- 02 Apr, 2020 40 commits
-
-
Johannes Weiner authored
Patch series "mm: memcontrol: recursive memory.low protection", v3. The current memory.low (and memory.min) semantics require protection to be assigned to a cgroup in an untinterrupted chain from the top-level cgroup all the way to the leaf. In practice, we want to protect entire cgroup subtrees from each other (system management software vs. workload), but we would like the VM to balance memory optimally *within* each subtree, without having to make explicit weight allocations among individual components. The current semantics make that impossible. They also introduce unmanageable complexity into more advanced resource trees. For example: host root `- system.slice `- rpm upgrades `- logging `- workload.slice `- a container `- system.slice `- workload.slice `- job A `- component 1 `- component 2 `- job B At a host-level perspective, we would like to protect the outer workload.slice subtree as a whole from rpm upgrades, logging etc. But for that to be effective, right now we'd have to propagate it down through the container, the inner workload.slice, into the job cgroup and ultimately the component cgroups where memory is actually, physically allocated. This may cross several tree delegation points and namespace boundaries, which make such a setup near impossible. CPU and IO on the other hand are already distributed recursively. The user would simply configure allowances at the host level, and they would apply to the entire subtree without any downward propagation. To enable the above-mentioned usecases and bring memory in line with other resource controllers, this patch series extends memory.low/min such that settings apply recursively to the entire subtree. Users can still assign explicit shares in subgroups, but if they don't, any ancestral protection will be distributed such that children compete freely amongst each other - as if no memory control were enabled inside the subtree - but enjoy protection from neighboring trees. In the above example, the user would then be able to configure shares of CPU, IO and memory at the host level to comprehensively protect and isolate the workload.slice as a whole from system.slice activity. Patch #1 fixes an existing bug that can give a cgroup tree more protection than it should receive as per ancestor configuration. Patch #2 simplifies and documents the existing code to make it easier to reason about the changes in the next patch. Patch #3 finally implements recursive memory protection semantics. Because of a risk of regressing legacy setups, the new semantics are hidden behind a cgroup2 mount option, 'memory_recursiveprot'. More details in patch #3. This patch (of 3): When memory.low is overcommitted - i.e. the children claim more protection than their shared ancestor grants them - the allowance is distributed in proportion to how much each sibling uses their own declared protection: low_usage = min(memory.low, memory.current) elow = parent_elow * (low_usage / siblings_low_usage) However, siblings_low_usage is not the sum of all low_usages. It sums up the usages of *only those cgroups that are within their memory.low* That means that low_usage can be *bigger* than siblings_low_usage, and consequently the total protection afforded to the children can be bigger than what the ancestor grants the subtree. Consider three groups where two are in excess of their protection: A/memory.low = 10G A/A1/memory.low = 10G, memory.current = 20G A/A2/memory.low = 10G, memory.current = 20G A/A3/memory.low = 10G, memory.current = 8G siblings_low_usage = 8G (only A3 contributes) A1/elow = parent_elow(10G) * low_usage(10G) / siblings_low_usage(8G) = 12.5G -> 10G A2/elow = parent_elow(10G) * low_usage(10G) / siblings_low_usage(8G) = 12.5G -> 10G A3/elow = parent_elow(10G) * low_usage(8G) / siblings_low_usage(8G) = 10.0G (the 12.5G are capped to the explicit memory.low setting of 10G) With that, the sum of all awarded protection below A is 30G, when A only grants 10G for the entire subtree. What does this mean in practice? A1 and A2 would still be in excess of their 10G allowance and would be reclaimed, whereas A3 would not. As they eventually drop below their protection setting, they would be counted in siblings_low_usage again and the error would right itself. When reclaim was applied in a binary fashion (cgroup is reclaimed when it's above its protection, otherwise it's skipped) this would actually work out just fine. However, since 1bc63fb1 ("mm, memcg: make scan aggression always exclude protection"), reclaim pressure is scaled to how much a cgroup is above its protection. As a result this calculation error unduly skews pressure away from A1 and A2 toward the rest of the system. But why did we do it like this in the first place? The reasoning behind exempting groups in excess from siblings_low_usage was to go after them first during reclaim in an overcommitted subtree: A/memory.low = 2G, memory.current = 4G A/A1/memory.low = 3G, memory.current = 2G A/A2/memory.low = 1G, memory.current = 2G siblings_low_usage = 2G (only A1 contributes) A1/elow = parent_elow(2G) * low_usage(2G) / siblings_low_usage(2G) = 2G A2/elow = parent_elow(2G) * low_usage(1G) / siblings_low_usage(2G) = 1G While the children combined are overcomitting A and are technically both at fault, A2 is actively declaring unprotected memory and we would like to reclaim that first. However, while this sounds like a noble goal on the face of it, it doesn't make much difference in actual memory distribution: Because A is overcommitted, reclaim will not stop once A2 gets pushed back to within its allowance; we'll have to reclaim A1 either way. The end result is still that protection is distributed proportionally, with A1 getting 3/4 (1.5G) and A2 getting 1/4 (0.5G) of A's allowance. [ If A weren't overcommitted, it wouldn't make a difference since each cgroup would just get the protection it declares: A/memory.low = 2G, memory.current = 3G A/A1/memory.low = 1G, memory.current = 1G A/A2/memory.low = 1G, memory.current = 2G With the current calculation: siblings_low_usage = 1G (only A1 contributes) A1/elow = parent_elow(2G) * low_usage(1G) / siblings_low_usage(1G) = 2G -> 1G A2/elow = parent_elow(2G) * low_usage(1G) / siblings_low_usage(1G) = 2G -> 1G Including excess groups in siblings_low_usage: siblings_low_usage = 2G A1/elow = parent_elow(2G) * low_usage(1G) / siblings_low_usage(2G) = 1G -> 1G A2/elow = parent_elow(2G) * low_usage(1G) / siblings_low_usage(2G) = 1G -> 1G ] Simplify the calculation and fix the proportional reclaim bug by including excess cgroups in siblings_low_usage. After this patch, the effective memory.low distribution from the example above would be as follows: A/memory.low = 10G A/A1/memory.low = 10G, memory.current = 20G A/A2/memory.low = 10G, memory.current = 20G A/A3/memory.low = 10G, memory.current = 8G siblings_low_usage = 28G A1/elow = parent_elow(10G) * low_usage(10G) / siblings_low_usage(28G) = 3.5G A2/elow = parent_elow(10G) * low_usage(10G) / siblings_low_usage(28G) = 3.5G A3/elow = parent_elow(10G) * low_usage(8G) / siblings_low_usage(28G) = 2.8G Fixes: 1bc63fb1 ("mm, memcg: make scan aggression always exclude protection") Fixes: 23067153 ("mm: memory.low hierarchical behavior") Signed-off-by:Johannes Weiner <hannes@cmpxchg.org> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Acked-by:
Tejun Heo <tj@kernel.org> Acked-by:
Roman Gushchin <guro@fb.com> Acked-by:
Chris Down <chris@chrisdown.name> Acked-by:
Michal Hocko <mhocko@suse.com> Cc: Michal Koutný <mkoutny@suse.com> Link: http://lkml.kernel.org/r/20200227195606.46212-2-hannes@cmpxchg.orgSigned-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Roman Gushchin authored
Drop the _memcg suffix from (__)memcg_kmem_(un)charge functions. It's shorter and more obvious. These are the most basic functions which are just (un)charging the given cgroup with the given amount of pages. Also fix up the corresponding comments. Signed-off-by:
Shakeel Butt <shakeelb@google.com> Acked-by:
-
Roman Gushchin authored
There are many places in memcg_charge_slab() and memcg_uncharge_slab() which are calculating the number of pages to charge, css references to grab etc depending on the order of the slab page. Let's simplify the code by calculating it once and caching in the local variable. Signed-off-by:
-
Roman Gushchin authored
These functions are charging the given number of kernel pages to the given memory cgroup. The number doesn't have to be a power of two. Let's make them to take the unsigned int nr_pages as an argument instead of the page order. It makes them look consistent with the corresponding uncharge functions and functions like: mem_cgroup_charge_skmem(memcg, nr_pages). Signed-off-by:
-
Roman Gushchin authored
Rename (__)memcg_kmem_(un)charge() into (__)memcg_kmem_(un)charge_page() to better reflect what they are actually doing: 1) call __memcg_kmem_(un)charge_memcg() to actually charge or uncharge the current memcg 2) set or clear the PageKmemcg flag Signed-off-by:
-
Roman Gushchin authored
Drop the unused page argument and put the memcg pointer at the first place. This make the function consistent with its peers: __memcg_kmem_uncharge_memcg(), memcg_kmem_charge_memcg(), etc. Signed-off-by:
-
Roman Gushchin authored
Patch series "mm: memcg: kmem API cleanup", v2. This patchset aims to clean up the kernel memory charging API. It doesn't bring any functional changes, just removes unused arguments, renames some functions and fixes some comments. Currently it's not obvious which functions are most basic (memcg_kmem_(un)charge_memcg()) and which are based on them (memcg_kmem_(un)charge()). The patchset renames these functions and removes unused arguments: TL;DR: was: memcg_kmem_charge_memcg(page, gfp, order, memcg) memcg_kmem_uncharge_memcg(memcg, nr_pages) memcg_kmem_charge(page, gfp, order) memcg_kmem_uncharge(page, order) now: memcg_kmem_charge(memcg, gfp, nr_pages) memcg_kmem_uncharge(memcg, nr_pages) memcg_kmem_charge_page(page, gfp, order) memcg_kmem_uncharge_page(page, order) This patch (of 6): The first argument of memcg_kmem_charge_memcg() and __memcg_kmem_charge_memcg() is the page pointer and it's not used. Let's drop it. Memcg pointer is passed as the last argument. Move it to the first place for consistency with other memcg functions, e.g. __memcg_kmem_uncharge_memcg() or try_charge(). Signed-off-by:
-
Roman Gushchin authored
Sometimes we need to get a memcg pointer from a charged kernel object. The right way to get it depends on whether it's a proper slab object or it's backed by raw pages (e.g. it's a vmalloc alloction). In the first case the kmem_cache->memcg_params.memcg indirection should be used; in other cases it's just page->mem_cgroup. To simplify this task and hide the implementation details let's use the mem_cgroup_from_obj() helper, which takes a pointer to any kernel object and returns a valid memcg pointer or NULL. Passing a kernel address rather than a pointer to a page will allow to use this helper for per-object (rather than per-page) tracked objects in the future. The caller is still responsible to ensure that the returned memcg isn't going away underneath: take the rcu read lock, cgroup mutex etc; depending on the context. mem_cgroup_from_kmem() defined in mm/list_lru.c is now obsolete and can be removed. Signed-off-by:
Yafang Shao <laoar.shao@gmail.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Link: http://lkml.kernel.org/r/20200117203609.3146239-1-guro@fb.comSigned-off-by:
-
Kirill Tkhai authored
The shrinker_map may be touched from any cpu (e.g., a bit there may be set by a task running everywhere) but kswapd is always bound to specific node. So allocate shrinker_map from the related NUMA node to respect its NUMA locality. Also, this follows generic way we use for allocation of memcg's per-node data. Signed-off-by:
Kirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by:
David Hildenbrand <david@redhat.com> Reviewed-by:
-
Yafang Shao authored
When I manually set default n to MEMCG_KMEM in init/Kconfig, bellow error occurs, mm/slab_common.c: In function 'memcg_slab_start': mm/slab_common.c:1530:30: error: 'struct mem_cgroup' has no member named 'kmem_caches' return seq_list_start(&memcg->kmem_caches, *pos); ^ mm/slab_common.c: In function 'memcg_slab_next': mm/slab_common.c:1537:32: error: 'struct mem_cgroup' has no member named 'kmem_caches' return seq_list_next(p, &memcg->kmem_caches, pos); ^ mm/slab_common.c: In function 'memcg_slab_show': mm/slab_common.c:1551:16: error: 'struct mem_cgroup' has no member named 'kmem_caches' if (p == memcg->kmem_caches.next) ^ CC arch/x86/xen/smp.o mm/slab_common.c: In function 'memcg_slab_start': mm/slab_common.c:1531:1: warning: control reaches end of non-void function [-Wreturn-type] } ^ mm/slab_common.c: In function 'memcg_slab_next': mm/slab_common.c:1538:1: warning: control reaches end of non-void function [-Wreturn-type] } ^ That's because kmem_caches is defined only when CONFIG_MEMCG_KMEM is set, while memcg_slab_start() will use it no matter CONFIG_MEMCG_KMEM is defined or not. By the way, the reason I mannuly undefined CONFIG_MEMCG_KMEM is to verify whether my some other code change is still stable when CONFIG_MEMCG_KMEM is not set. Unfortunately, the existing code has been already unstable since v4.11. Fixes: bc2791f8 ("slab: link memcg kmem_caches on their associated memory cgroup") Signed-off-by: -
Wei Yang authored
add_to_swap_cache() and delete_from_swap_cache() are counterparts, while currently they use different ways to count pages. It doesn't break anything because we only have two sizes for PageAnon, but this is confusing and not good practice. This patch corrects it by making both functions use hpage_nr_pages(). Signed-off-by:
Wei Yang <richard.weiyang@gmail.com> Signed-off-by:
Matthew Wilcox (Oracle) <willy@infradead.org> Link: http://lkml.kernel.org/r/20200315012920.2687-1-richard.weiyang@gmail.comSigned-off-by:
-
Yang Shi authored
Memory barrier is needed after setting LRU bit, but smp_mb() is too strong. Some architectures, i.e. x86, imply memory barrier with atomic operations, so replacing it with smp_mb__after_atomic() sounds better, which is nop on strong ordered machines, and full memory barriers on others. With this change the vm-scalability cases would perform better on x86, I saw total 6% improvement with this patch and previous inline fix. The test data (lru-file-readtwice throughput) against v5.6-rc4: mainline w/ inline fix w/ both (adding this) 150MB 154MB 159MB Fixes: 9c4e6b1a ("mm, mlock, vmscan: no more skipping pagevecs") Signed-off-by:
Yang Shi <yang.shi@linux.alibaba.com> Signed-off-by:
Vlastimil Babka <vbabka@suse.cz> Acked-by:
-
Yang Shi authored
When backporting commit 9c4e6b1a ("mm, mlock, vmscan: no more skipping pagevecs") to our 4.9 kernel, our test bench noticed around 10% down with a couple of vm-scalability's test cases (lru-file-readonce, lru-file-readtwice and lru-file-mmap-read). I didn't see that much down on my VM (32c-64g-2nodes). It might be caused by the test configuration, which is 32c-256g with NUMA disabled and the tests were run in root memcg, so the tests actually stress only one inactive and active lru. It sounds not very usual in mordern production environment. That commit did two major changes: 1. Call page_evictable() 2. Use smp_mb to force the PG_lru set visible It looks they contribute the most overhead. The page_evictable() is a function which does function prologue and epilogue, and that was used by page reclaim path only. However, lru add is a very hot path, so it sounds better to make it inline. However, it calls page_mapping() which is not inlined either, but the disassemble shows it doesn't do push and pop operations and it sounds not very straightforward to inline it. Other than this, it sounds smp_mb() is not necessary for x86 since SetPageLRU is atomic which enforces memory barrier already, replace it with smp_mb__after_atomic() in the following patch. With the two fixes applied, the tests can get back around 5% on that test bench and get back normal on my VM. Since the test bench configuration is not that usual and I also saw around 6% up on the latest upstream, so it sounds good enough IMHO. The below is test data (lru-file-readtwice throughput) against the v5.6-rc4: mainline w/ inline fix 150MB 154MB With this patch the throughput gets 2.67% up. The data with using smp_mb__after_atomic() is showed in the following patch. Shakeel Butt did the below test: On a real machine with limiting the 'dd' on a single node and reading 100 GiB sparse file (less than a single node). Just ran a single instance to not cause the lru lock contention. The cmdline used is "dd if=file-100GiB of=/dev/null bs=4k". Ran the cmd 10 times with drop_caches in between and measured the time it took. Without patch: 56.64143 +- 0.672 sec With patches: 56.10 +- 0.21 sec [akpm@linux-foundation.org: move page_evictable() to internal.h] Fixes: 9c4e6b1a ("mm, mlock, vmscan: no more skipping pagevecs") Signed-off-by:
-
Wei Yang authored
Currently we use a tmp pointer, pentry, to transfer and reset swap cache slot, which is a little redundant. Swap cache slot stores the entry value directly, assign and reset it by value would be straight forward. Also this patch merges the else and if, since this is the only case we refill and repeat swap cache. Signed-off-by:
Wei Yang <richard.weiyang@linux.alibaba.com> Signed-off-by:
Tim Chen <tim.c.chen@linux.intel.com> Link: http://lkml.kernel.org/r/20200311055352.50574-1-richard.weiyang@linux.alibaba.comSigned-off-by:
-
Qian Cai authored
si->inuse_pages could be accessed concurrently as noticed by KCSAN, write to 0xffff98b00ebd04dc of 4 bytes by task 82262 on cpu 92: swap_range_free+0xbe/0x230 swap_range_free at mm/swapfile.c:719 swapcache_free_entries+0x1be/0x250 free_swap_slot+0x1c8/0x220 __swap_entry_free.constprop.19+0xa3/0xb0 free_swap_and_cache+0x53/0xa0 unmap_page_range+0x7e0/0x1ce0 unmap_single_vma+0xcd/0x170 unmap_vmas+0x18b/0x220 exit_mmap+0xee/0x220 mmput+0xe7/0x240 do_exit+0x598/0xfd0 do_group_exit+0x8b/0x180 get_signal+0x293/0x13d0 do_signal+0x37/0x5d0 prepare_exit_to_usermode+0x1b7/0x2c0 ret_from_intr+0x32/0x42 read to 0xffff98b00ebd04dc of 4 bytes by task 82499 on cpu 46: try_to_unuse+0x86b/0xc80 try_to_unuse at mm/swapfile.c:2185 __x64_sys_swapoff+0x372/0xd40 do_syscall_64+0x91/0xb05 entry_SYSCALL_64_after_hwframe+0x49/0xbe The plain reads in try_to_unuse() are outside si->lock critical section which result in data races that could be dangerous to be used in a loop. Fix them by adding READ_ONCE(). Signed-off-by:
Qian Cai <cai@lca.pw> Signed-off-by:
-
Wei Yang authored
__pagevec_lru_add() is only used in mm directory now. Remove the export symbol. Signed-off-by:
Wei Yang <richardw.yang@linux.intel.com> Signed-off-by:
-
Chen Wandun authored
The -EEXIST returned by __swap_duplicate means there is a swap cache instead -EBUSY Signed-off-by:
Chen Wandun <chenwandun@huawei.com> Signed-off-by:
-
Pingfan Liu authored
FOLL_LONGTERM is a special case of FOLL_PIN. It suggests a pin which is going to be given to hardware and can't move. It would truncate CMA permanently and should be excluded. In gup slow path, where __gup_longterm_locked->check_and_migrate_cma_pages() handles FOLL_LONGTERM, but in fast path, there lacks such a check, which means a possible leak of CMA page to longterm pinned. Place a check in try_grab_compound_head() in the fast path to fix the leak, and if FOLL_LONGTERM happens on CMA, it will fall back to slow path to migrate the page. Some note about the check: Huge page's subpages have the same migrate type due to either allocation from a free_list[] or alloc_contig_range() with param MIGRATE_MOVABLE. So it is enough to check on a single subpage by is_migrate_cma_page(subpage) Signed-off-by:
Pingfan Liu <kernelfans@gmail.com> Signed-off-by:
Christoph Hellwig <hch@lst.de> Reviewed-by:
Jason Gunthorpe <jgg@mellanox.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Shuah Khan <shuah@kernel.org> Cc: Jason Gunthorpe <jgg@ziepe.ca> Link: http://lkml.kernel.org/r/1584876733-17405-3-git-send-email-kernelfans@gmail.comSigned-off-by:
-
Pingfan Liu authored
To better reflect the held state of pages and make code self-explaining, rename nr as nr_pinned. Signed-off-by:
John Hubbard <jhubbard@nvidia.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Shuah Khan <shuah@kernel.org> Cc: Jason Gunthorpe <jgg@ziepe.ca> Link: http://lkml.kernel.org/r/1584876733-17405-2-git-send-email-kernelfans@gmail.comSigned-off-by:
-
Claudio Imbrenda authored
With the introduction of protected KVM guests on s390 there is now a concept of inaccessible pages. These pages need to be made accessible before the host can access them. While cpu accesses will trigger a fault that can be resolved, I/O accesses will just fail. We need to add a callback into architecture code for places that will do I/O, namely when writeback is started or when a page reference is taken. This is not only to enable paging, file backing etc, it is also necessary to protect the host against a malicious user space. For example a bad QEMU could simply start direct I/O on such protected memory. We do not want userspace to be able to trigger I/O errors and thus the logic is "whenever somebody accesses that page (gup) or does I/O, make sure that this page can be accessed". When the guest tries to access that page we will wait in the page fault handler for writeback to have finished and for the page_ref to be the expected value. On s390x the function is not supposed to fail, so it is ok to use a WARN_ON on failure. If we ever need some more finegrained handling we can tackle this when we know the details. Signed-off-by:
Claudio Imbrenda <imbrenda@linux.ibm.com> Signed-off-by:
Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by:
Will Deacon <will@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Link: http://lkml.kernel.org/r/20200306132537.783769-3-imbrenda@linux.ibm.comSigned-off-by:
-
John Hubbard authored
As part of pin_user_pages() and related API calls, pages are "dma-pinned". For the case of compound pages of order > 1, the per-page accounting of dma pins is accomplished via the 3rd struct page in the compound page. In order to support debugging of any pin_user_pages()- related problems, enhance dump_page() so as to report the pin count in that case. Documentation/core-api/pin_user_pages.rst is also updated accordingly. Signed-off-by:
Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Link: http://lkml.kernel.org/r/20200211001536.1027652-13-jhubbard@nvidia.comSigned-off-by:
-
Matthew Wilcox (Oracle) authored
There was no protection against a corrupted struct page having an implausible compound_head(). Sanity check that a compound page has a head within reach of the maximum allocatable page (this will need to be adjusted if one of the plans to allocate 1GB pages comes to fruition). In addition, - Print the mapping pointer using %p insted of %px. The actual value of the pointer can be read out of the raw page dump and using %p gives a chance to correlate it with an earlier printk of the mapping pointer - Print the mapping pointer from the head page, not the tail page (the tail ->mapping pointer may be in use for other purposes, eg part of a list_head) - Print the order of the page for compound pages - Dump the raw head page as well as the raw page - Print the refcount from the head page, not the tail page Suggested-by:
-
John Hubbard authored
It's good to have basic unit test coverage of the new FOLL_PIN behavior. Fortunately, the gup_benchmark unit test is extremely fast (a few milliseconds), so adding it the the run_vmtests suite is going to cause no noticeable change in running time. So, add two new invocations to run_vmtests: 1) Run gup_benchmark with normal get_user_pages(). 2) Run gup_benchmark with pin_user_pages(). This is much like the first call, except that it sets FOLL_PIN. Running these two in quick succession also provide a visual comparison of the running times, which is convenient. The new invocations are fairly early in the run_vmtests script, because with test suites, it's usually preferable to put the shorter, faster tests first, all other things being equal. Signed-off-by:
Ira Weiny <ira.weiny@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Link: http://lkml.kernel.org/r/20200211001536.1027652-11-jhubbard@nvidia.comSigned-off-by:
-
John Hubbard authored
Up until now, gup_benchmark supported testing of the following kernel functions: * get_user_pages(): via the '-U' command line option * get_user_pages_longterm(): via the '-L' command line option * get_user_pages_fast(): as the default (no options required) Add test coverage for the new corresponding pin_*() functions: * pin_user_pages_fast(): via the '-a' command line option * pin_user_pages(): via the '-b' command line option Also, add an option for clarity: '-u' for what is now (still) the default choice: get_user_pages_fast(). Also, for the commands that set FOLL_PIN, verify that the pages really are dma-pinned, via the new is_dma_pinned() routine. Those commands are: PIN_FAST_BENCHMARK : calls pin_user_pages_fast() PIN_BENCHMARK : calls pin_user_pages() In between the calls to pin_*() and unpin_user_pages(), check each page: if page_maybe_dma_pinned() returns false, then WARN and return. Do this outside of the benchmark timestamps, so that it doesn't affect reported times. Signed-off-by: -
John Hubbard authored
Now that pages are "DMA-pinned" via pin_user_page*(), and unpinned via unpin_user_pages*(), we need some visibility into whether all of this is working correctly. Add two new fields to /proc/vmstat: nr_foll_pin_acquired nr_foll_pin_released These are documented in Documentation/core-api/pin_user_pages.rst. They represent the number of pages (since boot time) that have been pinned ("nr_foll_pin_acquired") and unpinned ("nr_foll_pin_released"), via pin_user_pages*() and unpin_user_pages*(). In the absence of long-running DMA or RDMA operations that hold pages pinned, the above two fields will normally be equal to each other. Also: update Documentation/core-api/pin_user_pages.rst, to remove an earlier (now confirmed untrue) claim about a performance problem with /proc/vmstat. Also: update Documentation/core-api/pin_user_pages.rst to rename the new /proc/vmstat entries, to the names listed here. Signed-off-by:Jan Kara <jack@suse.cz> Acked-by:
-
John Hubbard authored
For huge pages (and in fact, any compound page), the GUP_PIN_COUNTING_BIAS scheme tends to overflow too easily, each tail page increments the head page->_refcount by GUP_PIN_COUNTING_BIAS (1024). That limits the number of huge pages that can be pinned. This patch removes that limitation, by using an exact form of pin counting for compound pages of order > 1. The "order > 1" is required because this approach uses the 3rd struct page in the compound page, and order 1 compound pages only have two pages, so that won't work there. A new struct page field, hpage_pinned_refcount, has been added, replacing a padding field in the union (so no new space is used). This enhancement also has a useful side effect: huge pages and compound pages (of order > 1) do not suffer from the "potential false positives" problem that is discussed in the page_dma_pinned() comment block. That is because these compound pages have extra space for tracking things, so they get exact pin counts instead of overloading page->_refcount. Documentation/core-api/pin_user_pages.rst is updated accordingly. Suggested-by:
-
John Hubbard authored
Add tracking of pages that were pinned via FOLL_PIN. This tracking is implemented via overloading of page->_refcount: pins are added by adding GUP_PIN_COUNTING_BIAS (1024) to the refcount. This provides a fuzzy indication of pinning, and it can have false positives (and that's OK). Please see the pre-existing Documentation/core-api/pin_user_pages.rst for details. As mentioned in pin_user_pages.rst, callers who effectively set FOLL_PIN (typically via pin_user_pages*()) are required to ultimately free such pages via unpin_user_page(). Please also note the limitation, discussed in pin_user_pages.rst under the "TODO: for 1GB and larger huge pages" section. (That limitation will be removed in a following patch.) The effect of a FOLL_PIN flag is similar to that of FOLL_GET, and may be thought of as "FOLL_GET for DIO and/or RDMA use". Pages that have been pinned via FOLL_PIN are identifiable via a new function call: bool page_maybe_dma_pinned(struct page *page); What to do in response to encountering such a page, is left to later patchsets. There is discussion about this in [1], [2], [3], and [4]. This also changes a BUG_ON(), to a WARN_ON(), in follow_page_mask(). [1] Some slow progress on get_user_pages() (Apr 2, 2019): https://lwn.net/Articles/784574/ [2] DMA and get_user_pages() (LPC: Dec 12, 2018): https://lwn.net/Articles/774411/ [3] The trouble with get_user_pages() (Apr 30, 2018): https://lwn.net/Articles/753027/ [4] LWN kernel index: get_user_pages(): https://lwn.net/Kernel/Index/#Memory_management-get_user_pages [jhubbard@nvidia.com: add kerneldoc] Link: http://lkml.kernel.org/r/20200307021157.235726-1-jhubbard@nvidia.com [imbrenda@linux.ibm.com: if pin fails, we need to unpin, a simple put_page will not be enough] Link: http://lkml.kernel.org/r/20200306132537.783769-2-imbrenda@linux.ibm.com [akpm@linux-foundation.org: fix put_compound_head defined but not used] Suggested-by:Jérôme Glisse <jglisse@redhat.com> Signed-off-by:
-
John Hubbard authored
Internal to mm/gup.c, require that get_user_pages_fast() and __get_user_pages_fast() identify themselves, by setting FOLL_GET. This is required in order to be able to make decisions based on "FOLL_PIN, or FOLL_GET, or both or neither are set", in upcoming patches. Signed-off-by:
-
John Hubbard authored
In preparation for an upcoming patch, send gup flags args to two more routines: put_compound_head(), and undo_dev_pagemap(). Signed-off-by:
-
John Hubbard authored
An upcoming patch requires subtracting a large chunk of refcounts from a page, and checking what the resulting refcount is. This is a little different than the usual "check for zero refcount" that many of the page ref functions already do. However, it is similar to a few other routines that (like this one) are generally useful for things such as 1-based refcounting. Add page_ref_sub_return(), that subtracts a chunk of refcounts atomically, and returns an atomic snapshot of the result. Signed-off-by:
-
John Hubbard authored
A subsequent patch requires access to gup flags, so pass the flags argument through to the __gup_device_* functions. Also placate checkpatch.pl by shortening a nearby line. Signed-off-by:
-
John Hubbard authored
Patch series "mm/gup: track FOLL_PIN pages", v6. This activates tracking of FOLL_PIN pages. This is in support of fixing the get_user_pages()+DMA problem described in [1]-[4]. FOLL_PIN support is now in the main linux tree. However, the patch to use FOLL_PIN to track pages was *not* submitted, because Leon saw an RDMA test suite failure that involved (I think) page refcount overflows when huge pages were used. This patch definitively solves that kind of overflow problem, by adding an exact pincount, for compound pages (of order > 1), in the 3rd struct page of a compound page. If available, that form of pincounting is used, instead of the GUP_PIN_COUNTING_BIAS approach. Thanks again to Jan Kara for that idea. Other interesting changes: * dump_page(): added one, or two new things to report for compound pages: head refcount (for all compound pages), and map_pincount (for compound pages of order > 1). * Documentation/core-api/pin_user_pages.rst: removed the "TODO" for the huge page refcount upper limit problems, and added notes about how it works now. Also added a note about the dump_page() enhancements. * Added some comments in gup.c and mm.h, to explain that there are two ways to count pinned pages: exact (for compound pages of order > 1) and fuzzy (GUP_PIN_COUNTING_BIAS: for all other pages). ============================================================ General notes about the tracking patch: This is a prerequisite to solving the problem of proper interactions between file-backed pages, and [R]DMA activities, as discussed in [1], [2], [3], [4] and in a remarkable number of email threads since about 2017. :) In contrast to earlier approaches, the page tracking can be incrementally applied to the kernel call sites that, until now, have been simply calling get_user_pages() ("gup"). In other words, opt-in by changing from this: get_user_pages() (sets FOLL_GET) put_page() to this: pin_user_pages() (sets FOLL_PIN) unpin_user_page() ============================================================ Future steps: * Convert more subsystems from get_user_pages() to pin_user_pages(). The first probably needs to be bio/biovecs, because any filesystem testing is too difficult without those in place. * Change VFS and filesystems to respond appropriately when encountering dma-pinned pages. * Work with Ira and others to connect this all up with file system leases. [1] Some slow progress on get_user_pages() (Apr 2, 2019): https://lwn.net/Articles/784574/ [2] DMA and get_user_pages() (LPC: Dec 12, 2018): https://lwn.net/Articles/774411/ [3] The trouble with get_user_pages() (Apr 30, 2018): https://lwn.net/Articles/753027/ [4] LWN kernel index: get_user_pages() https://lwn.net/Kernel/Index/#Memory_management-get_user_pages This patch (of 12): An upcoming patch requires reusing the implementation of get_user_pages_remote(). Split up get_user_pages_remote() into an outer routine that checks flags, and an implementation routine that will be reused. This makes subsequent changes much easier to understand. There should be no change in behavior due to this patch. Signed-off-by: -
Matthew Wilcox (Oracle) authored
- These were never called PCG flags; they've been called FGP flags since their introduction in 2014. - The FGP_FOR_MMAP flag was misleadingly documented as if it was an alternative to FGP_CREAT instead of an option to it. - Rename the 'offset' parameter to 'index'. - Capitalisation, formatting, rewording. Signed-off-by:
-
Matthew Wilcox (Oracle) authored
No in-tree users (proc, madvise, memcg, mincore) can be built as a module. Signed-off-by:
-
Matthew Wilcox (Oracle) authored
Dumping the page information in this circumstance helps for debugging. Signed-off-by:
-
Matthew Wilcox (Oracle) authored
This isn't just a random struct page, it's known to be a head page, and calling it head makes the function better self-documenting. The pgoff_t is less confusing if it's named index instead of offset. Also add a couple of comments to explain why we're doing various things. Signed-off-by:
Pankaj Gupta <pankaj.gupta.linux@gmail.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/20200318140253.6141-3-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Use VM_FAULT_OOM instead of indirecting through vmf_error(-ENOMEM). Signed-off-by:
-
Souptick Joarder authored
The first argument of shrink_readahead_size_eio() is not used. Hence remove it from the function definition and from all the callers. Signed-off-by:
Souptick Joarder <jrdr.linux@gmail.com> Signed-off-by:
-
Xianting Tian authored
Mount failure issue happens under the scenario: Application forked dozens of threads to mount the same number of cramfs images separately in docker, but several mounts failed with high probability. Mount failed due to the checking result of the page(read from the superblock of loop dev) is not uptodate after wait_on_page_locked(page) returned in function cramfs_read: wait_on_page_locked(page); if (!PageUptodate(page)) { ... } The reason of the checking result of the page not uptodate: systemd-udevd read the loopX dev before mount, because the status of loopX is Lo_unbound at this time, so loop_make_request directly trigger the calling of io_end handler end_buffer_async_read, which called SetPageError(page). So It caused the page can't be set to uptodate in function end_buffer_async_read: if(page_uptodate && !PageError(page)) { SetPageUptodate(page); } Then mount operation is performed, it used the same page which is just accessed by systemd-udevd above, Because this page is not uptodate, it will launch a actual read via submit_bh, then wait on this page by calling wait_on_page_locked(page). When the I/O of the page done, io_end handler end_buffer_async_read is called, because no one cleared the page error(during the whole read path of mount), which is caused by systemd-udevd reading, so this page is still in "PageError" status, which can't be set to uptodate in function end_buffer_async_read, then caused mount failure. But sometimes mount succeed even through systemd-udeved read loopX dev just before, The reason is systemd-udevd launched other loopX read just between step 3.1 and 3.2, the steps as below: 1, loopX dev default status is Lo_unbound; 2, systemd-udved read loopX dev (page is set to PageError); 3, mount operation 1) set loopX status to Lo_bound; ==>systemd-udevd read loopX dev<== 2) read loopX dev(page has no error) 3) mount succeed As the loopX dev status is set to Lo_bound after step 3.1, so the other loopX dev read by systemd-udevd will go through the whole I/O stack, part of the call trace as below: SYS_read vfs_read do_sync_read blkdev_aio_read generic_file_aio_read do_generic_file_read: ClearPageError(page); mapping->a_ops->readpage(filp, page); here, mapping->a_ops->readpage() is blkdev_readpage. In latest kernel, some function name changed, the call trace as below: blkdev_read_iter generic_file_read_iter generic_file_buffered_read: /* * A previous I/O error may have been due to temporary * failures, eg. mutipath errors. * Pg_error will be set again if readpage fails. */ ClearPageError(page); /* Start the actual read. The read will unlock the page*/ error=mapping->a_ops->readpage(flip, page); We can see ClearPageError(page) is called before the actual read, then the read in step 3.2 succeed. This patch is to add the calling of ClearPageError just before the actual read of read path of cramfs mount. Without the patch, the call trace as below when performing cramfs mount: do_mount cramfs_read cramfs_blkdev_read read_cache_page do_read_cache_page: filler(data, page); or mapping->a_ops->readpage(data, page); With the patch, the call trace as below when performing mount: do_mount cramfs_read cramfs_blkdev_read read_cache_page: do_read_cache_page: ClearPageError(page); <== new add filler(data, page); or mapping->a_ops->readpage(data, page); With the patch, mount operation trigger the calling of ClearPageError(page) before the actual read, the page has no error if no additional page error happen when I/O done. Signed-off-by:Xianting Tian <xianting_tian@126.com> Signed-off-by:
-
Mauricio Faria de Oliveira authored
There used to be a 'retry' label in between the two (identical) checks when first introduced in commit f446daae ("mm: implement writeback livelock avoidance using page tagging"), and later modified/updated in commit 6e6938b6 ("writeback: introduce .tagged_writepages for the WB_SYNC_NONE sync stage"). The label has been removed in commit 64081362 ("mm/page-writeback.c: fix range_cyclic writeback vs writepages deadlock"), and the (identical) checks are now present / performed immediately one after another. So, remove/deduplicate the latter check, moving tag_pages_for_writeback() into the former check before the 'tag' variable assignment, so it's clear that it's not used in this (similarly-named) function call but only later in pagevec_lookup_range_tag(). Signed-off-by:
Mauricio Faria de Oliveira <mfo@canonical.com> Signed-off-by:
-
