | | | | | | | | | | Describe the purpose of struct oom_control and what each member does. Also make gfp_mask and order const since they are never manipulated or passed to functions that discard the qualifier. Signed-off-by: David Rientjes <rientjes@google.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm, oom: pass an oom order of -1 when triggered by sysrqDavid Rientjes2015-09-081-1/+0
| | | | | | | | | | | | | | The force_kill member of struct oom_control isn't needed if an order of -1 is used instead. This is the same as order == -1 in struct compact_control which requires full memory compaction. This patch introduces no functional change. Signed-off-by: David Rientjes <rientjes@google.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm, oom: organize oom context into structDavid Rientjes2015-09-081-10/+15
| | | | | | | | | | | | | | | | There are essential elements to an oom context that are passed around to multiple functions. Organize these elements into a new struct, struct oom_control, that specifies the context for an oom condition. This patch introduces no functional change. Signed-off-by: David Rientjes <rientjes@google.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm: improve __GFP_NORETRY comment based on implementationDavid Rientjes2015-09-081-1/+4
| | | | | | | | | | | Explicitly state that __GFP_NORETRY will attempt direct reclaim and memory compaction before returning NULL and that the oom killer is not called in the current implementation of the page allocator. [akpm@linux-foundation.org: s/has/have/] Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm: /proc/pid/smaps:: show proportional swap share of the mappingMinchan Kim2015-09-081-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We want to know per-process workingset size for smart memory management on userland and we use swap(ex, zram) heavily to maximize memory efficiency so workingset includes swap as well as RSS. On such system, if there are lots of shared anonymous pages, it's really hard to figure out exactly how many each process consumes memory(ie, rss + wap) if the system has lots of shared anonymous memory(e.g, android). This patch introduces SwapPss field on /proc/<pid>/smaps so we can get more exact workingset size per process. Bongkyu tested it. Result is below. 1. 50M used swap SwapTotal: 461976 kB SwapFree: 411192 kB $ adb shell cat /proc/*/smaps | grep "SwapPss:" | awk '{sum += $2} END {print sum}'; 48236 $ adb shell cat /proc/*/smaps | grep "Swap:" | awk '{sum += $2} END {print sum}'; 141184 2. 240M used swap SwapTotal: 461976 kB SwapFree: 216808 kB $ adb shell cat /proc/*/smaps | grep "SwapPss:" | awk '{sum += $2} END {print sum}'; 230315 $ adb shell cat /proc/*/smaps | grep "Swap:" | awk '{sum += $2} END {print sum}'; 1387744 [akpm@linux-foundation.org: simplify kunmap_atomic() call] Signed-off-by: Minchan Kim <minchan@kernel.org> Reported-by: Bongkyu Kim <bongkyu.kim@lge.com> Tested-by: Bongkyu Kim <bongkyu.kim@lge.com> Cc: Hugh Dickins <hughd@google.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm: remove put_page_unless_one()Vineet Gupta2015-09-081-12/+0
| | | | | | | | It has no callers. Signed-off-by: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* dax: don't use set_huge_zero_page()Kirill A. Shutemov2015-09-081-3/+0
| | | | | | | | | | | This is another place where DAX assumed that pgtable_t was a pointer. Open code the important parts of set_huge_zero_page() in DAX and make set_huge_zero_page() static again. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Matthew Wilcox <willy@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* dax: add huge page fault supportMatthew Wilcox2015-09-081-0/+14
| | | | | | | | | | | | | This is the support code for DAX-enabled filesystems to allow them to provide huge pages in response to faults. Signed-off-by: Matthew Wilcox <willy@linux.intel.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm: add vmf_insert_pfn_pmd()Matthew Wilcox2015-09-081-0/+2
| | | | | | | | | | | | | | | Similar to vm_insert_pfn(), but for PMDs rather than PTEs. The 'vmf_' prefix instead of 'vm_' prefix is intended to indicate that it returns a VMF_ value rather than an errno (which would only have to be converted into a VMF_ value anyway). Signed-off-by: Matthew Wilcox <willy@linux.intel.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm: export various functions for the benefit of DAXMatthew Wilcox2015-09-081-0/+10
| | | | | | | | | | | | To use the huge zero page in DAX, we need these functions exported. Signed-off-by: Matthew Wilcox <willy@linux.intel.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm: add a pmd_fault handlerMatthew Wilcox2015-09-081-0/+2
| | | | | | | | | | | | Allow non-anonymous VMAs to provide huge pages in response to a page fault. Signed-off-by: Matthew Wilcox <willy@linux.intel.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* thp: prepare for DAX huge pagesMatthew Wilcox2015-09-081-0/+4
| | | | | | | | | | | | | | Add a vma_is_dax() helper macro to test whether the VMA is DAX, and use it in zap_huge_pmd() and __split_huge_page_pmd(). [akpm@linux-foundation.org: fix build] Signed-off-by: Matthew Wilcox <willy@linux.intel.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* dax: move DAX-related functions to a new headerMatthew Wilcox2015-09-082-14/+21
| | | | | | | | | | | | | | | | | | | In order to handle the !CONFIG_TRANSPARENT_HUGEPAGES case, we need to return VM_FAULT_FALLBACK from the inlined dax_pmd_fault(), which is defined in linux/mm.h. Given that we don't want to include <linux/mm.h> in <linux/fs.h>, the easiest solution is to move the DAX-related functions to a new header, <linux/dax.h>. We could also have moved VM_FAULT_* definitions to a new header, or a different header that isn't quite such a boil-the-ocean header as <linux/mm.h>, but this felt like the best option. Signed-off-by: Matthew Wilcox <willy@linux.intel.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* thp: vma_adjust_trans_huge(): adjust file-backed VMA tooKirill A. Shutemov2015-09-081-10/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | This series of patches adds support for using PMD page table entries to map DAX files. We expect NV-DIMMs to start showing up that are many gigabytes in size and the memory consumption of 4kB PTEs will be astronomical. The patch series leverages much of the Transparant Huge Pages infrastructure, going so far as to borrow one of Kirill's patches from his THP page cache series. This patch (of 10): Since we're going to have huge pages in page cache, we need to call adjust file-backed VMA, which potentially can contain huge pages. For now we call it for all VMAs. Probably later we will need to introduce a flag to indicate that the VMA has huge pages. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Acked-by: Hillf Danton <dhillf@gmail.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm: introduce vma_is_anonymous(vma) helperOleg Nesterov2015-09-081-0/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | special_mapping_fault() is absolutely broken. It seems it was always wrong, but this didn't matter until vdso/vvar started to use more than one page. And after this change vma_is_anonymous() becomes really trivial, it simply checks vm_ops == NULL. However, I do think the helper makes sense. There are a lot of ->vm_ops != NULL checks, the helper makes the caller's code more understandable (self-documented) and this is more grep-friendly. This patch (of 3): Preparation. Add the new simple helper, vma_is_anonymous(vma), and change handle_pte_fault() to use it. It will have more users. The name is not accurate, say a hpet_mmap()'ed vma is not anonymous. Perhaps it should be named vma_has_fault() instead. But it matches the logic in mmap.c/memory.c (see next changes). "True" just means that a page fault will use do_anonymous_page(). Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* Merge tag 'nfs-for-4.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfsLinus Torvalds2015-09-079-61/+57
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull NFS client updates from Trond Myklebust: "Highlights include: Stable patches: - Fix atomicity of pNFS commit list updates - Fix NFSv4 handling of open(O_CREAT|O_EXCL|O_RDONLY) - nfs_set_pgio_error sometimes misses errors - Fix a thinko in xs_connect() - Fix borkage in _same_data_server_addrs_locked() - Fix a NULL pointer dereference of migration recovery ops for v4.2 client - Don't let the ctime override attribute barriers. - Revert "NFSv4: Remove incorrect check in can_open_delegated()" - Ensure flexfiles pNFS driver updates the inode after write finishes - flexfiles must not pollute the attribute cache with attrbutes from the DS - Fix a protocol error in layoutreturn - Fix a protocol issue with NFSv4.1 CLOSE stateids Bugfixes + cleanups - pNFS blocks bugfixes from Christoph - Various cleanups from Anna - More fixes for delegation corner cases - Don't fsync twice for O_SYNC/IS_SYNC files - Fix pNFS and flexfiles layoutstats bugs - pnfs/flexfiles: avoid duplicate tracking of mirror data - pnfs: Fix layoutget/layoutreturn/return-on-close serialisation issues - pnfs/flexfiles: error handling retries a layoutget before fallback to MDS Features: - Full support for the OPEN NFS4_CREATE_EXCLUSIVE4_1 mode from Kinglong - More RDMA client transport improvements from Chuck - Removal of the deprecated ib_reg_phys_mr() and ib_rereg_phys_mr() verbs from the SUNRPC, Lustre and core infiniband tree. - Optimise away the close-to-open getattr if there is no cached data" * tag 'nfs-for-4.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (108 commits) NFSv4: Respect the server imposed limit on how many changes we may cache NFSv4: Express delegation limit in units of pages Revert "NFS: Make close(2) asynchronous when closing NFS O_DIRECT files" NFS: Optimise away the close-to-open getattr if there is no cached data NFSv4.1/flexfiles: Clean up ff_layout_write_done_cb/ff_layout_commit_done_cb NFSv4.1/flexfiles: Mark the layout for return in ff_layout_io_track_ds_error() nfs: Remove unneeded checking of the return value from scnprintf nfs: Fix truncated client owner id without proto type NFSv4.1/flexfiles: Mark layout for return if the mirrors are invalid NFSv4.1/flexfiles: RW layouts are valid only if all mirrors are valid NFSv4.1/flexfiles: Fix incorrect usage of pnfs_generic_mark_devid_invalid() NFSv4.1/flexfiles: Fix freeing of mirrors NFSv4.1/pNFS: Don't request a minimal read layout beyond the end of file NFSv4.1/pnfs: Handle LAYOUTGET return values correctly NFSv4.1/pnfs: Don't ask for a read layout for an empty file. NFSv4.1: Fix a protocol issue with CLOSE stateids NFSv4.1/flexfiles: Don't mark the entire deviceid as bad for file errors SUNRPC: Prevent SYN+SYNACK+RST storms SUNRPC: xs_reset_transport must mark the connection as disconnected NFSv4.1/pnfs: Ensure layoutreturn reserves space for the opaque payload ...
| * NFSv4: Express delegation limit in units of pagesTrond Myklebust2015-09-071-1/+1
| | | | | | | | | | | | | | | | Since we're tracking modifications to the page cache on a per-page basis, it makes sense to express the limit to how much we may cache in units of pages. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * NFS: Send attributes in OPEN request for NFS4_CREATE_EXCLUSIVE4_1Kinglong Mee2015-08-271-1/+1
| | | | | | | | | | | | | | | | | | | | | | Client sends a SETATTR request after OPEN for updating attributes. For create file with S_ISGID is set, the S_ISGID in SETATTR will be ignored at nfs server as chmod of no PERMISSION. v3, same as v2. Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * NFS: Get suppattr_exclcreat when getting server capabilitiesKinglong Mee2015-08-272-0/+7
| | | | | | | | | | | | | | | | | | | | Create file with attributs as NFS4_CREATE_EXCLUSIVE4_1 mode depends on suppattr_exclcreat attribut. v3, same as v2. Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * NFS: Update NFS4_BITMAP_SIZEKinglong Mee2015-08-271-1/+1
| | | | | | | | | | | | | | | | | | | | v4.1/v4.2 have define attributes at word2, nfs client also support security label now. v3, same as v2. Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * NFSv4: Enable delegated opens even when reboot recovery is pendingTrond Myklebust2015-08-191-1/+1
| | | | | | | | | | | | | | | | | | | | | | Unlike the previous attempt, this takes into account the fact that we may be calling it from the recovery thread itself. Detect this by looking at what kind of open we're doing, and checking the state of the NFS_DELEGATION_NEED_RECLAIM if it turns out we're doing a reboot reclaim-type open. Cc: Olga Kornievskaia <aglo@umich.edu> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * SUNRPC: Drop double-underscores from __rpc_cmp_addr6()Trond Myklebust2015-08-171-1/+1
| | | | | | | | | | | | Reported-by: kbuild test robot <fengguang.wu@intel.com> Fixes: 7b0ce60c0b20 ("SUNRPC: Drop double-underscores from rpc_cmp_addr{4|6}()") Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * Merge tag 'nfs-rdma-for-4.3' of git://git.linux-nfs.org/projects/anna/nfs-rdmaTrond Myklebust2015-08-172-47/+1
| |\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | NFS: NFS over RDMA Client Side Changes These patches improve both client performance and scalability, most notably by increasing the maixmum allowed rsize and wsize and by increasing the number of RDMA "credits". There are also several bugfixes, such as correcting how WRITE compounds are encoded and fixing large NFS symlink operations. Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| | * core: Remove the ib_reg_phys_mr() and ib_rereg_phys_mr() verbsChuck Lever2015-08-051-46/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The verbs are obsolete. The ib_rereg_phys_mr() verb is not used by kernel ULPs, and the last ib_reg_phys_mr() call site in the kernel tree has now been removed. Two staging tree call sites remain in the Lustre client. The Lustre team has been notified of the deprecation of reg_phys_mr. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Acked-by: Doug Ledford <dledford@redhat.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| | * xprtrdma: Increase default credit limitChuck Lever2015-08-051-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In preparation for similar increases on NFS/RDMA servers, bump the advertised credit limit for RPC/RDMA to 128. This allocates some extra resources, but the client will continue to allow only the number of RPCs in flight that the server requests via its advertised credit limit. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-By: Sagi Grimberg <sagig@mellanox.com> Tested-by: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | NFS: Remove nfs_release()Anna Schumaker2015-08-171-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | And call nfs_file_clear_open_context() directly. This makes it obvious that nfs_file_release() will always return 0. Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * | SUNRPC: Add an rpc_cmp_addr_port() functionAnna Schumaker2015-08-171-0/+13
| | | | | | | | | | | | | | | | | | | | | | | | This function is to help determine if two sockaddrs are really the same socket. Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * | SUNRPC: Drop double-underscores from rpc_cmp_addr{4|6}()Anna Schumaker2015-08-171-6/+6
| | | | | | | | | | | | | | | | | | | | | | | | I'm planning on using these functions inside the client, so remove the underscores to make it feel like I'm using a public interface. Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * | pnfs: move common blocklayout XDR defintions to nfs4.hChristoph Hellwig2015-08-171-0/+18
| | | | | | | | | | | | | | | Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * | sunrpc: increase UNX_MAXNODENAME from 32 to __NEW_UTS_LEN bytesJeff Layton2015-08-121-2/+6
| |/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The current limit of 32 bytes artificially limits the name string that we end up stuffing into NFSv4.x client ID blobs. If you have multiple hosts with long hostnames that only differ near the end, then this can cause NFSv4 client ID collisions. Linux nodenames are actually limited to __NEW_UTS_LEN bytes (64), so use that as the limit instead. Also, use XDR_QUADLEN to specify the slack length, just for clarity and in case someone in the future changes this to something not evenly divisible by 4. Reported-by: Michael Skralivetsky <michael.skralivetsky@primarydata.com> Signed-off-by: Jeff Layton <jeff.layton@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
* | Merge branch 'for-linus' of ↵Linus Torvalds2015-09-054-16/+46
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs Pull vfs updates from Al Viro: "In this one: - d_move fixes (Eric Biederman) - UFS fixes (me; locking is mostly sane now, a bunch of bugs in error handling ought to be fixed) - switch of sb_writers to percpu rwsem (Oleg Nesterov) - superblock scalability (Josef Bacik and Dave Chinner) - swapon(2) race fix (Hugh Dickins)" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (65 commits) vfs: Test for and handle paths that are unreachable from their mnt_root dcache: Reduce the scope of i_lock in d_splice_alias dcache: Handle escaped paths in prepend_path mm: fix potential data race in SyS_swapon inode: don't softlockup when evicting inodes inode: rename i_wb_list to i_io_list sync: serialise per-superblock sync operations inode: convert inode_sb_list_lock to per-sb inode: add hlist_fake to avoid the inode hash lock in evict writeback: plug writeback at a high level change sb_writers to use percpu_rw_semaphore shift percpu_counter_destroy() into destroy_super_work() percpu-rwsem: kill CONFIG_PERCPU_RWSEM percpu-rwsem: introduce percpu_rwsem_release() and percpu_rwsem_acquire() percpu-rwsem: introduce percpu_down_read_trylock() document rwsem_release() in sb_wait_write() fix the broken lockdep logic in __sb_start_write() introduce __sb_writers_{acquired,release}() helpers ufs_inode_get{frag,block}(): get rid of 'phys' argument ufs_getfrag_block(): tidy up a bit ...
| * \ Merge branch 'superblock-scaling' of ↵Al Viro2015-08-213-5/+16
| |\ \ | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/josef/btrfs-next into for-next Conflicts: include/linux/fs.h
| | * | inode: rename i_wb_list to i_io_listDave Chinner2015-08-171-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There's a small consistency problem between the inode and writeback naming. Writeback calls the "for IO" inode queues b_io and b_more_io, but the inode calls these the "writeback list" or i_wb_list. This makes it hard to an new "under writeback" list to the inode, or call it an "under IO" list on the bdi because either way we'll have writeback on IO and IO on writeback and it'll just be confusing. I'm getting confused just writing this! So, rename the inode "for IO" list variable to i_io_list so we can add a new "writeback list" in a subsequent patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Josef Bacik <jbacik@fb.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: Dave Chinner <dchinner@redhat.com>
| | * | sync: serialise per-superblock sync operationsDave Chinner2015-08-171-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When competing sync(2) calls walk the same filesystem, they need to walk the list of inodes on the superblock to find all the inodes that we need to wait for IO completion on. However, when multiple wait_sb_inodes() calls do this at the same time, they contend on the the inode_sb_list_lock and the contention causes system wide slowdowns. In effect, concurrent sync(2) calls can take longer and burn more CPU than if they were serialised. Stop the worst of the contention by adding a per-sb mutex to wrap around wait_sb_inodes() so that we only execute one sync(2) IO completion walk per superblock superblock at a time and hence avoid contention being triggered by concurrent sync(2) calls. Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Josef Bacik <jbacik@fb.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: Dave Chinner <dchinner@redhat.com>
| | * | inode: convert inode_sb_list_lock to per-sbDave Chinner2015-08-172-3/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The process of reducing contention on per-superblock inode lists starts with moving the locking to match the per-superblock inode list. This takes the global lock out of the picture and reduces the contention problems to within a single filesystem. This doesn't get rid of contention as the locks still have global CPU scope, but it does isolate operations on different superblocks form each other. Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Josef Bacik <jbacik@fb.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: Dave Chinner <dchinner@redhat.com>
| | * | inode: add hlist_fake to avoid the inode hash lock in evictJosef Bacik2015-08-172-1/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Some filesystems don't use the VFS inode hash and fake the fact they are hashed so that all the writeback code works correctly. However, this means the evict() path still tries to remove the inode from the hash, meaning that the inode_hash_lock() needs to be taken unnecessarily. Hence under certain workloads the inode_hash_lock can be contended even if the inode is never actually hashed. To avoid this add hlist_fake to test if the inode isn't actually hashed to avoid taking the hash lock on inodes that have never been hashed. Based on Dave Chinner's inode: add IOP_NOTHASHED to avoid inode hash lock in evict basd on Al's suggestions. Thanks, Signed-off-by: Josef Bacik <jbacik@fb.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: Dave Chinner <dchinner@redhat.com>
| * | | change sb_writers to use percpu_rw_semaphoreOleg Nesterov2015-08-151-13/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We can remove everything from struct sb_writers except frozen and add the array of percpu_rw_semaphore's instead. This patch doesn't remove sb_writers->wait_unfrozen yet, we keep it for get_super_thawed(). We will probably remove it later. This change tries to address the following problems: - Firstly, __sb_start_write() looks simply buggy. It does __sb_end_write() if it sees ->frozen, but if it migrates to another CPU before percpu_counter_dec(), sb_wait_write() can wrongly succeed if there is another task which holds the same "semaphore": sb_wait_write() can miss the result of the previous percpu_counter_inc() but see the result of this percpu_counter_dec(). - As Dave Hansen reports, it is suboptimal. The trivial microbenchmark that writes to a tmpfs file in a loop runs 12% faster if we change this code to rely on RCU and kill the memory barriers. - This code doesn't look simple. It would be better to rely on the generic locking code. According to Dave, this change adds the same performance improvement. Note: with this change both freeze_super() and thaw_super() will do synchronize_sched_expedited() 3 times. This is just ugly. But: - This will be "fixed" by the rcu_sync changes we are going to merge. After that freeze_super()->percpu_down_write() will use synchronize_sched(), and thaw_super() won't use synchronize() at all. This doesn't need any changes in fs/super.c. - Once we merge rcu_sync changes, we can also change super.c so that all wb_write->rw_sem's will share the single ->rss in struct sb_writes, then freeze_super() will need only one synchronize_sched(). Signed-off-by: Oleg Nesterov <oleg@redhat.com> Reviewed-by: Jan Kara <jack@suse.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-09-15 06:11:21 +0000