From 156654f491dd8d52687a5fbe1637f472a52ce75b Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Fri, 28 Feb 2014 07:23:11 +0100 Subject: sched/numa: Move task_numa_free() to __put_task_struct() Bad idea on -rt: [ 908.026136] [] rt_spin_lock_slowlock+0xaa/0x2c0 [ 908.026145] [] task_numa_free+0x31/0x130 [ 908.026151] [] finish_task_switch+0xce/0x100 [ 908.026156] [] thread_return+0x48/0x4ae [ 908.026160] [] schedule+0x25/0xa0 [ 908.026163] [] rt_spin_lock_slowlock+0xd5/0x2c0 [ 908.026170] [] get_signal_to_deliver+0xaf/0x680 [ 908.026175] [] do_signal+0x3d/0x5b0 [ 908.026179] [] do_notify_resume+0x90/0xe0 [ 908.026186] [] int_signal+0x12/0x17 [ 908.026193] [<00007ff2a388b1d0>] 0x7ff2a388b1cf and since upstream does not mind where we do this, be a bit nicer ... Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra Cc: Mel Gorman Cc: Linus Torvalds Cc: Andrew Morton Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1393568591.6018.27.camel@marge.simpson.net Signed-off-by: Ingo Molnar --- kernel/fork.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index a17621c6cd4..332688e5e7b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -237,6 +237,7 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(atomic_read(&tsk->usage)); WARN_ON(tsk == current); + task_numa_free(tsk); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); -- cgit v1.2.3-70-g09d2 From e8604cb43690b781f9a7ad4a770f3e10259fe939 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 28 Mar 2014 15:18:27 +0800 Subject: cgroup: fix spurious lockdep warning in cgroup_exit() cgroup_exit() is called in fork and exit path. If it's called in the failure path during fork, PF_EXITING isn't set, and then lockdep will complain. Fix this by removing cgroup_exit() in that failure path. cgroup_fork() does nothing that needs cleanup. Reported-by: Sasha Levin Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- kernel/cgroup.c | 3 +-- kernel/fork.c | 5 ++--- 2 files changed, 3 insertions(+), 5 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index e378cb2fac5..60fd6f1f6d4 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4431,8 +4431,7 @@ void cgroup_post_fork(struct task_struct *child) * notify_on_release(), then leave the task attached to the root cgroup in * each hierarchy for the remainder of its exit. No need to bother with * init_css_set refcnting. init_css_set never goes away and we can't race - * with migration path - either PF_EXITING is visible to migration path or - * @tsk never got on the tasklist. + * with migration path - PF_EXITING is visible to migration path. */ void cgroup_exit(struct task_struct *tsk, int run_callbacks) { diff --git a/kernel/fork.c b/kernel/fork.c index a17621c6cd4..8852b3463ab 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1271,7 +1271,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; - goto bad_fork_cleanup_cgroup; + goto bad_fork_cleanup_threadgroup_lock; } mpol_fix_fork_child_flag(p); #endif @@ -1524,11 +1524,10 @@ bad_fork_cleanup_policy: perf_event_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); -bad_fork_cleanup_cgroup: +bad_fork_cleanup_threadgroup_lock: #endif if (clone_flags & CLONE_THREAD) threadgroup_change_end(current); - cgroup_exit(p, 0); delayacct_tsk_free(p); module_put(task_thread_info(p)->exec_domain->module); bad_fork_cleanup_count: -- cgit v1.2.3-70-g09d2 From a0715cc22601e8830ace98366c0c2bd8da52af52 Mon Sep 17 00:00:00 2001 From: Alex Thorlton Date: Mon, 7 Apr 2014 15:37:10 -0700 Subject: mm, thp: add VM_INIT_DEF_MASK and PRCTL_THP_DISABLE Add VM_INIT_DEF_MASK, to allow us to set the default flags for VMs. It also adds a prctl control which allows us to set the THP disable bit in mm->def_flags so that VMs will pick up the setting as they are created. Signed-off-by: Alex Thorlton Suggested-by: Oleg Nesterov Cc: Gerald Schaefer Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Christian Borntraeger Cc: Paolo Bonzini Cc: "Kirill A. Shutemov" Cc: Mel Gorman Acked-by: Rik van Riel Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Andrea Arcangeli Cc: Oleg Nesterov Cc: "Eric W. Biederman" Cc: Alexander Viro Cc: Johannes Weiner Cc: David Rientjes Cc: Paolo Bonzini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ include/uapi/linux/prctl.h | 3 +++ kernel/fork.c | 11 ++++++++--- kernel/sys.c | 15 +++++++++++++++ 4 files changed, 29 insertions(+), 3 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index 35300f390eb..c270fa68a32 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -177,6 +177,9 @@ extern unsigned int kobjsize(const void *objp); */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) +/* This mask defines which mm->def_flags a process can inherit its parent */ +#define VM_INIT_DEF_MASK VM_NOHUGEPAGE + /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 289760f424a..58afc04c107 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -149,4 +149,7 @@ #define PR_GET_TID_ADDRESS 40 +#define PR_SET_THP_DISABLE 41 +#define PR_GET_THP_DISABLE 42 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/fork.c b/kernel/fork.c index abc45890f0a..e40c0a01d5a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -530,8 +530,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) atomic_set(&mm->mm_count, 1); init_rwsem(&mm->mmap_sem); INIT_LIST_HEAD(&mm->mmlist); - mm->flags = (current->mm) ? - (current->mm->flags & MMF_INIT_MASK) : default_dump_filter; mm->core_state = NULL; atomic_long_set(&mm->nr_ptes, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); @@ -540,8 +538,15 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) mm_init_owner(mm, p); clear_tlb_flush_pending(mm); - if (likely(!mm_alloc_pgd(mm))) { + if (current->mm) { + mm->flags = current->mm->flags & MMF_INIT_MASK; + mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; + } else { + mm->flags = default_dump_filter; mm->def_flags = 0; + } + + if (likely(!mm_alloc_pgd(mm))) { mmu_notifier_mm_init(mm); return mm; } diff --git a/kernel/sys.c b/kernel/sys.c index adaeab6f7a8..fba0f29401e 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1996,6 +1996,21 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, if (arg2 || arg3 || arg4 || arg5) return -EINVAL; return current->no_new_privs ? 1 : 0; + case PR_GET_THP_DISABLE: + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + error = !!(me->mm->def_flags & VM_NOHUGEPAGE); + break; + case PR_SET_THP_DISABLE: + if (arg3 || arg4 || arg5) + return -EINVAL; + down_write(&me->mm->mmap_sem); + if (arg2) + me->mm->def_flags |= VM_NOHUGEPAGE; + else + me->mm->def_flags &= ~VM_NOHUGEPAGE; + up_write(&me->mm->mmap_sem); + break; default: error = -EINVAL; break; -- cgit v1.2.3-70-g09d2 From 615d6e8756c87149f2d4c1b93d471bca002bd849 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Mon, 7 Apr 2014 15:37:25 -0700 Subject: mm: per-thread vma caching This patch is a continuation of efforts trying to optimize find_vma(), avoiding potentially expensive rbtree walks to locate a vma upon faults. The original approach (https://lkml.org/lkml/2013/11/1/410), where the largest vma was also cached, ended up being too specific and random, thus further comparison with other approaches were needed. There are two things to consider when dealing with this, the cache hit rate and the latency of find_vma(). Improving the hit-rate does not necessarily translate in finding the vma any faster, as the overhead of any fancy caching schemes can be too high to consider. We currently cache the last used vma for the whole address space, which provides a nice optimization, reducing the total cycles in find_vma() by up to 250%, for workloads with good locality. On the other hand, this simple scheme is pretty much useless for workloads with poor locality. Analyzing ebizzy runs shows that, no matter how many threads are running, the mmap_cache hit rate is less than 2%, and in many situations below 1%. The proposed approach is to replace this scheme with a small per-thread cache, maximizing hit rates at a very low maintenance cost. Invalidations are performed by simply bumping up a 32-bit sequence number. The only expensive operation is in the rare case of a seq number overflow, where all caches that share the same address space are flushed. Upon a miss, the proposed replacement policy is based on the page number that contains the virtual address in question. Concretely, the following results are seen on an 80 core, 8 socket x86-64 box: 1) System bootup: Most programs are single threaded, so the per-thread scheme does improve ~50% hit rate by just adding a few more slots to the cache. +----------------+----------+------------------+ | caching scheme | hit-rate | cycles (billion) | +----------------+----------+------------------+ | baseline | 50.61% | 19.90 | | patched | 73.45% | 13.58 | +----------------+----------+------------------+ 2) Kernel build: This one is already pretty good with the current approach as we're dealing with good locality. +----------------+----------+------------------+ | caching scheme | hit-rate | cycles (billion) | +----------------+----------+------------------+ | baseline | 75.28% | 11.03 | | patched | 88.09% | 9.31 | +----------------+----------+------------------+ 3) Oracle 11g Data Mining (4k pages): Similar to the kernel build workload. +----------------+----------+------------------+ | caching scheme | hit-rate | cycles (billion) | +----------------+----------+------------------+ | baseline | 70.66% | 17.14 | | patched | 91.15% | 12.57 | +----------------+----------+------------------+ 4) Ebizzy: There's a fair amount of variation from run to run, but this approach always shows nearly perfect hit rates, while baseline is just about non-existent. The amounts of cycles can fluctuate between anywhere from ~60 to ~116 for the baseline scheme, but this approach reduces it considerably. For instance, with 80 threads: +----------------+----------+------------------+ | caching scheme | hit-rate | cycles (billion) | +----------------+----------+------------------+ | baseline | 1.06% | 91.54 | | patched | 99.97% | 14.18 | +----------------+----------+------------------+ [akpm@linux-foundation.org: fix nommu build, per Davidlohr] [akpm@linux-foundation.org: document vmacache_valid() logic] [akpm@linux-foundation.org: attempt to untangle header files] [akpm@linux-foundation.org: add vmacache_find() BUG_ON] [hughd@google.com: add vmacache_valid_mm() (from Oleg)] [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: adjust and enhance comments] Signed-off-by: Davidlohr Bueso Reviewed-by: Rik van Riel Acked-by: Linus Torvalds Reviewed-by: Michel Lespinasse Cc: Oleg Nesterov Tested-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/unicore32/include/asm/mmu_context.h | 4 +- fs/exec.c | 5 +- fs/proc/task_mmu.c | 3 +- include/linux/mm_types.h | 4 +- include/linux/sched.h | 7 ++ include/linux/vmacache.h | 38 +++++++++++ kernel/debug/debug_core.c | 14 +++- kernel/fork.c | 7 +- mm/Makefile | 2 +- mm/mmap.c | 55 ++++++++------- mm/nommu.c | 24 ++++--- mm/vmacache.c | 112 +++++++++++++++++++++++++++++++ 12 files changed, 231 insertions(+), 44 deletions(-) create mode 100644 include/linux/vmacache.h create mode 100644 mm/vmacache.c (limited to 'kernel/fork.c') diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h index fb5e4c658f7..ef470a7a3d0 100644 --- a/arch/unicore32/include/asm/mmu_context.h +++ b/arch/unicore32/include/asm/mmu_context.h @@ -14,6 +14,8 @@ #include #include +#include +#include #include #include @@ -73,7 +75,7 @@ do { \ else \ mm->mmap = NULL; \ rb_erase(&high_vma->vm_rb, &mm->mm_rb); \ - mm->mmap_cache = NULL; \ + vmacache_invalidate(mm); \ mm->map_count--; \ remove_vma(high_vma); \ } \ diff --git a/fs/exec.c b/fs/exec.c index 25dfeba6d55..b60ccf969a8 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -822,7 +823,7 @@ EXPORT_SYMBOL(read_code); static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; - struct mm_struct * old_mm, *active_mm; + struct mm_struct *old_mm, *active_mm; /* Notify parent that we're no longer interested in the old VM */ tsk = current; @@ -848,6 +849,8 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); + tsk->mm->vmacache_seqnum = 0; + vmacache_flush(tsk); task_unlock(tsk); if (old_mm) { up_read(&old_mm->mmap_sem); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index fb52b548080..442177b1119 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1,4 +1,5 @@ #include +#include #include #include #include @@ -152,7 +153,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) /* * We remember last_addr rather than next_addr to hit with - * mmap_cache most of the time. We have zero last_addr at + * vmacache most of the time. We have zero last_addr at * the beginning and also after lseek. We will have -1 last_addr * after the end of the vmas. */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 290901a8c1d..2b58d192ea2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -342,9 +342,9 @@ struct mm_rss_stat { struct kioctx_table; struct mm_struct { - struct vm_area_struct * mmap; /* list of VMAs */ + struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; - struct vm_area_struct * mmap_cache; /* last find_vma result */ + u32 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/sched.h b/include/linux/sched.h index 7cb07fd2668..642477dd814 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -132,6 +132,10 @@ struct perf_event_context; struct blk_plug; struct filename; +#define VMACACHE_BITS 2 +#define VMACACHE_SIZE (1U << VMACACHE_BITS) +#define VMACACHE_MASK (VMACACHE_SIZE - 1) + /* * List of flags we want to share for kernel threads, * if only because they are not used by them anyway. @@ -1235,6 +1239,9 @@ struct task_struct { #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif + /* per-thread vma caching */ + u32 vmacache_seqnum; + struct vm_area_struct *vmacache[VMACACHE_SIZE]; #if defined(SPLIT_RSS_COUNTING) struct task_rss_stat rss_stat; #endif diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h new file mode 100644 index 00000000000..c3fa0fd4394 --- /dev/null +++ b/include/linux/vmacache.h @@ -0,0 +1,38 @@ +#ifndef __LINUX_VMACACHE_H +#define __LINUX_VMACACHE_H + +#include +#include + +/* + * Hash based on the page number. Provides a good hit rate for + * workloads with good locality and those with random accesses as well. + */ +#define VMACACHE_HASH(addr) ((addr >> PAGE_SHIFT) & VMACACHE_MASK) + +static inline void vmacache_flush(struct task_struct *tsk) +{ + memset(tsk->vmacache, 0, sizeof(tsk->vmacache)); +} + +extern void vmacache_flush_all(struct mm_struct *mm); +extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); +extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, + unsigned long addr); + +#ifndef CONFIG_MMU +extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, + unsigned long start, + unsigned long end); +#endif + +static inline void vmacache_invalidate(struct mm_struct *mm) +{ + mm->vmacache_seqnum++; + + /* deal with overflows */ + if (unlikely(mm->vmacache_seqnum == 0)) + vmacache_flush_all(mm); +} + +#endif /* __LINUX_VMACACHE_H */ diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 99982a70dda..2956c8da160 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -224,10 +225,17 @@ static void kgdb_flush_swbreak_addr(unsigned long addr) if (!CACHE_FLUSH_IS_SAFE) return; - if (current->mm && current->mm->mmap_cache) { - flush_cache_range(current->mm->mmap_cache, - addr, addr + BREAK_INSTR_SIZE); + if (current->mm) { + int i; + + for (i = 0; i < VMACACHE_SIZE; i++) { + if (!current->vmacache[i]) + continue; + flush_cache_range(current->vmacache[i], + addr, addr + BREAK_INSTR_SIZE); + } } + /* Force flush instruction cache if it was outside the mm */ flush_icache_range(addr, addr + BREAK_INSTR_SIZE); } diff --git a/kernel/fork.c b/kernel/fork.c index e40c0a01d5a..bc0e96b78df 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -28,6 +28,8 @@ #include #include #include +#include +#include #include #include #include @@ -364,7 +366,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) mm->locked_vm = 0; mm->mmap = NULL; - mm->mmap_cache = NULL; + mm->vmacache_seqnum = 0; mm->map_count = 0; cpumask_clear(mm_cpumask(mm)); mm->mm_rb = RB_ROOT; @@ -882,6 +884,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) if (!oldmm) return 0; + /* initialize the new vmacache entries */ + vmacache_flush(tsk); + if (clone_flags & CLONE_VM) { atomic_inc(&oldmm->mm_users); mm = oldmm; diff --git a/mm/Makefile b/mm/Makefile index cdd741519ee..23a6f7e2301 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -16,7 +16,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ - compaction.o balloon_compaction.o \ + compaction.o balloon_compaction.o vmacache.o \ interval_tree.o list_lru.o workingset.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/mmap.c b/mm/mmap.c index 46433e137ab..b1202cf81f4 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -681,8 +682,9 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, prev->vm_next = next = vma->vm_next; if (next) next->vm_prev = prev; - if (mm->mmap_cache == vma) - mm->mmap_cache = prev; + + /* Kill the cache */ + vmacache_invalidate(mm); } /* @@ -1989,34 +1991,33 @@ EXPORT_SYMBOL(get_unmapped_area); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { - struct vm_area_struct *vma = NULL; + struct rb_node *rb_node; + struct vm_area_struct *vma; /* Check the cache first. */ - /* (Cache hit rate is typically around 35%.) */ - vma = ACCESS_ONCE(mm->mmap_cache); - if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) { - struct rb_node *rb_node; + vma = vmacache_find(mm, addr); + if (likely(vma)) + return vma; - rb_node = mm->mm_rb.rb_node; - vma = NULL; + rb_node = mm->mm_rb.rb_node; + vma = NULL; - while (rb_node) { - struct vm_area_struct *vma_tmp; - - vma_tmp = rb_entry(rb_node, - struct vm_area_struct, vm_rb); - - if (vma_tmp->vm_end > addr) { - vma = vma_tmp; - if (vma_tmp->vm_start <= addr) - break; - rb_node = rb_node->rb_left; - } else - rb_node = rb_node->rb_right; - } - if (vma) - mm->mmap_cache = vma; + while (rb_node) { + struct vm_area_struct *tmp; + + tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); + + if (tmp->vm_end > addr) { + vma = tmp; + if (tmp->vm_start <= addr) + break; + rb_node = rb_node->rb_left; + } else + rb_node = rb_node->rb_right; } + + if (vma) + vmacache_update(addr, vma); return vma; } @@ -2388,7 +2389,9 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, } else mm->highest_vm_end = prev ? prev->vm_end : 0; tail_vma->vm_next = NULL; - mm->mmap_cache = NULL; /* Kill the cache. */ + + /* Kill the cache */ + vmacache_invalidate(mm); } /* diff --git a/mm/nommu.c b/mm/nommu.c index e19482533ce..5d3f3524bbd 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -15,6 +15,7 @@ #include #include +#include #include #include #include @@ -768,16 +769,23 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) */ static void delete_vma_from_mm(struct vm_area_struct *vma) { + int i; struct address_space *mapping; struct mm_struct *mm = vma->vm_mm; + struct task_struct *curr = current; kenter("%p", vma); protect_vma(vma, 0); mm->map_count--; - if (mm->mmap_cache == vma) - mm->mmap_cache = NULL; + for (i = 0; i < VMACACHE_SIZE; i++) { + /* if the vma is cached, invalidate the entire cache */ + if (curr->vmacache[i] == vma) { + vmacache_invalidate(curr->mm); + break; + } + } /* remove the VMA from the mapping */ if (vma->vm_file) { @@ -825,8 +833,8 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) struct vm_area_struct *vma; /* check the cache first */ - vma = ACCESS_ONCE(mm->mmap_cache); - if (vma && vma->vm_start <= addr && vma->vm_end > addr) + vma = vmacache_find(mm, addr); + if (likely(vma)) return vma; /* trawl the list (there may be multiple mappings in which addr @@ -835,7 +843,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) if (vma->vm_start > addr) return NULL; if (vma->vm_end > addr) { - mm->mmap_cache = vma; + vmacache_update(addr, vma); return vma; } } @@ -874,8 +882,8 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, unsigned long end = addr + len; /* check the cache first */ - vma = mm->mmap_cache; - if (vma && vma->vm_start == addr && vma->vm_end == end) + vma = vmacache_find_exact(mm, addr, end); + if (vma) return vma; /* trawl the list (there may be multiple mappings in which addr @@ -886,7 +894,7 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, if (vma->vm_start > addr) return NULL; if (vma->vm_end == end) { - mm->mmap_cache = vma; + vmacache_update(addr, vma); return vma; } } diff --git a/mm/vmacache.c b/mm/vmacache.c new file mode 100644 index 00000000000..d4224b397c0 --- /dev/null +++ b/mm/vmacache.c @@ -0,0 +1,112 @@ +/* + * Copyright (C) 2014 Davidlohr Bueso. + */ +#include +#include +#include + +/* + * Flush vma caches for threads that share a given mm. + * + * The operation is safe because the caller holds the mmap_sem + * exclusively and other threads accessing the vma cache will + * have mmap_sem held at least for read, so no extra locking + * is required to maintain the vma cache. + */ +void vmacache_flush_all(struct mm_struct *mm) +{ + struct task_struct *g, *p; + + rcu_read_lock(); + for_each_process_thread(g, p) { + /* + * Only flush the vmacache pointers as the + * mm seqnum is already set and curr's will + * be set upon invalidation when the next + * lookup is done. + */ + if (mm == p->mm) + vmacache_flush(p); + } + rcu_read_unlock(); +} + +/* + * This task may be accessing a foreign mm via (for example) + * get_user_pages()->find_vma(). The vmacache is task-local and this + * task's vmacache pertains to a different mm (ie, its own). There is + * nothing we can do here. + * + * Also handle the case where a kernel thread has adopted this mm via use_mm(). + * That kernel thread's vmacache is not applicable to this mm. + */ +static bool vmacache_valid_mm(struct mm_struct *mm) +{ + return current->mm == mm && !(current->flags & PF_KTHREAD); +} + +void vmacache_update(unsigned long addr, struct vm_area_struct *newvma) +{ + if (vmacache_valid_mm(newvma->vm_mm)) + current->vmacache[VMACACHE_HASH(addr)] = newvma; +} + +static bool vmacache_valid(struct mm_struct *mm) +{ + struct task_struct *curr; + + if (!vmacache_valid_mm(mm)) + return false; + + curr = current; + if (mm->vmacache_seqnum != curr->vmacache_seqnum) { + /* + * First attempt will always be invalid, initialize + * the new cache for this task here. + */ + curr->vmacache_seqnum = mm->vmacache_seqnum; + vmacache_flush(curr); + return false; + } + return true; +} + +struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) +{ + int i; + + if (!vmacache_valid(mm)) + return NULL; + + for (i = 0; i < VMACACHE_SIZE; i++) { + struct vm_area_struct *vma = current->vmacache[i]; + + if (vma && vma->vm_start <= addr && vma->vm_end > addr) { + BUG_ON(vma->vm_mm != mm); + return vma; + } + } + + return NULL; +} + +#ifndef CONFIG_MMU +struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + int i; + + if (!vmacache_valid(mm)) + return NULL; + + for (i = 0; i < VMACACHE_SIZE; i++) { + struct vm_area_struct *vma = current->vmacache[i]; + + if (vma && vma->vm_start == start && vma->vm_end == end) + return vma; + } + + return NULL; +} +#endif -- cgit v1.2.3-70-g09d2 From 514ddb446c5c5a238eca32b7052b7a8accae4e93 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 7 Apr 2014 15:37:27 -0700 Subject: fork: collapse copy_flags into copy_process copy_flags() does not use the clone_flags formal and can be collapsed into copy_process() for cleaner code. Signed-off-by: David Rientjes Cc: Johannes Weiner Cc: Michal Hocko Cc: KAMEZAWA Hiroyuki Cc: Christoph Lameter Cc: Pekka Enberg Cc: Tejun Heo Cc: Mel Gorman Cc: Oleg Nesterov Cc: Rik van Riel Cc: Jianguo Wu Cc: Tim Hockin Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index bc0e96b78df..c777964c066 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1080,15 +1080,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) return 0; } -static void copy_flags(unsigned long clone_flags, struct task_struct *p) -{ - unsigned long new_flags = p->flags; - - new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER); - new_flags |= PF_FORKNOEXEC; - p->flags = new_flags; -} - SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; @@ -1238,7 +1229,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ - copy_flags(clone_flags, p); + p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER); + p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); -- cgit v1.2.3-70-g09d2 From f0432d159601f96839f514f286eaa5b75c4112dc Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 7 Apr 2014 15:37:30 -0700 Subject: mm, mempolicy: remove per-process flag PF_MEMPOLICY is an unnecessary optimization for CONFIG_SLAB users. There's no significant performance degradation to checking current->mempolicy rather than current->flags & PF_MEMPOLICY in the allocation path, especially since this is considered unlikely(). Running TCP_RR with netperf-2.4.5 through localhost on 16 cpu machine with 64GB of memory and without a mempolicy: threads before after 16 1249409 1244487 32 1281786 1246783 48 1239175 1239138 64 1244642 1241841 80 1244346 1248918 96 1266436 1254316 112 1307398 1312135 128 1327607 1326502 Per-process flags are a scarce resource so we should free them up whenever possible and make them available. We'll be using it shortly for memcg oom reserves. Signed-off-by: David Rientjes Cc: Johannes Weiner Cc: Michal Hocko Cc: KAMEZAWA Hiroyuki Cc: Christoph Lameter Cc: Pekka Enberg Cc: Tejun Heo Cc: Mel Gorman Cc: Oleg Nesterov Cc: Rik van Riel Cc: Jianguo Wu Cc: Tim Hockin Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 1 - include/linux/sched.h | 1 - kernel/fork.c | 1 - mm/mempolicy.c | 31 ------------------------------- mm/slab.c | 4 ++-- 5 files changed, 2 insertions(+), 36 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index cfe55dfca01..3c1b968da0c 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -143,7 +143,6 @@ extern void numa_policy_init(void); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new, enum mpol_rebind_step step); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); -extern void mpol_fix_fork_child_flag(struct task_struct *p); extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, diff --git a/include/linux/sched.h b/include/linux/sched.h index 642477dd814..6c70645eb3b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1851,7 +1851,6 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */ #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_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* this thread called freeze_processes and should not be frozen */ diff --git a/kernel/fork.c b/kernel/fork.c index c777964c066..e905e9c6b22 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1276,7 +1276,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->mempolicy = NULL; goto bad_fork_cleanup_threadgroup_lock; } - mpol_fix_fork_child_flag(p); #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0ad0ba31979..78e1472933e 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -795,36 +795,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, return err; } -/* - * Update task->flags PF_MEMPOLICY bit: set iff non-default - * mempolicy. Allows more rapid checking of this (combined perhaps - * with other PF_* flag bits) on memory allocation hot code paths. - * - * If called from outside this file, the task 'p' should -only- be - * a newly forked child not yet visible on the task list, because - * manipulating the task flags of a visible task is not safe. - * - * The above limitation is why this routine has the funny name - * mpol_fix_fork_child_flag(). - * - * It is also safe to call this with a task pointer of current, - * which the static wrapper mpol_set_task_struct_flag() does, - * for use within this file. - */ - -void mpol_fix_fork_child_flag(struct task_struct *p) -{ - if (p->mempolicy) - p->flags |= PF_MEMPOLICY; - else - p->flags &= ~PF_MEMPOLICY; -} - -static void mpol_set_task_struct_flag(void) -{ - mpol_fix_fork_child_flag(current); -} - /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) @@ -861,7 +831,6 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, } old = current->mempolicy; current->mempolicy = new; - mpol_set_task_struct_flag(); if (new && new->mode == MPOL_INTERLEAVE && nodes_weight(new->v.nodes)) current->il_next = first_node(new->v.nodes); diff --git a/mm/slab.c b/mm/slab.c index 4b17f4c2e92..3db4cb06e32 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3027,7 +3027,7 @@ out: #ifdef CONFIG_NUMA /* - * Try allocating on another node if PF_SPREAD_SLAB|PF_MEMPOLICY. + * Try allocating on another node if PF_SPREAD_SLAB is a mempolicy is set. * * If we are in_interrupt, then process context, including cpusets and * mempolicy, may not apply and should not be used for allocation policy. @@ -3259,7 +3259,7 @@ __do_cache_alloc(struct kmem_cache *cache, gfp_t flags) { void *objp; - if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) { + if (current->mempolicy || unlikely(current->flags & PF_SPREAD_SLAB)) { objp = alternate_node_alloc(cache, flags); if (objp) goto out; -- cgit v1.2.3-70-g09d2 From 52f5684c8e1ec7463192aba8e2916df49807511a Mon Sep 17 00:00:00 2001 From: Gideon Israel Dsouza Date: Mon, 7 Apr 2014 15:39:20 -0700 Subject: kernel: use macros from compiler.h instead of __attribute__((...)) To increase compiler portability there is which provides convenience macros for various gcc constructs. Eg: __weak for __attribute__((weak)). I've replaced all instances of gcc attributes with the right macro in the kernel subsystem. Signed-off-by: Gideon Israel Dsouza Cc: "Rafael J. Wysocki" Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 3 ++- kernel/kallsyms.c | 11 ++++++----- kernel/kexec.c | 5 +++-- kernel/ksysfs.c | 5 +++-- kernel/power/power.h | 3 ++- kernel/power/snapshot.c | 3 ++- kernel/power/suspend.c | 5 +++-- kernel/power/swap.c | 2 +- kernel/sched/clock.c | 3 ++- kernel/sched/core.c | 3 ++- kernel/signal.c | 4 +++- kernel/time/timekeeping.c | 5 +++-- kernel/trace/trace.h | 3 ++- 13 files changed, 34 insertions(+), 21 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index e905e9c6b22..54a8d26f612 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -73,6 +73,7 @@ #include #include #include +#include #include #include @@ -286,7 +287,7 @@ void __init fork_init(unsigned long mempages) init_task.signal->rlim[RLIMIT_NPROC]; } -int __attribute__((weak)) arch_dup_task_struct(struct task_struct *dst, +int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 3127ad52cdb..cb0cf37dac3 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -23,6 +23,7 @@ #include #include #include +#include #include @@ -36,8 +37,8 @@ * These will be re-linked against their real values * during the second link stage. */ -extern const unsigned long kallsyms_addresses[] __attribute__((weak)); -extern const u8 kallsyms_names[] __attribute__((weak)); +extern const unsigned long kallsyms_addresses[] __weak; +extern const u8 kallsyms_names[] __weak; /* * Tell the compiler that the count isn't in the small data section if the arch @@ -46,10 +47,10 @@ extern const u8 kallsyms_names[] __attribute__((weak)); extern const unsigned long kallsyms_num_syms __attribute__((weak, section(".rodata"))); -extern const u8 kallsyms_token_table[] __attribute__((weak)); -extern const u16 kallsyms_token_index[] __attribute__((weak)); +extern const u8 kallsyms_token_table[] __weak; +extern const u16 kallsyms_token_index[] __weak; -extern const unsigned long kallsyms_markers[] __attribute__((weak)); +extern const unsigned long kallsyms_markers[] __weak; static inline int is_kernel_inittext(unsigned long addr) { diff --git a/kernel/kexec.c b/kernel/kexec.c index c0d261c7db7..c8380ad203b 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include @@ -1551,10 +1552,10 @@ void vmcoreinfo_append_str(const char *fmt, ...) * provide an empty default implementation here -- architecture * code may override this */ -void __attribute__ ((weak)) arch_crash_save_vmcoreinfo(void) +void __weak arch_crash_save_vmcoreinfo(void) {} -unsigned long __attribute__ ((weak)) paddr_vmcoreinfo_note(void) +unsigned long __weak paddr_vmcoreinfo_note(void) { return __pa((unsigned long)(char *)&vmcoreinfo_note); } diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index e660964086e..2495a9b14ac 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -18,6 +18,7 @@ #include #include #include +#include #include /* rcu_expedited */ @@ -162,8 +163,8 @@ KERNEL_ATTR_RW(rcu_expedited); /* * Make /sys/kernel/notes give the raw contents of our kernel .notes section. */ -extern const void __start_notes __attribute__((weak)); -extern const void __stop_notes __attribute__((weak)); +extern const void __start_notes __weak; +extern const void __stop_notes __weak; #define notes_size (&__stop_notes - &__start_notes) static ssize_t notes_read(struct file *filp, struct kobject *kobj, diff --git a/kernel/power/power.h b/kernel/power/power.h index 1ca75310655..15f37ea0871 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -2,6 +2,7 @@ #include #include #include +#include struct swsusp_info { struct new_utsname uts; @@ -11,7 +12,7 @@ struct swsusp_info { unsigned long image_pages; unsigned long pages; unsigned long size; -} __attribute__((aligned(PAGE_SIZE))); +} __aligned(PAGE_SIZE); #ifdef CONFIG_HIBERNATION /* kernel/power/snapshot.c */ diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 149e745eaa5..18fb7a2fb14 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -155,7 +156,7 @@ static inline void free_image_page(void *addr, int clear_nosave_free) struct linked_page { struct linked_page *next; char data[LINKED_PAGE_DATA_SIZE]; -} __attribute__((packed)); +} __packed; static inline void free_list_of_pages(struct linked_page *list, int clear_page_nosave) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 90b3d9366d1..c3ad9cafe93 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -26,6 +26,7 @@ #include #include #include +#include #include "power.h" @@ -156,13 +157,13 @@ static int suspend_prepare(suspend_state_t state) } /* default implementation */ -void __attribute__ ((weak)) arch_suspend_disable_irqs(void) +void __weak arch_suspend_disable_irqs(void) { local_irq_disable(); } /* default implementation */ -void __attribute__ ((weak)) arch_suspend_enable_irqs(void) +void __weak arch_suspend_enable_irqs(void) { local_irq_enable(); } diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 7c33ed20041..8c9a4819f79 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -101,7 +101,7 @@ struct swsusp_header { unsigned int flags; /* Flags to pass to the "boot" kernel */ char orig_sig[10]; char sig[10]; -} __attribute__((packed)); +} __packed; static struct swsusp_header *swsusp_header; diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index b30a2924ef1..3ef6451e972 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -60,13 +60,14 @@ #include #include #include +#include /* * Scheduler clock - returns current time in nanosec units. * This is default implementation. * Architectures and sub-architectures can override this. */ -unsigned long long __attribute__((weak)) sched_clock(void) +unsigned long long __weak sched_clock(void) { return (unsigned long long)(jiffies - INITIAL_JIFFIES) * (NSEC_PER_SEC / HZ); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1d1b87b3677..80bd491b718 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -73,6 +73,7 @@ #include #include #include +#include #include #include @@ -6498,7 +6499,7 @@ static cpumask_var_t fallback_doms; * cpu core maps. It is supposed to return 1 if the topology changed * or 0 if it stayed the same. */ -int __attribute__((weak)) arch_update_cpu_topology(void) +int __weak arch_update_cpu_topology(void) { return 0; } diff --git a/kernel/signal.c b/kernel/signal.c index 5d4b05a229a..6ea13c09ae5 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -33,6 +33,8 @@ #include #include #include +#include + #define CREATE_TRACE_POINTS #include @@ -3618,7 +3620,7 @@ SYSCALL_DEFINE3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask) } #endif -__attribute__((weak)) const char *arch_vma_name(struct vm_area_struct *vma) +__weak const char *arch_vma_name(struct vm_area_struct *vma) { return NULL; } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 5b40279ecd7..f7df8ea2170 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "tick-internal.h" #include "ntp_internal.h" @@ -760,7 +761,7 @@ u64 timekeeping_max_deferment(void) * * XXX - Do be sure to remove it once all arches implement it. */ -void __attribute__((weak)) read_persistent_clock(struct timespec *ts) +void __weak read_persistent_clock(struct timespec *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; @@ -775,7 +776,7 @@ void __attribute__((weak)) read_persistent_clock(struct timespec *ts) * * XXX - Do be sure to remove it once all arches implement it. */ -void __attribute__((weak)) read_boot_clock(struct timespec *ts) +void __weak read_boot_clock(struct timespec *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ffc314b7e92..2e29d7ba5a5 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -13,6 +13,7 @@ #include #include #include +#include #ifdef CONFIG_FTRACE_SYSCALLS #include /* For NR_SYSCALLS */ @@ -1279,7 +1280,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ extern struct ftrace_event_call \ - __attribute__((__aligned__(4))) event_##call; + __aligned(4) event_##call; #undef FTRACE_ENTRY_DUP #define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ -- cgit v1.2.3-70-g09d2