From 37721e1b0cf98cb65895f234d8c500d270546529 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 10 Jan 2011 08:17:10 +0200 Subject: headers: path.h redux Remove path.h from sched.h and other files. Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 341acbbc434..c118a7f203a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -70,7 +70,6 @@ struct sched_param { #include #include #include -#include #include #include #include -- cgit v1.2.3-70-g09d2 From 57cc7215b70856dc6bae8e55b00ecd7b1d7429b1 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 10 Jan 2011 08:18:25 +0200 Subject: headers: kobject.h redux Remove kobject.h from files which don't need it, notably, sched.h and fs.h. Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- arch/arm/plat-s3c24xx/cpu-freq.c | 1 - arch/powerpc/platforms/pseries/eeh_sysfs.c | 1 - drivers/char/snsc.h | 1 - drivers/net/bonding/bonding.h | 1 - drivers/pci/hotplug/acpiphp.h | 1 - drivers/pci/hotplug/rpaphp_slot.c | 1 - drivers/s390/char/tape_class.h | 1 - drivers/sh/clk/core.c | 1 - drivers/usb/musb/musb_debugfs.c | 1 - fs/gfs2/incore.h | 1 + fs/nilfs2/super.c | 1 - fs/sysfs/inode.c | 1 + fs/sysfs/sysfs.h | 1 + include/linux/firmware-map.h | 1 - include/linux/fs.h | 2 +- include/linux/sched.h | 1 - include/linux/sunrpc/cache.h | 1 + security/apparmor/include/match.h | 1 + 18 files changed, 6 insertions(+), 13 deletions(-) (limited to 'include/linux/sched.h') diff --git a/arch/arm/plat-s3c24xx/cpu-freq.c b/arch/arm/plat-s3c24xx/cpu-freq.c index 1ecc15bfe9d..25a8fc7f512 100644 --- a/arch/arm/plat-s3c24xx/cpu-freq.c +++ b/arch/arm/plat-s3c24xx/cpu-freq.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include diff --git a/arch/powerpc/platforms/pseries/eeh_sysfs.c b/arch/powerpc/platforms/pseries/eeh_sysfs.c index 15e13b56890..23982c7892d 100644 --- a/arch/powerpc/platforms/pseries/eeh_sysfs.c +++ b/arch/powerpc/platforms/pseries/eeh_sysfs.c @@ -25,7 +25,6 @@ #include #include #include -#include /** * EEH_SHOW_ATTR -- create sysfs entry for eeh statistic diff --git a/drivers/char/snsc.h b/drivers/char/snsc.h index 4be62eda9fb..e8c52c882b2 100644 --- a/drivers/char/snsc.h +++ b/drivers/char/snsc.h @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 4da384cc760..31fe980e4e2 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include "bond_3ad.h" diff --git a/drivers/pci/hotplug/acpiphp.h b/drivers/pci/hotplug/acpiphp.h index bab52047baa..7722108e78d 100644 --- a/drivers/pci/hotplug/acpiphp.h +++ b/drivers/pci/hotplug/acpiphp.h @@ -36,7 +36,6 @@ #define _ACPIPHP_H #include -#include #include #include diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c index 2ea9cf1a8d0..b283bbea6d2 100644 --- a/drivers/pci/hotplug/rpaphp_slot.c +++ b/drivers/pci/hotplug/rpaphp_slot.c @@ -24,7 +24,6 @@ */ #include #include -#include #include #include #include diff --git a/drivers/s390/char/tape_class.h b/drivers/s390/char/tape_class.h index 707b7f48c23..9e32780c317 100644 --- a/drivers/s390/char/tape_class.h +++ b/drivers/s390/char/tape_class.h @@ -14,7 +14,6 @@ #include #include #include -#include #include #include diff --git a/drivers/sh/clk/core.c b/drivers/sh/clk/core.c index 3f5e387ed56..5f63c3b8382 100644 --- a/drivers/sh/clk/core.c +++ b/drivers/sh/clk/core.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/usb/musb/musb_debugfs.c b/drivers/usb/musb/musb_debugfs.c index 9e8639d4e86..b0176e4569e 100644 --- a/drivers/usb/musb/musb_debugfs.c +++ b/drivers/usb/musb/musb_debugfs.c @@ -36,7 +36,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 8d3d2b4a0a7..a79790c0627 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -11,6 +11,7 @@ #define __INCORE_DOT_H__ #include +#include #include #include #include diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 6ea32d9b1b9..70dfdd532b8 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -47,7 +47,6 @@ #include #include #include -#include #include #include #include "nilfs.h" diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index 30ac2734558..0a12eb89cd3 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include "sysfs.h" diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index ffaaa816bfb..3d28af31d86 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -9,6 +9,7 @@ */ #include +#include #include struct sysfs_open_dirent; diff --git a/include/linux/firmware-map.h b/include/linux/firmware-map.h index c6dcc1dfe78..43fe52fcef0 100644 --- a/include/linux/firmware-map.h +++ b/include/linux/firmware-map.h @@ -17,7 +17,6 @@ #define _LINUX_FIRMWARE_MAP_H #include -#include /* * provide a dummy interface if CONFIG_FIRMWARE_MEMMAP is disabled diff --git a/include/linux/fs.h b/include/linux/fs.h index baf3e556ff0..f84d9928bdb 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -382,7 +382,6 @@ struct inodes_stat_t { #include #include #include -#include #include #include #include @@ -402,6 +401,7 @@ struct hd_geometry; struct iovec; struct nameidata; struct kiocb; +struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; diff --git a/include/linux/sched.h b/include/linux/sched.h index c118a7f203a..abc527aa855 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -87,7 +87,6 @@ struct sched_param { #include #include #include -#include #include #include diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 6950c981882..78aa104250b 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -13,6 +13,7 @@ #ifndef _LINUX_SUNRPC_CACHE_H_ #define _LINUX_SUNRPC_CACHE_H_ +#include #include #include #include diff --git a/security/apparmor/include/match.h b/security/apparmor/include/match.h index 734a6d35112..19ba16e8aac 100644 --- a/security/apparmor/include/match.h +++ b/security/apparmor/include/match.h @@ -15,6 +15,7 @@ #ifndef __AA_MATCH_H #define __AA_MATCH_H +#include #include #define DFA_NOMATCH 0 -- cgit v1.2.3-70-g09d2 From 52bd19f7691b2ea6433aef0ef94c08c57efd7e79 Mon Sep 17 00:00:00 2001 From: Robin Holt Date: Wed, 12 Jan 2011 17:00:01 -0800 Subject: epoll: convert max_user_watches to long On a 16TB machine, max_user_watches has an integer overflow. Convert it to use a long and handle the associated fallout. Signed-off-by: Robin Holt Cc: "Eric W. Biederman" Acked-by: Davide Libenzi Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/eventpoll.c | 20 ++++++++++++-------- include/linux/sched.h | 2 +- 2 files changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux/sched.h') diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 8cf07242067..cc8a9b7d606 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -217,7 +217,7 @@ struct ep_send_events_data { * Configuration options available inside /proc/sys/fs/epoll/ */ /* Maximum number of epoll watched descriptors, per user */ -static int max_user_watches __read_mostly; +static long max_user_watches __read_mostly; /* * This mutex is used to serialize ep_free() and eventpoll_release_file(). @@ -240,16 +240,18 @@ static struct kmem_cache *pwq_cache __read_mostly; #include -static int zero; +static long zero; +static long long_max = LONG_MAX; ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, - .maxlen = sizeof(int), + .maxlen = sizeof(max_user_watches), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &zero, + .extra2 = &long_max, }, { } }; @@ -561,7 +563,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) /* At this point it is safe to free the eventpoll item */ kmem_cache_free(epi_cache, epi); - atomic_dec(&ep->user->epoll_watches); + atomic_long_dec(&ep->user->epoll_watches); return 0; } @@ -898,11 +900,12 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, { int error, revents, pwake = 0; unsigned long flags; + long user_watches; struct epitem *epi; struct ep_pqueue epq; - if (unlikely(atomic_read(&ep->user->epoll_watches) >= - max_user_watches)) + user_watches = atomic_long_read(&ep->user->epoll_watches); + if (unlikely(user_watches >= max_user_watches)) return -ENOSPC; if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL))) return -ENOMEM; @@ -966,7 +969,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, spin_unlock_irqrestore(&ep->lock, flags); - atomic_inc(&ep->user->epoll_watches); + atomic_long_inc(&ep->user->epoll_watches); /* We have to call this outside the lock */ if (pwake) @@ -1426,6 +1429,7 @@ static int __init eventpoll_init(void) */ max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) / EP_ITEM_COST; + BUG_ON(max_user_watches < 0); /* Initialize the structure used to perform safe poll wait head wake ups */ ep_nested_calls_init(&poll_safewake_ncalls); diff --git a/include/linux/sched.h b/include/linux/sched.h index abc527aa855..96e23215e27 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -683,7 +683,7 @@ struct user_struct { atomic_t fanotify_listeners; #endif #ifdef CONFIG_EPOLL - atomic_t epoll_watches; /* The number of file descriptors currently watched */ + atomic_long_t epoll_watches; /* The number of file descriptors currently watched */ #endif #ifdef CONFIG_POSIX_MQUEUE /* protected by mq_lock */ -- cgit v1.2.3-70-g09d2 From 43bb40c9e3aa51a3b038c9df2c9afb4d4685614d Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Thu, 13 Jan 2011 15:45:40 -0800 Subject: sched: remove long deprecated CLONE_STOPPED flag This warning was added in commit bdff746a3915 ("clone: prepare to recycle CLONE_STOPPED") three years ago. 2.6.26 came and went. As far as I know, no-one is actually using CLONE_STOPPED. Signed-off-by: Dave Jones Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 ++- kernel/fork.c | 28 +--------------------------- 2 files changed, 3 insertions(+), 28 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 96e23215e27..07402530fc7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -21,7 +21,8 @@ #define CLONE_DETACHED 0x00400000 /* Unused, ignored */ #define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */ #define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */ -#define CLONE_STOPPED 0x02000000 /* Start in stopped state */ +/* 0x02000000 was previously the unused CLONE_STOPPED (Start in stopped state) + and is now available for re-use. */ #define CLONE_NEWUTS 0x04000000 /* New utsname group? */ #define CLONE_NEWIPC 0x08000000 /* New ipcs */ #define CLONE_NEWUSER 0x10000000 /* New user namespace */ diff --git a/kernel/fork.c b/kernel/fork.c index d9b44f20b6b..76a1fdd80bd 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1409,23 +1409,6 @@ long do_fork(unsigned long clone_flags, return -EPERM; } - /* - * We hope to recycle these flags after 2.6.26 - */ - if (unlikely(clone_flags & CLONE_STOPPED)) { - static int __read_mostly count = 100; - - if (count > 0 && printk_ratelimit()) { - char comm[TASK_COMM_LEN]; - - count--; - printk(KERN_INFO "fork(): process `%s' used deprecated " - "clone flags 0x%lx\n", - get_task_comm(comm, current), - clone_flags & CLONE_STOPPED); - } - } - /* * When called from kernel_thread, don't do user tracing stuff. */ @@ -1464,16 +1447,7 @@ long do_fork(unsigned long clone_flags, */ p->flags &= ~PF_STARTING; - if (unlikely(clone_flags & CLONE_STOPPED)) { - /* - * We'll start up with an immediate SIGSTOP. - */ - sigaddset(&p->pending.signal, SIGSTOP); - set_tsk_thread_flag(p, TIF_SIGPENDING); - __set_task_state(p, TASK_STOPPED); - } else { - wake_up_new_task(p, clone_flags); - } + wake_up_new_task(p, clone_flags); tracehook_report_clone_complete(trace, regs, clone_flags, nr, p); -- cgit v1.2.3-70-g09d2 From dabb16f639820267b3850d804571c70bd93d4e07 Mon Sep 17 00:00:00 2001 From: Mandeep Singh Baines Date: Thu, 13 Jan 2011 15:46:05 -0800 Subject: oom: allow a non-CAP_SYS_RESOURCE proces to oom_score_adj down We'd like to be able to oom_score_adj a process up/down as it enters/leaves the foreground. Currently, it is not possible to oom_adj down without CAP_SYS_RESOURCE. This patch allows a task to decrease its oom_score_adj back to the value that a CAP_SYS_RESOURCE thread set it to or its inherited value at fork. Assuming the thread that has forked it has oom_score_adj of 0, each process could decrease it back from 0 upon activation unless a CAP_SYS_RESOURCE thread elevated it to something higher. Alternative considered: * a setuid binary * a daemon with CAP_SYS_RESOURCE Since you don't wan't all processes to be able to reduce their oom_adj, a setuid or daemon implementation would be complex. The alternatives also have much higher overhead. This patch updated from original patch based on feedback from David Rientjes. Signed-off-by: Mandeep Singh Baines Acked-by: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Rik van Riel Cc: Ying Han Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 4 ++++ fs/proc/base.c | 4 +++- include/linux/sched.h | 2 ++ kernel/fork.c | 1 + 4 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index ef757fca470..23cae6548d3 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1323,6 +1323,10 @@ scaled linearly with /proc//oom_score_adj. Writing to /proc//oom_score_adj or /proc//oom_adj will change the other with its scaled value. +The value of /proc//oom_score_adj may be reduced no lower than the last +value set by a CAP_SYS_RESOURCE process. To reduce the value any lower +requires CAP_SYS_RESOURCE. + NOTICE: /proc//oom_adj is deprecated and will be removed, please see Documentation/feature-removal-schedule.txt. diff --git a/fs/proc/base.c b/fs/proc/base.c index 93f1cdd5d3d..9d096e82b20 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1151,7 +1151,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, goto err_task_lock; } - if (oom_score_adj < task->signal->oom_score_adj && + if (oom_score_adj < task->signal->oom_score_adj_min && !capable(CAP_SYS_RESOURCE)) { err = -EACCES; goto err_sighand; @@ -1164,6 +1164,8 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, atomic_dec(&task->mm->oom_disable_count); } task->signal->oom_score_adj = oom_score_adj; + if (has_capability_noaudit(current, CAP_SYS_RESOURCE)) + task->signal->oom_score_adj_min = oom_score_adj; /* * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is * always attainable. diff --git a/include/linux/sched.h b/include/linux/sched.h index 07402530fc7..f23b5bb6f52 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -634,6 +634,8 @@ struct signal_struct { int oom_adj; /* OOM kill score adjustment (bit shift) */ int oom_score_adj; /* OOM kill score adjustment */ + int oom_score_adj_min; /* OOM kill score adjustment minimum value. + * Only settable by CAP_SYS_RESOURCE. */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations diff --git a/kernel/fork.c b/kernel/fork.c index 76a1fdd80bd..1499607e4da 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -910,6 +910,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->oom_adj = current->signal->oom_adj; sig->oom_score_adj = current->signal->oom_score_adj; + sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); -- cgit v1.2.3-70-g09d2 From ba76149f47d8c939efa0acc07a191237af900471 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:58 -0800 Subject: thp: khugepaged Add khugepaged to relocate fragmented pages into hugepages if new hugepages become available. (this is indipendent of the defrag logic that will have to make new hugepages available) The fundamental reason why khugepaged is unavoidable, is that some memory can be fragmented and not everything can be relocated. So when a virtual machine quits and releases gigabytes of hugepages, we want to use those freely available hugepages to create huge-pmd in the other virtual machines that may be running on fragmented memory, to maximize the CPU efficiency at all times. The scan is slow, it takes nearly zero cpu time, except when it copies data (in which case it means we definitely want to pay for that cpu time) so it seems a good tradeoff. In addition to the hugepages being released by other process releasing memory, we have the strong suspicion that the performance impact of potentially defragmenting hugepages during or before each page fault could lead to more performance inconsistency than allocating small pages at first and having them collapsed into large pages later... if they prove themselfs to be long lived mappings (khugepaged scan is slow so short lived mappings have low probability to run into khugepaged if compared to long lived mappings). Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 1 + include/linux/khugepaged.h | 66 +++ include/linux/sched.h | 1 + kernel/fork.c | 5 + mm/huge_memory.c | 1073 +++++++++++++++++++++++++++++++++++++++++++- 5 files changed, 1136 insertions(+), 10 deletions(-) create mode 100644 include/linux/khugepaged.h (limited to 'include/linux/sched.h') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index d9ab70d776e..43a694ef890 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -25,6 +25,7 @@ enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, + TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, #ifdef CONFIG_DEBUG_VM TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG, #endif diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h new file mode 100644 index 00000000000..552f3184756 --- /dev/null +++ b/include/linux/khugepaged.h @@ -0,0 +1,66 @@ +#ifndef _LINUX_KHUGEPAGED_H +#define _LINUX_KHUGEPAGED_H + +#include /* MMF_VM_HUGEPAGE */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern int __khugepaged_enter(struct mm_struct *mm); +extern void __khugepaged_exit(struct mm_struct *mm); +extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma); + +#define khugepaged_enabled() \ + (transparent_hugepage_flags & \ + ((1<flags)) + return __khugepaged_enter(mm); + return 0; +} + +static inline void khugepaged_exit(struct mm_struct *mm) +{ + if (test_bit(MMF_VM_HUGEPAGE, &mm->flags)) + __khugepaged_exit(mm); +} + +static inline int khugepaged_enter(struct vm_area_struct *vma) +{ + if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) + if (khugepaged_always() || + (khugepaged_req_madv() && + vma->vm_flags & VM_HUGEPAGE)) + if (__khugepaged_enter(vma->vm_mm)) + return -ENOMEM; + return 0; +} +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) +{ + return 0; +} +static inline void khugepaged_exit(struct mm_struct *mm) +{ +} +static inline int khugepaged_enter(struct vm_area_struct *vma) +{ + return 0; +} +static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma) +{ + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#endif /* _LINUX_KHUGEPAGED_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index f23b5bb6f52..d747f948b34 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -434,6 +434,7 @@ extern int get_dumpable(struct mm_struct *mm); #endif /* leave room for more dump flags */ #define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ +#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) diff --git a/kernel/fork.c b/kernel/fork.c index f78f50ba6cb..25e429152dd 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -66,6 +66,7 @@ #include #include #include +#include #include #include @@ -328,6 +329,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) rb_parent = NULL; pprev = &mm->mmap; retval = ksm_fork(mm, oldmm); + if (retval) + goto out; + retval = khugepaged_fork(mm, oldmm); if (retval) goto out; @@ -546,6 +550,7 @@ void mmput(struct mm_struct *mm) if (atomic_dec_and_test(&mm->mm_users)) { exit_aio(mm); ksm_exit(mm); + khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 7101112a542..ae2bf08b109 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -12,14 +12,111 @@ #include #include #include +#include +#include +#include #include #include #include "internal.h" +/* + * By default transparent hugepage support is enabled for all mappings + * and khugepaged scans all mappings. Defrag is only invoked by + * khugepaged hugepage allocations and by page faults inside + * MADV_HUGEPAGE regions to avoid the risk of slowing down short lived + * allocations. + */ unsigned long transparent_hugepage_flags __read_mostly = - (1< 0) { + int err = start_khugepaged(); + if (err) + ret = err; + } + + return ret; } static struct kobj_attribute enabled_attr = __ATTR(enabled, 0644, enabled_show, enabled_store); @@ -153,20 +260,212 @@ static struct attribute *hugepage_attr[] = { static struct attribute_group hugepage_attr_group = { .attrs = hugepage_attr, - .name = "transparent_hugepage", +}; + +static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_scan_sleep_millisecs); +} + +static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long msecs; + int err; + + err = strict_strtoul(buf, 10, &msecs); + if (err || msecs > UINT_MAX) + return -EINVAL; + + khugepaged_scan_sleep_millisecs = msecs; + wake_up_interruptible(&khugepaged_wait); + + return count; +} +static struct kobj_attribute scan_sleep_millisecs_attr = + __ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show, + scan_sleep_millisecs_store); + +static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_alloc_sleep_millisecs); +} + +static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long msecs; + int err; + + err = strict_strtoul(buf, 10, &msecs); + if (err || msecs > UINT_MAX) + return -EINVAL; + + khugepaged_alloc_sleep_millisecs = msecs; + wake_up_interruptible(&khugepaged_wait); + + return count; +} +static struct kobj_attribute alloc_sleep_millisecs_attr = + __ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show, + alloc_sleep_millisecs_store); + +static ssize_t pages_to_scan_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_pages_to_scan); +} +static ssize_t pages_to_scan_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long pages; + + err = strict_strtoul(buf, 10, &pages); + if (err || !pages || pages > UINT_MAX) + return -EINVAL; + + khugepaged_pages_to_scan = pages; + + return count; +} +static struct kobj_attribute pages_to_scan_attr = + __ATTR(pages_to_scan, 0644, pages_to_scan_show, + pages_to_scan_store); + +static ssize_t pages_collapsed_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_pages_collapsed); +} +static struct kobj_attribute pages_collapsed_attr = + __ATTR_RO(pages_collapsed); + +static ssize_t full_scans_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_full_scans); +} +static struct kobj_attribute full_scans_attr = + __ATTR_RO(full_scans); + +static ssize_t khugepaged_defrag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return single_flag_show(kobj, attr, buf, + TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); +} +static ssize_t khugepaged_defrag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + return single_flag_store(kobj, attr, buf, count, + TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); +} +static struct kobj_attribute khugepaged_defrag_attr = + __ATTR(defrag, 0644, khugepaged_defrag_show, + khugepaged_defrag_store); + +/* + * max_ptes_none controls if khugepaged should collapse hugepages over + * any unmapped ptes in turn potentially increasing the memory + * footprint of the vmas. When max_ptes_none is 0 khugepaged will not + * reduce the available free memory in the system as it + * runs. Increasing max_ptes_none will instead potentially reduce the + * free memory in the system during the khugepaged scan. + */ +static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_max_ptes_none); +} +static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long max_ptes_none; + + err = strict_strtoul(buf, 10, &max_ptes_none); + if (err || max_ptes_none > HPAGE_PMD_NR-1) + return -EINVAL; + + khugepaged_max_ptes_none = max_ptes_none; + + return count; +} +static struct kobj_attribute khugepaged_max_ptes_none_attr = + __ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show, + khugepaged_max_ptes_none_store); + +static struct attribute *khugepaged_attr[] = { + &khugepaged_defrag_attr.attr, + &khugepaged_max_ptes_none_attr.attr, + &pages_to_scan_attr.attr, + &pages_collapsed_attr.attr, + &full_scans_attr.attr, + &scan_sleep_millisecs_attr.attr, + &alloc_sleep_millisecs_attr.attr, + NULL, +}; + +static struct attribute_group khugepaged_attr_group = { + .attrs = khugepaged_attr, + .name = "khugepaged", }; #endif /* CONFIG_SYSFS */ static int __init hugepage_init(void) { -#ifdef CONFIG_SYSFS int err; +#ifdef CONFIG_SYSFS + static struct kobject *hugepage_kobj; - err = sysfs_create_group(mm_kobj, &hugepage_attr_group); - if (err) - printk(KERN_ERR "hugepage: register sysfs failed\n"); + err = -ENOMEM; + hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj); + if (unlikely(!hugepage_kobj)) { + printk(KERN_ERR "hugepage: failed kobject create\n"); + goto out; + } + + err = sysfs_create_group(hugepage_kobj, &hugepage_attr_group); + if (err) { + printk(KERN_ERR "hugepage: failed register hugeage group\n"); + goto out; + } + + err = sysfs_create_group(hugepage_kobj, &khugepaged_attr_group); + if (err) { + printk(KERN_ERR "hugepage: failed register hugeage group\n"); + goto out; + } #endif - return 0; + + err = khugepaged_slab_init(); + if (err) + goto out; + + err = mm_slots_hash_init(); + if (err) { + khugepaged_slab_free(); + goto out; + } + + start_khugepaged(); + +out: + return err; } module_init(hugepage_init) @@ -285,6 +584,8 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) { if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; + if (unlikely(khugepaged_enter(vma))) + return VM_FAULT_OOM; page = alloc_hugepage(transparent_hugepage_defrag(vma)); if (unlikely(!page)) goto out; @@ -941,6 +1242,758 @@ int hugepage_madvise(unsigned long *vm_flags) return 0; } +static int __init khugepaged_slab_init(void) +{ + mm_slot_cache = kmem_cache_create("khugepaged_mm_slot", + sizeof(struct mm_slot), + __alignof__(struct mm_slot), 0, NULL); + if (!mm_slot_cache) + return -ENOMEM; + + return 0; +} + +static void __init khugepaged_slab_free(void) +{ + kmem_cache_destroy(mm_slot_cache); + mm_slot_cache = NULL; +} + +static inline struct mm_slot *alloc_mm_slot(void) +{ + if (!mm_slot_cache) /* initialization failed */ + return NULL; + return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL); +} + +static inline void free_mm_slot(struct mm_slot *mm_slot) +{ + kmem_cache_free(mm_slot_cache, mm_slot); +} + +static int __init mm_slots_hash_init(void) +{ + mm_slots_hash = kzalloc(MM_SLOTS_HASH_HEADS * sizeof(struct hlist_head), + GFP_KERNEL); + if (!mm_slots_hash) + return -ENOMEM; + return 0; +} + +#if 0 +static void __init mm_slots_hash_free(void) +{ + kfree(mm_slots_hash); + mm_slots_hash = NULL; +} +#endif + +static struct mm_slot *get_mm_slot(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + struct hlist_head *bucket; + struct hlist_node *node; + + bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct)) + % MM_SLOTS_HASH_HEADS]; + hlist_for_each_entry(mm_slot, node, bucket, hash) { + if (mm == mm_slot->mm) + return mm_slot; + } + return NULL; +} + +static void insert_to_mm_slots_hash(struct mm_struct *mm, + struct mm_slot *mm_slot) +{ + struct hlist_head *bucket; + + bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct)) + % MM_SLOTS_HASH_HEADS]; + mm_slot->mm = mm; + hlist_add_head(&mm_slot->hash, bucket); +} + +static inline int khugepaged_test_exit(struct mm_struct *mm) +{ + return atomic_read(&mm->mm_users) == 0; +} + +int __khugepaged_enter(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + int wakeup; + + mm_slot = alloc_mm_slot(); + if (!mm_slot) + return -ENOMEM; + + /* __khugepaged_exit() must not run from under us */ + VM_BUG_ON(khugepaged_test_exit(mm)); + if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) { + free_mm_slot(mm_slot); + return 0; + } + + spin_lock(&khugepaged_mm_lock); + insert_to_mm_slots_hash(mm, mm_slot); + /* + * Insert just behind the scanning cursor, to let the area settle + * down a little. + */ + wakeup = list_empty(&khugepaged_scan.mm_head); + list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head); + spin_unlock(&khugepaged_mm_lock); + + atomic_inc(&mm->mm_count); + if (wakeup) + wake_up_interruptible(&khugepaged_wait); + + return 0; +} + +int khugepaged_enter_vma_merge(struct vm_area_struct *vma) +{ + unsigned long hstart, hend; + if (!vma->anon_vma) + /* + * Not yet faulted in so we will register later in the + * page fault if needed. + */ + return 0; + if (vma->vm_file || vma->vm_ops) + /* khugepaged not yet working on file or special mappings */ + return 0; + VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma)); + hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = vma->vm_end & HPAGE_PMD_MASK; + if (hstart < hend) + return khugepaged_enter(vma); + return 0; +} + +void __khugepaged_exit(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + int free = 0; + + spin_lock(&khugepaged_mm_lock); + mm_slot = get_mm_slot(mm); + if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { + hlist_del(&mm_slot->hash); + list_del(&mm_slot->mm_node); + free = 1; + } + + if (free) { + spin_unlock(&khugepaged_mm_lock); + clear_bit(MMF_VM_HUGEPAGE, &mm->flags); + free_mm_slot(mm_slot); + mmdrop(mm); + } else if (mm_slot) { + spin_unlock(&khugepaged_mm_lock); + /* + * This is required to serialize against + * khugepaged_test_exit() (which is guaranteed to run + * under mmap sem read mode). Stop here (after we + * return all pagetables will be destroyed) until + * khugepaged has finished working on the pagetables + * under the mmap_sem. + */ + down_write(&mm->mmap_sem); + up_write(&mm->mmap_sem); + } else + spin_unlock(&khugepaged_mm_lock); +} + +static void release_pte_page(struct page *page) +{ + /* 0 stands for page_is_file_cache(page) == false */ + dec_zone_page_state(page, NR_ISOLATED_ANON + 0); + unlock_page(page); + putback_lru_page(page); +} + +static void release_pte_pages(pte_t *pte, pte_t *_pte) +{ + while (--_pte >= pte) { + pte_t pteval = *_pte; + if (!pte_none(pteval)) + release_pte_page(pte_page(pteval)); + } +} + +static void release_all_pte_pages(pte_t *pte) +{ + release_pte_pages(pte, pte + HPAGE_PMD_NR); +} + +static int __collapse_huge_page_isolate(struct vm_area_struct *vma, + unsigned long address, + pte_t *pte) +{ + struct page *page; + pte_t *_pte; + int referenced = 0, isolated = 0, none = 0; + for (_pte = pte; _pte < pte+HPAGE_PMD_NR; + _pte++, address += PAGE_SIZE) { + pte_t pteval = *_pte; + if (pte_none(pteval)) { + if (++none <= khugepaged_max_ptes_none) + continue; + else { + release_pte_pages(pte, _pte); + goto out; + } + } + if (!pte_present(pteval) || !pte_write(pteval)) { + release_pte_pages(pte, _pte); + goto out; + } + page = vm_normal_page(vma, address, pteval); + if (unlikely(!page)) { + release_pte_pages(pte, _pte); + goto out; + } + VM_BUG_ON(PageCompound(page)); + BUG_ON(!PageAnon(page)); + VM_BUG_ON(!PageSwapBacked(page)); + + /* cannot use mapcount: can't collapse if there's a gup pin */ + if (page_count(page) != 1) { + release_pte_pages(pte, _pte); + goto out; + } + /* + * We can do it before isolate_lru_page because the + * page can't be freed from under us. NOTE: PG_lock + * is needed to serialize against split_huge_page + * when invoked from the VM. + */ + if (!trylock_page(page)) { + release_pte_pages(pte, _pte); + goto out; + } + /* + * Isolate the page to avoid collapsing an hugepage + * currently in use by the VM. + */ + if (isolate_lru_page(page)) { + unlock_page(page); + release_pte_pages(pte, _pte); + goto out; + } + /* 0 stands for page_is_file_cache(page) == false */ + inc_zone_page_state(page, NR_ISOLATED_ANON + 0); + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(PageLRU(page)); + + /* If there is no mapped pte young don't collapse the page */ + if (pte_young(pteval)) + referenced = 1; + } + if (unlikely(!referenced)) + release_all_pte_pages(pte); + else + isolated = 1; +out: + return isolated; +} + +static void __collapse_huge_page_copy(pte_t *pte, struct page *page, + struct vm_area_struct *vma, + unsigned long address, + spinlock_t *ptl) +{ + pte_t *_pte; + for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++) { + pte_t pteval = *_pte; + struct page *src_page; + + if (pte_none(pteval)) { + clear_user_highpage(page, address); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); + } else { + src_page = pte_page(pteval); + copy_user_highpage(page, src_page, address, vma); + VM_BUG_ON(page_mapcount(src_page) != 1); + VM_BUG_ON(page_count(src_page) != 2); + release_pte_page(src_page); + /* + * ptl mostly unnecessary, but preempt has to + * be disabled to update the per-cpu stats + * inside page_remove_rmap(). + */ + spin_lock(ptl); + /* + * paravirt calls inside pte_clear here are + * superfluous. + */ + pte_clear(vma->vm_mm, address, _pte); + page_remove_rmap(src_page); + spin_unlock(ptl); + free_page_and_swap_cache(src_page); + } + + address += PAGE_SIZE; + page++; + } +} + +static void collapse_huge_page(struct mm_struct *mm, + unsigned long address, + struct page **hpage) +{ + struct vm_area_struct *vma; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd, _pmd; + pte_t *pte; + pgtable_t pgtable; + struct page *new_page; + spinlock_t *ptl; + int isolated; + unsigned long hstart, hend; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + VM_BUG_ON(!*hpage); + + /* + * Prevent all access to pagetables with the exception of + * gup_fast later hanlded by the ptep_clear_flush and the VM + * handled by the anon_vma lock + PG_lock. + */ + down_write(&mm->mmap_sem); + if (unlikely(khugepaged_test_exit(mm))) + goto out; + + vma = find_vma(mm, address); + hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = vma->vm_end & HPAGE_PMD_MASK; + if (address < hstart || address + HPAGE_PMD_SIZE > hend) + goto out; + + if (!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) + goto out; + + /* VM_PFNMAP vmas may have vm_ops null but vm_file set */ + if (!vma->anon_vma || vma->vm_ops || vma->vm_file) + goto out; + VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma)); + + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + goto out; + + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + goto out; + + pmd = pmd_offset(pud, address); + /* pmd can't go away or become huge under us */ + if (!pmd_present(*pmd) || pmd_trans_huge(*pmd)) + goto out; + + new_page = *hpage; + if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) + goto out; + + anon_vma_lock(vma->anon_vma); + + pte = pte_offset_map(pmd, address); + ptl = pte_lockptr(mm, pmd); + + spin_lock(&mm->page_table_lock); /* probably unnecessary */ + /* + * After this gup_fast can't run anymore. This also removes + * any huge TLB entry from the CPU so we won't allow + * huge and small TLB entries for the same virtual address + * to avoid the risk of CPU bugs in that area. + */ + _pmd = pmdp_clear_flush_notify(vma, address, pmd); + spin_unlock(&mm->page_table_lock); + + spin_lock(ptl); + isolated = __collapse_huge_page_isolate(vma, address, pte); + spin_unlock(ptl); + pte_unmap(pte); + + if (unlikely(!isolated)) { + spin_lock(&mm->page_table_lock); + BUG_ON(!pmd_none(*pmd)); + set_pmd_at(mm, address, pmd, _pmd); + spin_unlock(&mm->page_table_lock); + anon_vma_unlock(vma->anon_vma); + mem_cgroup_uncharge_page(new_page); + goto out; + } + + /* + * All pages are isolated and locked so anon_vma rmap + * can't run anymore. + */ + anon_vma_unlock(vma->anon_vma); + + __collapse_huge_page_copy(pte, new_page, vma, address, ptl); + __SetPageUptodate(new_page); + pgtable = pmd_pgtable(_pmd); + VM_BUG_ON(page_count(pgtable) != 1); + VM_BUG_ON(page_mapcount(pgtable) != 0); + + _pmd = mk_pmd(new_page, vma->vm_page_prot); + _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); + _pmd = pmd_mkhuge(_pmd); + + /* + * spin_lock() below is not the equivalent of smp_wmb(), so + * this is needed to avoid the copy_huge_page writes to become + * visible after the set_pmd_at() write. + */ + smp_wmb(); + + spin_lock(&mm->page_table_lock); + BUG_ON(!pmd_none(*pmd)); + page_add_new_anon_rmap(new_page, vma, address); + set_pmd_at(mm, address, pmd, _pmd); + update_mmu_cache(vma, address, entry); + prepare_pmd_huge_pte(pgtable, mm); + mm->nr_ptes--; + spin_unlock(&mm->page_table_lock); + + *hpage = NULL; + khugepaged_pages_collapsed++; +out: + up_write(&mm->mmap_sem); +} + +static int khugepaged_scan_pmd(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long address, + struct page **hpage) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte, *_pte; + int ret = 0, referenced = 0, none = 0; + struct page *page; + unsigned long _address; + spinlock_t *ptl; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + goto out; + + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + goto out; + + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd) || pmd_trans_huge(*pmd)) + goto out; + + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; + _pte++, _address += PAGE_SIZE) { + pte_t pteval = *_pte; + if (pte_none(pteval)) { + if (++none <= khugepaged_max_ptes_none) + continue; + else + goto out_unmap; + } + if (!pte_present(pteval) || !pte_write(pteval)) + goto out_unmap; + page = vm_normal_page(vma, _address, pteval); + if (unlikely(!page)) + goto out_unmap; + VM_BUG_ON(PageCompound(page)); + if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) + goto out_unmap; + /* cannot use mapcount: can't collapse if there's a gup pin */ + if (page_count(page) != 1) + goto out_unmap; + if (pte_young(pteval)) + referenced = 1; + } + if (referenced) + ret = 1; +out_unmap: + pte_unmap_unlock(pte, ptl); + if (ret) { + up_read(&mm->mmap_sem); + collapse_huge_page(mm, address, hpage); + } +out: + return ret; +} + +static void collect_mm_slot(struct mm_slot *mm_slot) +{ + struct mm_struct *mm = mm_slot->mm; + + VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock)); + + if (khugepaged_test_exit(mm)) { + /* free mm_slot */ + hlist_del(&mm_slot->hash); + list_del(&mm_slot->mm_node); + + /* + * Not strictly needed because the mm exited already. + * + * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); + */ + + /* khugepaged_mm_lock actually not necessary for the below */ + free_mm_slot(mm_slot); + mmdrop(mm); + } +} + +static unsigned int khugepaged_scan_mm_slot(unsigned int pages, + struct page **hpage) +{ + struct mm_slot *mm_slot; + struct mm_struct *mm; + struct vm_area_struct *vma; + int progress = 0; + + VM_BUG_ON(!pages); + VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock)); + + if (khugepaged_scan.mm_slot) + mm_slot = khugepaged_scan.mm_slot; + else { + mm_slot = list_entry(khugepaged_scan.mm_head.next, + struct mm_slot, mm_node); + khugepaged_scan.address = 0; + khugepaged_scan.mm_slot = mm_slot; + } + spin_unlock(&khugepaged_mm_lock); + + mm = mm_slot->mm; + down_read(&mm->mmap_sem); + if (unlikely(khugepaged_test_exit(mm))) + vma = NULL; + else + vma = find_vma(mm, khugepaged_scan.address); + + progress++; + for (; vma; vma = vma->vm_next) { + unsigned long hstart, hend; + + cond_resched(); + if (unlikely(khugepaged_test_exit(mm))) { + progress++; + break; + } + + if (!(vma->vm_flags & VM_HUGEPAGE) && + !khugepaged_always()) { + progress++; + continue; + } + + /* VM_PFNMAP vmas may have vm_ops null but vm_file set */ + if (!vma->anon_vma || vma->vm_ops || vma->vm_file) { + khugepaged_scan.address = vma->vm_end; + progress++; + continue; + } + VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma)); + + hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = vma->vm_end & HPAGE_PMD_MASK; + if (hstart >= hend) { + progress++; + continue; + } + if (khugepaged_scan.address < hstart) + khugepaged_scan.address = hstart; + if (khugepaged_scan.address > hend) { + khugepaged_scan.address = hend + HPAGE_PMD_SIZE; + progress++; + continue; + } + BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); + + while (khugepaged_scan.address < hend) { + int ret; + cond_resched(); + if (unlikely(khugepaged_test_exit(mm))) + goto breakouterloop; + + VM_BUG_ON(khugepaged_scan.address < hstart || + khugepaged_scan.address + HPAGE_PMD_SIZE > + hend); + ret = khugepaged_scan_pmd(mm, vma, + khugepaged_scan.address, + hpage); + /* move to next address */ + khugepaged_scan.address += HPAGE_PMD_SIZE; + progress += HPAGE_PMD_NR; + if (ret) + /* we released mmap_sem so break loop */ + goto breakouterloop_mmap_sem; + if (progress >= pages) + goto breakouterloop; + } + } +breakouterloop: + up_read(&mm->mmap_sem); /* exit_mmap will destroy ptes after this */ +breakouterloop_mmap_sem: + + spin_lock(&khugepaged_mm_lock); + BUG_ON(khugepaged_scan.mm_slot != mm_slot); + /* + * Release the current mm_slot if this mm is about to die, or + * if we scanned all vmas of this mm. + */ + if (khugepaged_test_exit(mm) || !vma) { + /* + * Make sure that if mm_users is reaching zero while + * khugepaged runs here, khugepaged_exit will find + * mm_slot not pointing to the exiting mm. + */ + if (mm_slot->mm_node.next != &khugepaged_scan.mm_head) { + khugepaged_scan.mm_slot = list_entry( + mm_slot->mm_node.next, + struct mm_slot, mm_node); + khugepaged_scan.address = 0; + } else { + khugepaged_scan.mm_slot = NULL; + khugepaged_full_scans++; + } + + collect_mm_slot(mm_slot); + } + + return progress; +} + +static int khugepaged_has_work(void) +{ + return !list_empty(&khugepaged_scan.mm_head) && + khugepaged_enabled(); +} + +static int khugepaged_wait_event(void) +{ + return !list_empty(&khugepaged_scan.mm_head) || + !khugepaged_enabled(); +} + +static void khugepaged_do_scan(struct page **hpage) +{ + unsigned int progress = 0, pass_through_head = 0; + unsigned int pages = khugepaged_pages_to_scan; + + barrier(); /* write khugepaged_pages_to_scan to local stack */ + + while (progress < pages) { + cond_resched(); + + if (!*hpage) { + *hpage = alloc_hugepage(khugepaged_defrag()); + if (unlikely(!*hpage)) + break; + } + + spin_lock(&khugepaged_mm_lock); + if (!khugepaged_scan.mm_slot) + pass_through_head++; + if (khugepaged_has_work() && + pass_through_head < 2) + progress += khugepaged_scan_mm_slot(pages - progress, + hpage); + else + progress = pages; + spin_unlock(&khugepaged_mm_lock); + } +} + +static struct page *khugepaged_alloc_hugepage(void) +{ + struct page *hpage; + + do { + hpage = alloc_hugepage(khugepaged_defrag()); + if (!hpage) { + DEFINE_WAIT(wait); + add_wait_queue(&khugepaged_wait, &wait); + schedule_timeout_interruptible( + msecs_to_jiffies( + khugepaged_alloc_sleep_millisecs)); + remove_wait_queue(&khugepaged_wait, &wait); + } + } while (unlikely(!hpage) && + likely(khugepaged_enabled())); + return hpage; +} + +static void khugepaged_loop(void) +{ + struct page *hpage; + + while (likely(khugepaged_enabled())) { + hpage = khugepaged_alloc_hugepage(); + if (unlikely(!hpage)) + break; + + khugepaged_do_scan(&hpage); + if (hpage) + put_page(hpage); + if (khugepaged_has_work()) { + DEFINE_WAIT(wait); + if (!khugepaged_scan_sleep_millisecs) + continue; + add_wait_queue(&khugepaged_wait, &wait); + schedule_timeout_interruptible( + msecs_to_jiffies( + khugepaged_scan_sleep_millisecs)); + remove_wait_queue(&khugepaged_wait, &wait); + } else if (khugepaged_enabled()) + wait_event_interruptible(khugepaged_wait, + khugepaged_wait_event()); + } +} + +static int khugepaged(void *none) +{ + struct mm_slot *mm_slot; + + set_user_nice(current, 19); + + /* serialize with start_khugepaged() */ + mutex_lock(&khugepaged_mutex); + + for (;;) { + mutex_unlock(&khugepaged_mutex); + BUG_ON(khugepaged_thread != current); + khugepaged_loop(); + BUG_ON(khugepaged_thread != current); + + mutex_lock(&khugepaged_mutex); + if (!khugepaged_enabled()) + break; + } + + spin_lock(&khugepaged_mm_lock); + mm_slot = khugepaged_scan.mm_slot; + khugepaged_scan.mm_slot = NULL; + if (mm_slot) + collect_mm_slot(mm_slot); + spin_unlock(&khugepaged_mm_lock); + + khugepaged_thread = NULL; + mutex_unlock(&khugepaged_mutex); + + return 0; +} + void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd) { struct page *page; -- cgit v1.2.3-70-g09d2