From 4d54954a197175c0dcb3c82af0c0740d0c5f827a Mon Sep 17 00:00:00 2001 From: Sebastien Boisvert Date: Fri, 26 Oct 2018 15:02:23 -0700 Subject: include/linux/pfn_t.h: force '~' to be parsed as an unary operator Tracing the event "fs_dax:dax_pmd_insert_mapping" with perf produces this warning: [fs_dax:dax_pmd_insert_mapping] unknown op '~' It is printed in process_op (tools/lib/traceevent/event-parse.c) because '~' is parsed as a binary operator. perf reads the format of fs_dax:dax_pmd_insert_mapping ("print fmt") from /sys/kernel/debug/tracing/events/fs_dax/dax_pmd_insert_mapping/format . The format contains: ~(((u64) ~(~(((1UL) << 12)-1))) ^ \ interpreted as a binary operator by process_op(). This part is generated in the declaration of the event class dax_pmd_insert_mapping_class in include/trace/events/fs_dax.h : __print_flags_u64(__entry->pfn_val & PFN_FLAGS_MASK, "|", PFN_FLAGS_TRACE), This patch adds a pair of parentheses in the declaration of PFN_FLAGS_MASK to make sure that '~' is parsed as a unary operator by perf. The part of the format that was problematic is now: ~(((u64) (~(~(((1UL) << 12)-1)))) Now, all the '~' are parsed as unary operators. Link: http://lkml.kernel.org/r/20181021145939.8760-1-sebhtml@videotron.qc.ca Signed-off-by: Sebastien Boisvert Acked-by: Dan Williams Cc: "Steven Rostedt (VMware)" Cc: Arnaldo Carvalho de Melo Cc: "Tzvetomir Stoyanov (VMware)" Cc: Namhyung Kim Cc: Ross Zwisler Cc: Elenie Godzaridis Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pfn_t.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 21713dc14ce2..673546ba7342 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -10,7 +10,7 @@ * PFN_DEV - pfn is not covered by system memmap by default * PFN_MAP - pfn has a dynamic page mapping established by a device driver */ -#define PFN_FLAGS_MASK (((u64) ~PAGE_MASK) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) +#define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1)) #define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2)) #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3)) -- cgit v1.2.3 From 74f213ea25b99fddcf34cbe07dabdb01136bcd86 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 26 Oct 2018 15:02:27 -0700 Subject: include/linux/linkage.h: align weak symbols Since WEAK() supposed to be used instead of ENTRY() to define weak symbols, but unlike ENTRY() it doesn't have ALIGN directive. It seems there is no actual reason to not have, so let's add ALIGN to WEAK() too. Link: http://lkml.kernel.org/r/20180920135631.23833-1-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Will Deacon , Catalin Marinas Cc: Kyeongdon Kim Cc: Ard Biesheuvel Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Mark Rutland Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/linkage.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index d7618c41f74c..7c47b1a471d4 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -90,6 +90,7 @@ #ifndef WEAK #define WEAK(name) \ .weak name ASM_NL \ + ALIGN ASM_NL \ name: #endif -- cgit v1.2.3 From 5780a02fd1e87641ad6a8dd6891a1e890cf45c5d Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Fri, 26 Oct 2018 15:02:59 -0700 Subject: fs/iomap.c: change return type to vm_fault_t Change iomap_page_mkwrite() return type to vm_fault_t. see commit 1c8f422059ae ("mm: change return type to vm_fault_t") for reference. Link: http://lkml.kernel.org/r/20180827172050.GA18673@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Reviewed-by: Matthew Wilcox Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/iomap.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 3555d54bf79a..9a4258154b25 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -6,6 +6,7 @@ #include #include #include +#include struct address_space; struct fiemap_extent_info; @@ -141,7 +142,8 @@ int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); -int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); +vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, + const struct iomap_ops *ops); int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, const struct iomap_ops *ops); loff_t iomap_seek_hole(struct inode *inode, loff_t offset, -- cgit v1.2.3 From 9b6f7e163cd0f468d1b9696b785659d3c27c8667 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Oct 2018 15:03:19 -0700 Subject: mm: rework memcg kernel stack accounting If CONFIG_VMAP_STACK is set, kernel stacks are allocated using __vmalloc_node_range() with __GFP_ACCOUNT. So kernel stack pages are charged against corresponding memory cgroups on allocation and uncharged on releasing them. The problem is that we do cache kernel stacks in small per-cpu caches and do reuse them for new tasks, which can belong to different memory cgroups. Each stack page still holds a reference to the original cgroup, so the cgroup can't be released until the vmap area is released. To make this happen we need more than two subsequent exits without forks in between on the current cpu, which makes it very unlikely to happen. As a result, I saw a significant number of dying cgroups (in theory, up to 2 * number_of_cpu + number_of_tasks), which can't be released even by significant memory pressure. As a cgroup structure can take a significant amount of memory (first of all, per-cpu data like memcg statistics), it leads to a noticeable waste of memory. Link: http://lkml.kernel.org/r/20180827162621.30187-1-guro@fb.com Fixes: ac496bf48d97 ("fork: Optimize task creation by caching two thread stacks per CPU if CONFIG_VMAP_STACK=y") Signed-off-by: Roman Gushchin Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Andy Lutomirski Cc: Konstantin Khlebnikov Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 652f602167df..4399cc3f00e4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1268,10 +1268,11 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); void memcg_kmem_put_cache(struct kmem_cache *cachep); int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, struct mem_cgroup *memcg); + +#ifdef CONFIG_MEMCG_KMEM int memcg_kmem_charge(struct page *page, gfp_t gfp, int order); void memcg_kmem_uncharge(struct page *page, int order); -#ifdef CONFIG_MEMCG_KMEM extern struct static_key_false memcg_kmem_enabled_key; extern struct workqueue_struct *memcg_kmem_cache_wq; @@ -1307,6 +1308,16 @@ extern int memcg_expand_shrinker_maps(int new_id); extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); #else + +static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +{ + return 0; +} + +static inline void memcg_kmem_uncharge(struct page *page, int order) +{ +} + #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) -- cgit v1.2.3 From 68600f623d69da428c6163275f97ca126e1a8ec5 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Oct 2018 15:03:27 -0700 Subject: mm: don't miss the last page because of round-off error I've noticed, that dying memory cgroups are often pinned in memory by a single pagecache page. Even under moderate memory pressure they sometimes stayed in such state for a long time. That looked strange. My investigation showed that the problem is caused by applying the LRU pressure balancing math: scan = div64_u64(scan * fraction[lru], denominator), where denominator = fraction[anon] + fraction[file] + 1. Because fraction[lru] is always less than denominator, if the initial scan size is 1, the result is always 0. This means the last page is not scanned and has no chances to be reclaimed. Fix this by rounding up the result of the division. In practice this change significantly improves the speed of dying cgroups reclaim. [guro@fb.com: prevent double calculation of DIV64_U64_ROUND_UP() arguments] Link: http://lkml.kernel.org/r/20180829213311.GA13501@castle Link: http://lkml.kernel.org/r/20180827162621.30187-3-guro@fb.com Signed-off-by: Roman Gushchin Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Cc: Rik van Riel Cc: Konstantin Khlebnikov Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/math64.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index 837f2f2d1d34..bb2c84afb80c 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -281,4 +281,7 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) } #endif /* mul_u64_u32_div */ +#define DIV64_U64_ROUND_UP(ll, d) \ + ({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); }) + #endif /* _LINUX_MATH64_H */ -- cgit v1.2.3 From 33490af3f5c15757448b6c454ca93b48a333aa1b Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 26 Oct 2018 15:03:35 -0700 Subject: mm, mmu_notifier: be explicit about range invalition non-blocking mode If invalidate_range_start() is called for !blocking mode then all callbacks have to guarantee they will no block/sleep. The same obviously applies to invalidate_range_end because this operation pairs with the former and they are called from the same context. Make sure this is appropriately documented. Link: http://lkml.kernel.org/r/20180827112623.8992-3-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Jerome Glisse Cc: Boris Ostrovsky Cc: David Rientjes Cc: Juergen Gross Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 133ba78820ee..698e371aafe3 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -153,7 +153,9 @@ struct mmu_notifier_ops { * * If blockable argument is set to false then the callback cannot * sleep and has to return with -EAGAIN. 0 should be returned - * otherwise. + * otherwise. Please note that if invalidate_range_start approves + * a non-blocking behavior then the same applies to + * invalidate_range_end. * */ int (*invalidate_range_start)(struct mmu_notifier *mn, -- cgit v1.2.3 From 4e15a073a168b62311db911a55c4d4f1500c2821 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 26 Oct 2018 15:03:39 -0700 Subject: Revert "mm, mmu_notifier: annotate mmu notifiers with blockable invalidate callbacks" Revert 5ff7091f5a2ca ("mm, mmu_notifier: annotate mmu notifiers with blockable invalidate callbacks"). MMU_INVALIDATE_DOES_NOT_BLOCK flags was the only one used and it is no longer needed since 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers"). We now have a full support for per range !blocking behavior so we can drop the stop gap workaround which the per notifier flag was used for. Link: http://lkml.kernel.org/r/20180827112623.8992-4-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: David Rientjes Cc: Boris Ostrovsky Cc: Jerome Glisse Cc: Juergen Gross Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 698e371aafe3..9893a6432adf 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -2,7 +2,6 @@ #ifndef _LINUX_MMU_NOTIFIER_H #define _LINUX_MMU_NOTIFIER_H -#include #include #include #include @@ -11,9 +10,6 @@ struct mmu_notifier; struct mmu_notifier_ops; -/* mmu_notifier_ops flags */ -#define MMU_INVALIDATE_DOES_NOT_BLOCK (0x01) - #ifdef CONFIG_MMU_NOTIFIER /* @@ -30,15 +26,6 @@ struct mmu_notifier_mm { }; struct mmu_notifier_ops { - /* - * Flags to specify behavior of callbacks for this MMU notifier. - * Used to determine which context an operation may be called. - * - * MMU_INVALIDATE_DOES_NOT_BLOCK: invalidate_range_* callbacks do not - * block - */ - int flags; - /* * Called either by mmu_notifier_unregister or when the mm is * being destroyed by exit_mmap, always before all pages are @@ -183,10 +170,6 @@ struct mmu_notifier_ops { * Note that this function might be called with just a sub-range * of what was passed to invalidate_range_start()/end(), if * called between those functions. - * - * If this callback cannot block, and invalidate_range_{start,end} - * cannot block, mmu_notifier_ops.flags should have - * MMU_INVALIDATE_DOES_NOT_BLOCK set. */ void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end); @@ -241,7 +224,6 @@ extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, bool only_end); extern void __mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end); -extern bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm); static inline void mmu_notifier_release(struct mm_struct *mm) { @@ -495,11 +477,6 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, { } -static inline bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm) -{ - return false; -} - static inline void mmu_notifier_mm_init(struct mm_struct *mm) { } -- cgit v1.2.3 From 5d7476374564645b1a2d299e242ad7b17b1104ee Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:10 -0700 Subject: mm: remove vm_insert_mixed() All callers are now converted to vmf_insert_mixed() so convert vmf_insert_mixed() from being a compatibility wrapper into the real function. Link: http://lkml.kernel.org/r/20180828145728.11873-3-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index daa2b8f1e9a8..ecc6f9347756 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2506,7 +2506,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); -int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); @@ -2525,19 +2525,6 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -static inline vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, - unsigned long addr, pfn_t pfn) -{ - int err = vm_insert_mixed(vma, addr, pfn); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; -} - static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { -- cgit v1.2.3 From f5e6d1d5f8f3080aa7a51acea1f77085f45abe9c Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:13 -0700 Subject: mm: introduce vmf_insert_pfn_prot() Like vm_insert_pfn_prot(), but returns a vm_fault_t instead of an errno. Also unexport vm_insert_pfn_prot as it has no modular users. Link: http://lkml.kernel.org/r/20180828145728.11873-4-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ecc6f9347756..f1293bdc6de2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2506,6 +2506,8 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); +vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, -- cgit v1.2.3 From bc12e6ad9617831727e4201e7cbf5c3b868cc8fd Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:21 -0700 Subject: mm: make vm_insert_pfn_prot() static Now this is no longer used outside mm/memory.c, make it static. Link: http://lkml.kernel.org/r/20180828145728.11873-6-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f1293bdc6de2..0f5db0455e61 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2504,8 +2504,6 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr, int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); -int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, -- cgit v1.2.3 From 67fa1666223d7c825f6651add97f0011fe155f36 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:26 -0700 Subject: mm: remove references to vm_insert_pfn() Documentation and comments. Link: http://lkml.kernel.org/r/20180828145728.11873-7-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 4c92e3ba3e16..dde947083d4e 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -107,7 +107,7 @@ enum hmm_pfn_flag_e { * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory * HMM_PFN_NONE: corresponding CPU page table entry is pte_none() * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the - * result of vm_insert_pfn() or vm_insert_page(). Therefore, it should not + * result of vmf_insert_pfn() or vm_insert_page(). Therefore, it should not * be mirrored by a device, because the entry will never have HMM_PFN_VALID * set and the pfn value is undefined. * -- cgit v1.2.3 From ae2b01f37044c10e975d22116755df56252b09d8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:29 -0700 Subject: mm: remove vm_insert_pfn() All callers are now converted to vmf_insert_pfn() so convert vmf_insert_pfn() from being a compatibility wrapper around vm_insert_pfn() to being a compatibility wrapper around vmf_insert_pfn_prot(). Link: http://lkml.kernel.org/r/20180828145728.11873-8-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0f5db0455e61..737279bb479c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2502,7 +2502,7 @@ struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); @@ -2525,19 +2525,6 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, - unsigned long addr, unsigned long pfn) -{ - int err = vm_insert_pfn(vma, addr, pfn); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; -} - static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) -- cgit v1.2.3 From cc252eae85e09552f9c1e7ac0c3227f835efdf2d Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:34 -0700 Subject: mm, slab: combine kmalloc_caches and kmalloc_dma_caches Patch series "kmalloc-reclaimable caches", v4. As discussed at LSF/MM [1] here's a patchset that introduces kmalloc-reclaimable caches (more details in the second patch) and uses them for dcache external names. That allows us to repurpose the NR_INDIRECTLY_RECLAIMABLE_BYTES counter later in the series. With patch 3/6, dcache external names are allocated from kmalloc-rcl-* caches, eliminating the need for manual accounting. More importantly, it also ensures the reclaimable kmalloc allocations are grouped in pages separate from the regular kmalloc allocations. The need for proper accounting of dcache external names has shown it's easy for misbehaving process to allocate lots of them, causing premature OOMs. Without the added grouping, it's likely that a similar workload can interleave the dcache external names allocations with regular kmalloc allocations (note: I haven't searched myself for an example of such regular kmalloc allocation, but I would be very surprised if there wasn't some). A pathological case would be e.g. one 64byte regular allocations with 63 external dcache names in a page (64x64=4096), which means the page is not freed even after reclaiming after all dcache names, and the process can thus "steal" the whole page with single 64byte allocation. If other kmalloc users similar to dcache external names become identified, they can also benefit from the new functionality simply by adding __GFP_RECLAIMABLE to the kmalloc calls. Side benefits of the patchset (that could be also merged separately) include removed branch for detecting __GFP_DMA kmalloc(), and shortening kmalloc cache names in /proc/slabinfo output. The latter is potentially an ABI break in case there are tools parsing the names and expecting the values to be in bytes. This is how /proc/slabinfo looks like after booting in virtme: ... kmalloc-rcl-4M 0 0 4194304 1 1024 : tunables 1 1 0 : slabdata 0 0 0 ... kmalloc-rcl-96 7 32 128 32 1 : tunables 120 60 8 : slabdata 1 1 0 kmalloc-rcl-64 25 128 64 64 1 : tunables 120 60 8 : slabdata 2 2 0 kmalloc-rcl-32 0 0 32 124 1 : tunables 120 60 8 : slabdata 0 0 0 kmalloc-4M 0 0 4194304 1 1024 : tunables 1 1 0 : slabdata 0 0 0 kmalloc-2M 0 0 2097152 1 512 : tunables 1 1 0 : slabdata 0 0 0 kmalloc-1M 0 0 1048576 1 256 : tunables 1 1 0 : slabdata 0 0 0 ... /proc/vmstat with renamed nr_indirectly_reclaimable_bytes counter: ... nr_slab_reclaimable 2817 nr_slab_unreclaimable 1781 ... nr_kernel_misc_reclaimable 0 ... /proc/meminfo with new KReclaimable counter: ... Shmem: 564 kB KReclaimable: 11260 kB Slab: 18368 kB SReclaimable: 11260 kB SUnreclaim: 7108 kB KernelStack: 1248 kB ... This patch (of 6): The kmalloc caches currently mainain separate (optional) array kmalloc_dma_caches for __GFP_DMA allocations. There are tests for __GFP_DMA in the allocation hotpaths. We can avoid the branches by combining kmalloc_caches and kmalloc_dma_caches into a single two-dimensional array where the outer dimension is cache "type". This will also allow to add kmalloc-reclaimable caches as a third type. Link: http://lkml.kernel.org/r/20180731090649.16028-2-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: Michal Hocko Cc: Johannes Weiner Cc: David Rientjes Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Laura Abbott Cc: Sumit Semwal Cc: Vijayanand Jitta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 42 +++++++++++++++++++++++++++++++----------- 1 file changed, 31 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index ed9cbddeb4a6..2a7137043e91 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -295,12 +295,29 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) +enum kmalloc_cache_type { + KMALLOC_NORMAL = 0, +#ifdef CONFIG_ZONE_DMA + KMALLOC_DMA, +#endif + NR_KMALLOC_TYPES +}; + #ifndef CONFIG_SLOB -extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; +extern struct kmem_cache * +kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; + +static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) +{ + int is_dma = 0; + #ifdef CONFIG_ZONE_DMA -extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1]; + is_dma = !!(flags & __GFP_DMA); #endif + return is_dma; +} + /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. @@ -501,18 +518,20 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { +#ifndef CONFIG_SLOB + unsigned int index; +#endif if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); #ifndef CONFIG_SLOB - if (!(flags & GFP_DMA)) { - unsigned int index = kmalloc_index(size); + index = kmalloc_index(size); - if (!index) - return ZERO_SIZE_PTR; + if (!index) + return ZERO_SIZE_PTR; - return kmem_cache_alloc_trace(kmalloc_caches[index], - flags, size); - } + return kmem_cache_alloc_trace( + kmalloc_caches[kmalloc_type(flags)][index], + flags, size); #endif } return __kmalloc(size, flags); @@ -542,13 +561,14 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && - size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) { + size <= KMALLOC_MAX_CACHE_SIZE) { unsigned int i = kmalloc_index(size); if (!i) return ZERO_SIZE_PTR; - return kmem_cache_alloc_node_trace(kmalloc_caches[i], + return kmem_cache_alloc_node_trace( + kmalloc_caches[kmalloc_type(flags)][i], flags, node, size); } #endif -- cgit v1.2.3 From 1291523f2c1d631fea34102fd241fb54a4e8f7a0 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:38 -0700 Subject: mm, slab/slub: introduce kmalloc-reclaimable caches Kmem caches can be created with a SLAB_RECLAIM_ACCOUNT flag, which indicates they contain objects which can be reclaimed under memory pressure (typically through a shrinker). This makes the slab pages accounted as NR_SLAB_RECLAIMABLE in vmstat, which is reflected also the MemAvailable meminfo counter and in overcommit decisions. The slab pages are also allocated with __GFP_RECLAIMABLE, which is good for anti-fragmentation through grouping pages by mobility. The generic kmalloc-X caches are created without this flag, but sometimes are used also for objects that can be reclaimed, which due to varying size cannot have a dedicated kmem cache with SLAB_RECLAIM_ACCOUNT flag. A prominent example are dcache external names, which prompted the creation of a new, manually managed vmstat counter NR_INDIRECTLY_RECLAIMABLE_BYTES in commit f1782c9bc547 ("dcache: account external names as indirectly reclaimable memory"). To better handle this and any other similar cases, this patch introduces SLAB_RECLAIM_ACCOUNT variants of kmalloc caches, named kmalloc-rcl-X. They are used whenever the kmalloc() call passes __GFP_RECLAIMABLE among gfp flags. They are added to the kmalloc_caches array as a new type. Allocations with both __GFP_DMA and __GFP_RECLAIMABLE will use a dma type cache. This change only applies to SLAB and SLUB, not SLOB. This is fine, since SLOB's target are tiny system and this patch does add some overhead of kmem management objects. Link: http://lkml.kernel.org/r/20180731090649.16028-3-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Laura Abbott Cc: Matthew Wilcox Cc: Michal Hocko Cc: Sumit Semwal Cc: Vijayanand Jitta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 2a7137043e91..918f374e7156 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -295,8 +295,13 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) +/* + * Whenever changing this, take care of that kmalloc_type() and + * create_kmalloc_caches() still work as intended. + */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, + KMALLOC_RECLAIM, #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif @@ -310,12 +315,21 @@ kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) { int is_dma = 0; + int type_dma = 0; + int is_reclaimable; #ifdef CONFIG_ZONE_DMA is_dma = !!(flags & __GFP_DMA); + type_dma = is_dma * KMALLOC_DMA; #endif - return is_dma; + is_reclaimable = !!(flags & __GFP_RECLAIMABLE); + + /* + * If an allocation is both __GFP_DMA and __GFP_RECLAIMABLE, return + * KMALLOC_DMA and effectively ignore __GFP_RECLAIMABLE + */ + return type_dma + (is_reclaimable & !is_dma) * KMALLOC_RECLAIM; } /* -- cgit v1.2.3 From b29940c1abd7a4c3abeb926df0a5ec84d6902d47 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:46 -0700 Subject: mm: rename and change semantics of nr_indirectly_reclaimable_bytes The vmstat counter NR_INDIRECTLY_RECLAIMABLE_BYTES was introduced by commit eb59254608bc ("mm: introduce NR_INDIRECTLY_RECLAIMABLE_BYTES") with the goal of accounting objects that can be reclaimed, but cannot be allocated via a SLAB_RECLAIM_ACCOUNT cache. This is now possible via kmalloc() with __GFP_RECLAIMABLE flag, and the dcache external names user is converted. The counter is however still useful for accounting direct page allocations (i.e. not slab) with a shrinker, such as the ION page pool. So keep it, and: - change granularity to pages to be more like other counters; sub-page allocations should be able to use kmalloc - rename the counter to NR_KERNEL_MISC_RECLAIMABLE - expose the counter again in vmstat as "nr_kernel_misc_reclaimable"; we can again remove the check for not printing "hidden" counters Link: http://lkml.kernel.org/r/20180731090649.16028-5-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: Vijayanand Jitta Cc: Laura Abbott Cc: Sumit Semwal Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d4b0c79d2924..7bbeba21f6a3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -180,7 +180,7 @@ enum node_stat_item { NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ - NR_INDIRECTLY_RECLAIMABLE_BYTES, /* measured in bytes */ + NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_VM_NODE_STAT_ITEMS }; -- cgit v1.2.3 From 1899ad18c6072d689896badafb81267b0a1092a4 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:04 -0700 Subject: mm: workingset: tell cache transitions from workingset thrashing Refaults happen during transitions between workingsets as well as in-place thrashing. Knowing the difference between the two has a range of applications, including measuring the impact of memory shortage on the system performance, as well as the ability to smarter balance pressure between the filesystem cache and the swap-backed workingset. During workingset transitions, inactive cache refaults and pushes out established active cache. When that active cache isn't stale, however, and also ends up refaulting, that's bonafide thrashing. Introduce a new page flag that tells on eviction whether the page has been active or not in its lifetime. This bit is then stored in the shadow entry, to classify refaults as transitioning or thrashing. How many page->flags does this leave us with on 32-bit? 20 bits are always page flags 21 if you have an MMU 23 with the zone bits for DMA, Normal, HighMem, Movable 29 with the sparsemem section bits 30 if PAE is enabled 31 with this patch. So on 32-bit PAE, that leaves 1 bit for distinguishing two NUMA nodes. If that's not enough, the system can switch to discontigmem and re-gain the 6 or 7 sparsemem section bits. Link: http://lkml.kernel.org/r/20180828172258.3185-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/linux/page-flags.h | 5 ++++- include/linux/swap.h | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7bbeba21f6a3..ba51d5bf7af1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -163,6 +163,7 @@ enum node_stat_item { NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, + WORKINGSET_RESTORE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 74bee8cecf4c..4d99504f6496 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -69,13 +69,14 @@ */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ - PG_error, PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_active, + PG_workingset, PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ + PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, @@ -280,6 +281,8 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) +PAGEFLAG(Workingset, workingset, PF_HEAD) + TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 8e2c11e692ba..b93740d72e78 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -296,7 +296,7 @@ struct vma_swap_readahead { /* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); -bool workingset_refault(void *shadow); +void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); /* Do not use directly, use workingset_lookup_update */ -- cgit v1.2.3 From b1d29ba82cf2bc784f4c963ddd6a2cf29e229b33 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:08 -0700 Subject: delayacct: track delays from thrashing cache pages Delay accounting already measures the time a task spends in direct reclaim and waiting for swapin, but in low memory situations tasks spend can spend a significant amount of their time waiting on thrashing page cache. This isn't tracked right now. To know the full impact of memory contention on an individual task, measure the delay when waiting for a recently evicted active cache page to read back into memory. Also update tools/accounting/getdelays.c: [hannes@computer accounting]$ sudo ./getdelays -d -p 1 print delayacct stats ON PID 1 CPU count real total virtual total delay total delay average 50318 745000000 847346785 400533713 0.008ms IO count delay total delay average 435 122601218 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 19 12621439 0ms Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 31c865d1842e..577d1b25fccd 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -57,7 +57,12 @@ struct task_delay_info { u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ + + u64 thrashing_start; + u64 thrashing_delay; /* wait for thrashing page */ + u32 freepages_count; /* total count of memory reclaim */ + u32 thrashing_count; /* total count of thrash waits */ }; #endif @@ -76,6 +81,8 @@ extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); +extern void __delayacct_thrashing_start(void); +extern void __delayacct_thrashing_end(void); static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { @@ -156,6 +163,18 @@ static inline void delayacct_freepages_end(void) __delayacct_freepages_end(); } +static inline void delayacct_thrashing_start(void) +{ + if (current->delays) + __delayacct_thrashing_start(); +} + +static inline void delayacct_thrashing_end(void) +{ + if (current->delays) + __delayacct_thrashing_end(); +} + #else static inline void delayacct_set_flag(int flag) {} @@ -182,6 +201,10 @@ static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} +static inline void delayacct_thrashing_start(void) +{} +static inline void delayacct_thrashing_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ -- cgit v1.2.3 From 8508cf3ffad4defa202b303e5b6379efc4cd9054 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:11 -0700 Subject: sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD There are several definitions of those functions/macros in places that mess with fixed-point load averages. Provide an official version. [akpm@linux-foundation.org: fix missed conversion in block/blk-iolatency.c] Link: http://lkml.kernel.org/r/20180828172258.3185-5-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Suren Baghdasaryan Tested-by: Daniel Drake Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/loadavg.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index 80bc84ba5d2a..cc9cc62bb1f8 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -22,10 +22,23 @@ extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift); #define EXP_5 2014 /* 1/exp(5sec/5min) */ #define EXP_15 2037 /* 1/exp(5sec/15min) */ -#define CALC_LOAD(load,exp,n) \ - load *= exp; \ - load += n*(FIXED_1-exp); \ - load >>= FSHIFT; +/* + * a1 = a0 * e + a * (1 - e) + */ +static inline unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + unsigned long newload; + + newload = load * exp + active * (FIXED_1 - exp); + if (active >= load) + newload += FIXED_1-1; + + return newload / FIXED_1; +} + +#define LOAD_INT(x) ((x) >> FSHIFT) +#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) extern void calc_global_load(unsigned long ticks); -- cgit v1.2.3 From 5c54f5b9edb1aa2eabbb1091c458f1b6776a1896 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:16 -0700 Subject: sched: loadavg: make calc_load_n() public It's going to be used in a later patch. Keep the churn separate. Link: http://lkml.kernel.org/r/20180828172258.3185-6-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Suren Baghdasaryan Tested-by: Daniel Drake Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/loadavg.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index cc9cc62bb1f8..4859bea47a7b 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -37,6 +37,9 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) return newload / FIXED_1; } +extern unsigned long calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n); + #define LOAD_INT(x) ((x) >> FSHIFT) #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) -- cgit v1.2.3 From eb414681d5a07d28d2ff90dc05f69ec6b232ebd2 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:27 -0700 Subject: psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/psi.h | 28 +++++++++++++++ include/linux/psi_types.h | 92 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 10 ++++++ 3 files changed, 130 insertions(+) create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h (limited to 'include/linux') diff --git a/include/linux/psi.h b/include/linux/psi.h new file mode 100644 index 000000000000..b0daf050de58 --- /dev/null +++ b/include/linux/psi.h @@ -0,0 +1,28 @@ +#ifndef _LINUX_PSI_H +#define _LINUX_PSI_H + +#include +#include + +#ifdef CONFIG_PSI + +extern bool psi_disabled; + +void psi_init(void); + +void psi_task_change(struct task_struct *task, int clear, int set); + +void psi_memstall_tick(struct task_struct *task, int cpu); +void psi_memstall_enter(unsigned long *flags); +void psi_memstall_leave(unsigned long *flags); + +#else /* CONFIG_PSI */ + +static inline void psi_init(void) {} + +static inline void psi_memstall_enter(unsigned long *flags) {} +static inline void psi_memstall_leave(unsigned long *flags) {} + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_H */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h new file mode 100644 index 000000000000..2cf422db5d18 --- /dev/null +++ b/include/linux/psi_types.h @@ -0,0 +1,92 @@ +#ifndef _LINUX_PSI_TYPES_H +#define _LINUX_PSI_TYPES_H + +#include +#include + +#ifdef CONFIG_PSI + +/* Tracked task states */ +enum psi_task_count { + NR_IOWAIT, + NR_MEMSTALL, + NR_RUNNING, + NR_PSI_TASK_COUNTS, +}; + +/* Task state bitmasks */ +#define TSK_IOWAIT (1 << NR_IOWAIT) +#define TSK_MEMSTALL (1 << NR_MEMSTALL) +#define TSK_RUNNING (1 << NR_RUNNING) + +/* Resources that workloads could be stalled on */ +enum psi_res { + PSI_IO, + PSI_MEM, + PSI_CPU, + NR_PSI_RESOURCES, +}; + +/* + * Pressure states for each resource: + * + * SOME: Stalled tasks & working tasks + * FULL: Stalled tasks & no working tasks + */ +enum psi_states { + PSI_IO_SOME, + PSI_IO_FULL, + PSI_MEM_SOME, + PSI_MEM_FULL, + PSI_CPU_SOME, + /* Only per-CPU, to weigh the CPU in the global average: */ + PSI_NONIDLE, + NR_PSI_STATES, +}; + +struct psi_group_cpu { + /* 1st cacheline updated by the scheduler */ + + /* Aggregator needs to know of concurrent changes */ + seqcount_t seq ____cacheline_aligned_in_smp; + + /* States of the tasks belonging to this group */ + unsigned int tasks[NR_PSI_TASK_COUNTS]; + + /* Period time sampling buckets for each state of interest (ns) */ + u32 times[NR_PSI_STATES]; + + /* Time of last task change in this group (rq_clock) */ + u64 state_start; + + /* 2nd cacheline updated by the aggregator */ + + /* Delta detection against the sampling buckets */ + u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp; +}; + +struct psi_group { + /* Protects data updated during an aggregation */ + struct mutex stat_lock; + + /* Per-cpu task state & time tracking */ + struct psi_group_cpu __percpu *pcpu; + + /* Periodic aggregation state */ + u64 total_prev[NR_PSI_STATES - 1]; + u64 last_update; + u64 next_update; + struct delayed_work clock_work; + + /* Total stall times and sampled pressure averages */ + u64 total[NR_PSI_STATES - 1]; + unsigned long avg[NR_PSI_STATES - 1][3]; +}; + +#else /* CONFIG_PSI */ + +struct psi_group { }; + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_TYPES_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index adfb3f9a7597..b8fcc6b3080c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -706,6 +707,10 @@ struct task_struct { unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_remote_wakeup:1; +#ifdef CONFIG_PSI + unsigned sched_psi_wake_requeue:1; +#endif + /* Force alignment to the next boundary: */ unsigned :0; @@ -965,6 +970,10 @@ struct task_struct { kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; +#ifdef CONFIG_PSI + /* Pressure stall state */ + unsigned int psi_flags; +#endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; @@ -1391,6 +1400,7 @@ extern struct pid *cad_pid; #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +#define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ -- cgit v1.2.3 From 2ce7135adc9ad081aa3c49744144376ac74fea60 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:31 -0700 Subject: psi: cgroup support On a system that executes multiple cgrouped jobs and independent workloads, we don't just care about the health of the overall system, but also that of individual jobs, so that we can ensure individual job health, fairness between jobs, or prioritize some jobs over others. This patch implements pressure stall tracking for cgroups. In kernels with CONFIG_PSI=y, cgroup2 groups will have cpu.pressure, memory.pressure, and io.pressure files that track aggregate pressure stall times for only the tasks inside the cgroup. Link: http://lkml.kernel.org/r/20180828172258.3185-10-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Tejun Heo Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup-defs.h | 4 ++++ include/linux/cgroup.h | 15 +++++++++++++++ include/linux/psi.h | 25 +++++++++++++++++++++++++ 3 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 22254c1fe1c5..5e1694fe035b 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -20,6 +20,7 @@ #include #include #include +#include #ifdef CONFIG_CGROUPS @@ -436,6 +437,9 @@ struct cgroup { /* used to schedule release agent */ struct work_struct release_agent_work; + /* used to track pressure stalls */ + struct psi_group psi; + /* used to store eBPF programs */ struct cgroup_bpf bpf; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b622d6608605..9968332cceed 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -650,6 +650,11 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return &cgrp->psi; +} + static inline void cgroup_init_kthreadd(void) { /* @@ -703,6 +708,16 @@ static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) return NULL; } +static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) +{ + return NULL; +} + +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return NULL; +} + static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { diff --git a/include/linux/psi.h b/include/linux/psi.h index b0daf050de58..8e0725aac0aa 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -4,6 +4,9 @@ #include #include +struct seq_file; +struct css_set; + #ifdef CONFIG_PSI extern bool psi_disabled; @@ -16,6 +19,14 @@ void psi_memstall_tick(struct task_struct *task, int cpu); void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); +int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgrp); +void psi_cgroup_free(struct cgroup *cgrp); +void cgroup_move_task(struct task_struct *p, struct css_set *to); +#endif + #else /* CONFIG_PSI */ static inline void psi_init(void) {} @@ -23,6 +34,20 @@ static inline void psi_init(void) {} static inline void psi_memstall_enter(unsigned long *flags) {} static inline void psi_memstall_leave(unsigned long *flags) {} +#ifdef CONFIG_CGROUPS +static inline int psi_cgroup_alloc(struct cgroup *cgrp) +{ + return 0; +} +static inline void psi_cgroup_free(struct cgroup *cgrp) +{ +} +static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) +{ + rcu_assign_pointer(p->cgroups, to); +} +#endif + #endif /* CONFIG_PSI */ #endif /* _LINUX_PSI_H */ -- cgit v1.2.3 From 68d48e6a2df575b935edd420396c3cb8b6aa6ad3 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:39 -0700 Subject: mm: workingset: add vmstat counter for shadow nodes Make it easier to catch bugs in the shadow node shrinker by adding a counter for the shadow nodes in circulation. [akpm@linux-foundation.org: assert that irqs are disabled, for __inc_lruvec_page_state()] [akpm@linux-foundation.org: s/WARN_ON_ONCE/VM_WARN_ON_ONCE/, per Johannes] Link: http://lkml.kernel.org/r/20181009184732.762-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ba51d5bf7af1..9f0caccd5833 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -161,6 +161,7 @@ enum node_stat_item { NR_SLAB_UNRECLAIMABLE, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ + WORKINGSET_NODES, WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, WORKINGSET_RESTORE, -- cgit v1.2.3 From 85cfb245060e45640fa3447f8b0bad5e8bd3bdaf Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 26 Oct 2018 15:07:41 -0700 Subject: memcg: remove memcg_kmem_skip_account The flag memcg_kmem_skip_account was added during the era of opt-out kmem accounting. There is no need for such flag in the opt-in world as there aren't any __GFP_ACCOUNT allocations within memcg_create_cache_enqueue(). Link: http://lkml.kernel.org/r/20180919004501.178023-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b8fcc6b3080c..8f8a5418b627 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -724,9 +724,6 @@ struct task_struct { #endif #ifdef CONFIG_MEMCG unsigned in_user_fault:1; -#ifdef CONFIG_MEMCG_KMEM - unsigned memcg_kmem_skip_account:1; -#endif #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; -- cgit v1.2.3 From f682a97a00591def7cefbb5003dc04045028e405 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:45 -0700 Subject: mm: provide kernel parameter to allow disabling page init poisoning Patch series "Address issues slowing persistent memory initialization", v5. The main thing this patch set achieves is that it allows us to initialize each node worth of persistent memory independently. As a result we reduce page init time by about 2 minutes because instead of taking 30 to 40 seconds per node and going through each node one at a time, we process all 4 nodes in parallel in the case of a 12TB persistent memory setup spread evenly over 4 nodes. This patch (of 3): On systems with a large amount of memory it can take a significant amount of time to initialize all of the page structs with the PAGE_POISON_PATTERN value. I have seen it take over 2 minutes to initialize a system with over 12TB of RAM. In order to work around the issue I had to disable CONFIG_DEBUG_VM and then the boot time returned to something much more reasonable as the arch_add_memory call completed in milliseconds versus seconds. However in doing that I had to disable all of the other VM debugging on the system. In order to work around a kernel that might have CONFIG_DEBUG_VM enabled on a system that has a large amount of memory I have added a new kernel parameter named "vm_debug" that can be set to "-" in order to disable it. Link: http://lkml.kernel.org/r/20180925201921.3576.84239.stgit@localhost.localdomain Reviewed-by: Pavel Tatashin Signed-off-by: Alexander Duyck Cc: Dave Hansen Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4d99504f6496..934f91ef3f54 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -163,6 +163,14 @@ static inline int PagePoisoned(const struct page *page) return page->flags == PAGE_POISON_PATTERN; } +#ifdef CONFIG_DEBUG_VM +void page_init_poison(struct page *page, size_t size); +#else +static inline void page_init_poison(struct page *page, size_t size) +{ +} +#endif + /* * Page flags policies wrt compound pages * -- cgit v1.2.3 From d483da5bc78b86fe4200d2947f193a745f711713 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:48 -0700 Subject: mm: create non-atomic version of SetPageReserved for init use It doesn't make much sense to use the atomic SetPageReserved at init time when we are using memset to clear the memory and manipulating the page flags via simple "&=" and "|=" operations in __init_single_page. This patch adds a non-atomic version __SetPageReserved that can be used during page init and shows about a 10% improvement in initialization times on the systems I have available for testing. On those systems I saw initialization times drop from around 35 seconds to around 32 seconds to initialize a 3TB block of persistent memory. I believe the main advantage of this is that it allows for more compiler optimization as the __set_bit operation can be reordered whereas the atomic version cannot. I tried adding a bit of documentation based on f1dd2cd13c4 ("mm, memory_hotplug: do not associate hotadded memory to zones until online"). Ideally the reserved flag should be set earlier since there is a brief window where the page is initialization via __init_single_page and we have not set the PG_Reserved flag. I'm leaving that for a future patch set as that will require a more significant refactor. Link: http://lkml.kernel.org/r/20180925202018.3576.11607.stgit@localhost.localdomain Signed-off-by: Alexander Duyck Reviewed-by: Pavel Tatashin Acked-by: Michal Hocko Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 934f91ef3f54..50ce1bddaf56 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -303,6 +303,7 @@ PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) + __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) -- cgit v1.2.3 From 966cf44f637e6aeea7e3d01ba004bf8b5beac78f Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:52 -0700 Subject: mm: defer ZONE_DEVICE page initialization to the point where we init pgmap The ZONE_DEVICE pages were being initialized in two locations. One was with the memory_hotplug lock held and another was outside of that lock. The problem with this is that it was nearly doubling the memory initialization time. Instead of doing this twice, once while holding a global lock and once without, I am opting to defer the initialization to the one outside of the lock. This allows us to avoid serializing the overhead for memory init and we can instead focus on per-node init times. One issue I encountered is that devm_memremap_pages and hmm_devmmem_pages_create were initializing only the pgmap field the same way. One wasn't initializing hmm_data, and the other was initializing it to a poison value. Since this is something that is exposed to the driver in the case of hmm I am opting for a third option and just initializing hmm_data to 0 since this is going to be exposed to unknown third party drivers. [alexander.h.duyck@linux.intel.com: fix reference count for pgmap in devm_memremap_pages] Link: http://lkml.kernel.org/r/20181008233404.1909.37302.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/20180925202053.3576.66039.stgit@localhost.localdomain Signed-off-by: Alexander Duyck Reviewed-by: Pavel Tatashin Tested-by: Dan Williams Cc: Dave Hansen Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 737279bb479c..33228a49d7d2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -848,6 +848,8 @@ static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } +extern void memmap_init_zone_device(struct zone *, unsigned long, + unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { -- cgit v1.2.3 From 85a06835f6f1ba79f0f00838ccd5ad840dd1eafb Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:08:50 -0700 Subject: mm: mremap: downgrade mmap_sem to read when shrinking Other than munmap, mremap might be used to shrink memory mapping too. So, it may hold write mmap_sem for long time when shrinking large mapping, as what commit ("mm: mmap: zap pages with read mmap_sem in munmap") described. The mremap() will not manipulate vmas anymore after __do_munmap() call for the mapping shrink use case, so it is safe to downgrade to read mmap_sem. So, the same optimization, which downgrades mmap_sem to read for zapping pages, is also feasible and reasonable to this case. The period of holding exclusive mmap_sem for shrinking large mapping would be reduced significantly with this optimization. MREMAP_FIXED and MREMAP_MAYMOVE are more complicated to adopt this optimization since they need manipulate vmas after do_munmap(), downgrading mmap_sem may create race window. Simple mapping shrink is the low hanging fruit, and it may cover the most cases of unmap with munmap together. [akpm@linux-foundation.org: tweak comment] [yang.shi@linux.alibaba.com: fix unsigned compare against 0 issue] Link: http://lkml.kernel.org/r/1538687672-17795-2-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1538067582-60038-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Michal Hocko Cc: Matthew Wilcox Cc: Laurent Dufour Cc: Colin Ian King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 33228a49d7d2..a023c5ce71fa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2306,6 +2306,8 @@ extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); +extern int __do_munmap(struct mm_struct *, unsigned long, size_t, + struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); -- cgit v1.2.3 From cc4b8c794f476076c9ce19f43eb4d98dc4b5e155 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:08:57 -0700 Subject: mm: dax: add comment for PFN_SPECIAL The comment for PFN_SPECIAL is missed in pfn_t.h. Add comment to get consistent with other pfn flags. Link: http://lkml.kernel.org/r/1538086549-100536-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Suggested-by: Dan Williams Reviewed-by: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pfn_t.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 673546ba7342..7bb77850c65a 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -9,6 +9,8 @@ * PFN_SG_LAST - pfn references a page and is the last scatterlist entry * PFN_DEV - pfn is not covered by system memmap by default * PFN_MAP - pfn has a dynamic page mapping established by a device driver + * PFN_SPECIAL - for CONFIG_FS_DAX_LIMITED builds to allow XIP, but not + * get_user_pages */ #define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1)) -- cgit v1.2.3 From 1c2d479a119b84feacbe4de782016f1bf1ad16dc Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 26 Oct 2018 15:09:28 -0700 Subject: mm/memcontrol.c: convert mem_cgroup_id::ref to refcount_t type This will allow to use generic refcount_t interfaces to check counters overflow instead of currently existing VM_BUG_ON(). The only difference after the patch is VM_BUG_ON() may cause BUG(), while refcount_t fires with WARN(). But this seems not to be significant here, since such the problems are usually caught by syzbot with panic-on-warn enabled. Link: http://lkml.kernel.org/r/153910718919.7006.13400779039257185427.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Reviewed-by: Andrew Morton Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Andrea Parri Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 4399cc3f00e4..7ab2120155a4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -78,7 +78,7 @@ struct mem_cgroup_reclaim_cookie { struct mem_cgroup_id { int id; - atomic_t ref; + refcount_t ref; }; /* -- cgit v1.2.3 From 907ec5fca3dc38d37737de826f06f25b063aa08e Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 26 Oct 2018 15:10:15 -0700 Subject: mm: zero remaining unavailable struct pages Patch series "mm: Fix for movable_node boot option", v3. This patch series contains a fix for the movable_node boot option issue which was introduced by commit 124049decbb1 ("x86/e820: put !E820_TYPE_RAM regions into memblock.reserved"). The commit breaks the option because it changed the memory gap range to reserved memblock. So, the node is marked as Normal zone even if the SRAT has Hot pluggable affinity. First and second patch fix the original issue which the commit tried to fix, then revert the commit. This patch (of 3): There is a kernel panic that is triggered when reading /proc/kpageflags on the kernel booted with kernel parameter 'memmap=nn[KMG]!ss[KMG]': BUG: unable to handle kernel paging request at fffffffffffffffe PGD 9b20e067 P4D 9b20e067 PUD 9b210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 1728 Comm: page-types Not tainted 4.17.0-rc6-mm1-v4.17-rc6-180605-0816-00236-g2dfb086ef02c+ #160 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.fc28 04/01/2014 RIP: 0010:stable_page_flags+0x27/0x3c0 Code: 00 00 00 0f 1f 44 00 00 48 85 ff 0f 84 a0 03 00 00 41 54 55 49 89 fc 53 48 8b 57 08 48 8b 2f 48 8d 42 ff 83 e2 01 48 0f 44 c7 <48> 8b 00 f6 c4 01 0f 84 10 03 00 00 31 db 49 8b 54 24 08 4c 89 e7 RSP: 0018:ffffbbd44111fde0 EFLAGS: 00010202 RAX: fffffffffffffffe RBX: 00007fffffffeff9 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000202 RDI: ffffed1182fff5c0 RBP: ffffffffffffffff R08: 0000000000000001 R09: 0000000000000001 R10: ffffbbd44111fed8 R11: 0000000000000000 R12: ffffed1182fff5c0 R13: 00000000000bffd7 R14: 0000000002fff5c0 R15: ffffbbd44111ff10 FS: 00007efc4335a500(0000) GS:ffff93a5bfc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffffffffffffe CR3: 00000000b2a58000 CR4: 00000000001406e0 Call Trace: kpageflags_read+0xc7/0x120 proc_reg_read+0x3c/0x60 __vfs_read+0x36/0x170 vfs_read+0x89/0x130 ksys_pread64+0x71/0x90 do_syscall_64+0x5b/0x160 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7efc42e75e23 Code: 09 00 ba 9f 01 00 00 e8 ab 81 f4 ff 66 2e 0f 1f 84 00 00 00 00 00 90 83 3d 29 0a 2d 00 00 75 13 49 89 ca b8 11 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 db d3 01 00 48 89 04 24 According to kernel bisection, this problem became visible due to commit f7f99100d8d9 which changes how struct pages are initialized. Memblock layout affects the pfn ranges covered by node/zone. Consider that we have a VM with 2 NUMA nodes and each node has 4GB memory, and the default (no memmap= given) memblock layout is like below: MEMBLOCK configuration: memory size = 0x00000001fff75c00 reserved size = 0x000000000300c000 memory.cnt = 0x4 memory[0x0] [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0 memory[0x1] [0x0000000000100000-0x00000000bffd6fff], 0x00000000bfed7000 bytes on node 0 flags: 0x0 memory[0x2] [0x0000000100000000-0x000000013fffffff], 0x0000000040000000 bytes on node 0 flags: 0x0 memory[0x3] [0x0000000140000000-0x000000023fffffff], 0x0000000100000000 bytes on node 1 flags: 0x0 ... If you give memmap=1G!4G (so it just covers memory[0x2]), the range [0x100000000-0x13fffffff] is gone: MEMBLOCK configuration: memory size = 0x00000001bff75c00 reserved size = 0x000000000300c000 memory.cnt = 0x3 memory[0x0] [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0 memory[0x1] [0x0000000000100000-0x00000000bffd6fff], 0x00000000bfed7000 bytes on node 0 flags: 0x0 memory[0x2] [0x0000000140000000-0x000000023fffffff], 0x0000000100000000 bytes on node 1 flags: 0x0 ... This causes shrinking node 0's pfn range because it is calculated by the address range of memblock.memory. So some of struct pages in the gap range are left uninitialized. We have a function zero_resv_unavail() which does zeroing the struct pages outside memblock.memory, but currently it covers only the reserved unavailable range (i.e. memblock.memory && !memblock.reserved). This patch extends it to cover all unavailable range, which fixes the reported issue. Link: http://lkml.kernel.org/r/20181002143821.5112-2-msys.mizuma@gmail.com Fixes: f7f99100d8d9 ("mm: stop zeroing memory during allocation in vmemmap") Signed-off-by: Naoya Horiguchi Signed-off-by-by: Masayoshi Mizuma Tested-by: Oscar Salvador Tested-by: Masayoshi Mizuma Reviewed-by: Pavel Tatashin Cc: Ingo Molnar Cc: Michal Hocko Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 516920549378..2acdd046df2d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -265,21 +265,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ nid, flags, p_start, p_end, p_nid) -/** - * for_each_resv_unavail_range - iterate through reserved and unavailable memory - * @i: u64 used as loop variable - * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL - * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL - * - * Walks over unavailable but reserved (reserved && !memory) areas of memblock. - * Available as soon as memblock is initialized. - * Note: because this memory does not belong to any physical node, flags and - * nid arguments do not make sense and thus not exported as arguments. - */ -#define for_each_resv_unavail_range(i, p_start, p_end) \ - for_each_mem_range(i, &memblock.reserved, &memblock.memory, \ - NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL) - static inline void memblock_set_region_flags(struct memblock_region *r, enum memblock_flags flags) { -- cgit v1.2.3 From df06b37ffe5a442503b7095b77b0a970df515459 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 26 Oct 2018 15:10:28 -0700 Subject: mm/gup: cache dev_pagemap while pinning pages Getting pages from ZONE_DEVICE memory needs to check the backing device's live-ness, which is tracked in the device's dev_pagemap metadata. This metadata is stored in a radix tree and looking it up adds measurable software overhead. This patch avoids repeating this relatively costly operation when dev_pagemap is used by caching the last dev_pagemap while getting user pages. The gup_benchmark kernel self test reports this reduces time to get user pages to as low as 1/3 of the previous time. Link: http://lkml.kernel.org/r/20181012173040.15669-1-keith.busch@intel.com Signed-off-by: Keith Busch Reviewed-by: Dan Williams Acked-by: Kirill A. Shutemov Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 8 ++++---- include/linux/mm.h | 12 ++---------- 2 files changed, 6 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index fdcb45999b26..4663ee96cf59 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -213,9 +213,9 @@ static inline int hpage_nr_pages(struct page *page) } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, int flags); + pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags); + pud_t *pud, int flags, struct dev_pagemap **pgmap); extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); @@ -344,13 +344,13 @@ static inline void mm_put_huge_zero_page(struct mm_struct *mm) } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmd, int flags) + unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, - unsigned long addr, pud_t *pud, int flags) + unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) { return NULL; } diff --git a/include/linux/mm.h b/include/linux/mm.h index a023c5ce71fa..1e52b8fd1685 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2536,16 +2536,8 @@ static inline vm_fault_t vmf_error(int err) return VM_FAULT_SIGBUS; } -struct page *follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int foll_flags, - unsigned int *page_mask); - -static inline struct page *follow_page(struct vm_area_struct *vma, - unsigned long address, unsigned int foll_flags) -{ - unsigned int unused_page_mask; - return follow_page_mask(vma, address, foll_flags, &unused_page_mask); -} +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int foll_flags); #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ -- cgit v1.2.3 From bc4ae27d817a4e92071ef67cb6368120cfabe7ec Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 26 Oct 2018 15:10:51 -0700 Subject: mm: split SWP_FILE into SWP_ACTIVATED and SWP_FS The SWP_FILE flag serves two purposes: to make swap_{read,write}page() go through the filesystem, and to make swapoff() call ->swap_deactivate(). For Btrfs, we want the latter but not the former, so split this flag into two. This makes us always call ->swap_deactivate() if ->swap_activate() succeeded, not just if it didn't add any swap extents itself. This also resolves the issue of the very misleading name of SWP_FILE, which is only used for swap files over NFS. Link: http://lkml.kernel.org/r/6d63d8668c4287a4f6d203d65696e96f80abdfc7.1536704650.git.osandov@fb.com Signed-off-by: Omar Sandoval Reviewed-by: Nikolay Borisov Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: David Sterba Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index b93740d72e78..38195f5c96b1 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -167,13 +167,14 @@ enum { SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ - SWP_FILE = (1 << 7), /* set after swap_activate success */ - SWP_AREA_DISCARD = (1 << 8), /* single-time swap area discards */ - SWP_PAGE_DISCARD = (1 << 9), /* freed swap page-cluster discards */ - SWP_STABLE_WRITES = (1 << 10), /* no overwrite PG_writeback pages */ - SWP_SYNCHRONOUS_IO = (1 << 11), /* synchronous IO is efficient */ + SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ + SWP_FS = (1 << 8), /* swap file goes through fs */ + SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ + SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ + SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ + SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ - SWP_SCANNING = (1 << 12), /* refcount in scan_swap_map */ + SWP_SCANNING = (1 << 13), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL -- cgit v1.2.3