From 77ed2c5745d93416992857d124f35834b62b3e70 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Tue, 8 Mar 2016 20:01:32 +0900 Subject: android,lowmemorykiller: Don't abuse TIF_MEMDIE. Currently, lowmemorykiller (LMK) is using TIF_MEMDIE for two purposes. One is to remember processes killed by LMK, and the other is to accelerate termination of processes killed by LMK. But since LMK is invoked as a memory shrinker function, there still should be some memory available. It is very likely that memory allocations by processes killed by LMK will succeed without using ALLOC_NO_WATERMARKS via TIF_MEMDIE. Even if their allocations cannot escape from memory allocation loop unless they use ALLOC_NO_WATERMARKS, lowmem_deathpending_timeout can guarantee forward progress by choosing next victim process. On the other hand, mark_oom_victim() assumes that it must be called with oom_lock held and it must not be called after oom_killer_disable() was called. But LMK is calling it without holding oom_lock and checking oom_killer_disabled. It is possible that LMK calls mark_oom_victim() due to allocation requests by kernel threads after current thread returned from oom_killer_disabled(). This will break synchronization for PM/suspend. This patch introduces per a task_struct flag for remembering processes killed by LMK, and replaces TIF_MEMDIE with that flag. By applying this patch, assumption by mark_oom_victim() becomes true. Signed-off-by: Tetsuo Handa Acked-by: Michal Hocko Cc: Arve Hjonnevag Cc: Riley Andrews Signed-off-by: Greg Kroah-Hartman --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 60bba7e032dc..9dff190e6a0a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2184,6 +2184,7 @@ static inline void memalloc_noio_restore(unsigned int flags) #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ +#define PFA_LMK_WAITING 3 /* Lowmemorykiller is waiting */ #define TASK_PFA_TEST(name, func) \ @@ -2207,6 +2208,9 @@ TASK_PFA_TEST(SPREAD_SLAB, spread_slab) TASK_PFA_SET(SPREAD_SLAB, spread_slab) TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) +TASK_PFA_TEST(LMK_WAITING, lmk_waiting) +TASK_PFA_SET(LMK_WAITING, lmk_waiting) + /* * task->jobctl flags */ -- cgit v1.2.3 From bb8a4b7fd1266ef888b3a80aa5f266062b224ef4 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 20 May 2016 16:57:18 -0700 Subject: mm, oom_reaper: hide oom reaped tasks from OOM killer more carefully Commit 36324a990cf5 ("oom: clear TIF_MEMDIE after oom_reaper managed to unmap the address space") not only clears TIF_MEMDIE for oom reaped task but also set OOM_SCORE_ADJ_MIN for the target task to hide it from the oom killer. This works in simple cases but it is not sufficient for (unlikely) cases where the mm is shared between independent processes (as they do not share signal struct). If the mm had only small amount of memory which could be reaped then another task sharing the mm could be selected and that wouldn't help to move out from the oom situation. Introduce MMF_OOM_REAPED mm flag which is checked in oom_badness (same as OOM_SCORE_ADJ_MIN) and task is skipped if the flag is set. Set the flag after __oom_reap_task is done with a task. This will force the select_bad_process() to ignore all already oom reaped tasks as well as no such task is sacrificed for its parent. Signed-off-by: Michal Hocko Cc: Tetsuo Handa Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + mm/oom_kill.c | 9 +++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 31bd0d97d178..40eabf176ce2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -521,6 +521,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HAS_UPROBES 19 /* has uprobes */ #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ +#define MMF_OOM_REAPED 21 /* mm has been already reaped */ #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 415f7eb913fa..c0376efa79ec 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -174,8 +174,13 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, if (!p) return 0; + /* + * Do not even consider tasks which are explicitly marked oom + * unkillable or have been already oom reaped. + */ adj = (long)p->signal->oom_score_adj; - if (adj == OOM_SCORE_ADJ_MIN) { + if (adj == OOM_SCORE_ADJ_MIN || + test_bit(MMF_OOM_REAPED, &p->mm->flags)) { task_unlock(p); return 0; } @@ -513,7 +518,7 @@ static bool __oom_reap_task(struct task_struct *tsk) * This task can be safely ignored because we cannot do much more * to release its memory. */ - tsk->signal->oom_score_adj = OOM_SCORE_ADJ_MIN; + set_bit(MMF_OOM_REAPED, &mm->flags); out: mmput(mm); return ret; -- cgit v1.2.3 From ec8d7c14ea14922fe21945b458a75e39f11dd832 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 20 May 2016 16:57:21 -0700 Subject: mm, oom_reaper: do not mmput synchronously from the oom reaper context Tetsuo has properly noted that mmput slow path might get blocked waiting for another party (e.g. exit_aio waits for an IO). If that happens the oom_reaper would be put out of the way and will not be able to process next oom victim. We should strive for making this context as reliable and independent on other subsystems as much as possible. Introduce mmput_async which will perform the slow path from an async (WQ) context. This will delay the operation but that shouldn't be a problem because the oom_reaper has reclaimed the victim's address space for most cases as much as possible and the remaining context shouldn't bind too much memory anymore. The only exception is when mmap_sem trylock has failed which shouldn't happen too often. The issue is only theoretical but not impossible. Signed-off-by: Michal Hocko Reported-by: Tetsuo Handa Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 ++ include/linux/sched.h | 5 +++++ kernel/fork.c | 50 +++++++++++++++++++++++++++++++++--------------- mm/oom_kill.c | 8 ++++++-- 4 files changed, 48 insertions(+), 17 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 1fda9c99ef95..d553855503e6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -513,6 +514,7 @@ struct mm_struct { #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif + struct work_struct async_put_work; }; static inline void mm_init_cpumask(struct mm_struct *mm) diff --git a/include/linux/sched.h b/include/linux/sched.h index 40eabf176ce2..479e3cade7e9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2730,6 +2730,11 @@ static inline void mmdrop(struct mm_struct * mm) /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); +/* same as above but performs the slow path from the async kontext. Can + * be called from the atomic context as well + */ +extern void mmput_async(struct mm_struct *); + /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); /* diff --git a/kernel/fork.c b/kernel/fork.c index 3e8451527cbe..8fbed7194af1 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -699,6 +699,26 @@ void __mmdrop(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(__mmdrop); +static inline void __mmput(struct mm_struct *mm) +{ + VM_BUG_ON(atomic_read(&mm->mm_users)); + + uprobe_clear_state(mm); + 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)) { + spin_lock(&mmlist_lock); + list_del(&mm->mmlist); + spin_unlock(&mmlist_lock); + } + if (mm->binfmt) + module_put(mm->binfmt->module); + mmdrop(mm); +} + /* * Decrement the use count and release all resources for an mm. */ @@ -706,24 +726,24 @@ void mmput(struct mm_struct *mm) { might_sleep(); + if (atomic_dec_and_test(&mm->mm_users)) + __mmput(mm); +} +EXPORT_SYMBOL_GPL(mmput); + +static void mmput_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); + __mmput(mm); +} + +void mmput_async(struct mm_struct *mm) +{ if (atomic_dec_and_test(&mm->mm_users)) { - uprobe_clear_state(mm); - 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)) { - spin_lock(&mmlist_lock); - list_del(&mm->mmlist); - spin_unlock(&mmlist_lock); - } - if (mm->binfmt) - module_put(mm->binfmt->module); - mmdrop(mm); + INIT_WORK(&mm->async_put_work, mmput_async_fn); + schedule_work(&mm->async_put_work); } } -EXPORT_SYMBOL_GPL(mmput); /** * set_mm_exe_file - change a reference to the mm's executable file diff --git a/mm/oom_kill.c b/mm/oom_kill.c index c0376efa79ec..c0e37dd1422f 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -446,7 +446,6 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait); static struct task_struct *oom_reaper_list; static DEFINE_SPINLOCK(oom_reaper_lock); - static bool __oom_reap_task(struct task_struct *tsk) { struct mmu_gather tlb; @@ -520,7 +519,12 @@ static bool __oom_reap_task(struct task_struct *tsk) */ set_bit(MMF_OOM_REAPED, &mm->flags); out: - mmput(mm); + /* + * Drop our reference but make sure the mmput slow path is called from a + * different context because we shouldn't risk we get stuck there and + * put the oom_reaper out of the way. + */ + mmput_async(mm); return ret; } -- cgit v1.2.3 From f44666b04605d1c7fd94ab90b7ccf633e7eff228 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 20 May 2016 16:57:27 -0700 Subject: mm,oom: speed up select_bad_process() loop Since commit 3a5dda7a17cf ("oom: prevent unnecessary oom kills or kernel panics"), select_bad_process() is using for_each_process_thread(). Since oom_unkillable_task() scans all threads in the caller's thread group and oom_task_origin() scans signal_struct of the caller's thread group, we don't need to call oom_unkillable_task() and oom_task_origin() on each thread. Also, since !mm test will be done later at oom_badness(), we don't need to do !mm test on each thread. Therefore, we only need to do TIF_MEMDIE test on each thread. Although the original code was correct it was quite inefficient because each thread group was scanned num_threads times which can be a lot especially with processes with many threads. Even though the OOM is extremely cold path it is always good to be as effective as possible when we are inside rcu_read_lock() - aka unpreemptible context. If we track number of TIF_MEMDIE threads inside signal_struct, we don't need to do TIF_MEMDIE test on each thread. This will allow select_bad_process() to use for_each_process(). This patch adds a counter to signal_struct for tracking how many TIF_MEMDIE threads are in a given thread group, and check it at oom_scan_process_thread() so that select_bad_process() can use for_each_process() rather than for_each_process_thread(). [mhocko@suse.com: do not blow the signal_struct size] Link: http://lkml.kernel.org/r/20160520075035.GF19172@dhcp22.suse.cz Link: http://lkml.kernel.org/r/201605182230.IDC73435.MVSOHLFOQFOJtF@I-love.SAKURA.ne.jp Signed-off-by: Tetsuo Handa Acked-by: Michal Hocko Cc: David Rientjes Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + mm/oom_kill.c | 17 ++++++----------- 2 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 479e3cade7e9..01fe1bb68754 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -669,6 +669,7 @@ struct signal_struct { atomic_t sigcnt; atomic_t live; int nr_threads; + atomic_t oom_victims; /* # of TIF_MEDIE threads in this thread group */ struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ diff --git a/mm/oom_kill.c b/mm/oom_kill.c index c0e37dd1422f..5bb2f7698ad7 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -283,12 +283,8 @@ enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, * This task already has access to memory reserves and is being killed. * Don't allow any other task to have access to the reserves. */ - if (test_tsk_thread_flag(task, TIF_MEMDIE)) { - if (!is_sysrq_oom(oc)) - return OOM_SCAN_ABORT; - } - if (!task->mm) - return OOM_SCAN_CONTINUE; + if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims)) + return OOM_SCAN_ABORT; /* * If task is allocating a lot of memory and has been marked to be @@ -307,12 +303,12 @@ enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, static struct task_struct *select_bad_process(struct oom_control *oc, unsigned int *ppoints, unsigned long totalpages) { - struct task_struct *g, *p; + struct task_struct *p; struct task_struct *chosen = NULL; unsigned long chosen_points = 0; rcu_read_lock(); - for_each_process_thread(g, p) { + for_each_process(p) { unsigned int points; switch (oom_scan_process_thread(oc, p, totalpages)) { @@ -331,9 +327,6 @@ static struct task_struct *select_bad_process(struct oom_control *oc, points = oom_badness(p, NULL, oc->nodemask, totalpages); if (!points || points < chosen_points) continue; - /* Prefer thread group leaders for display purposes */ - if (points == chosen_points && thread_group_leader(chosen)) - continue; chosen = p; chosen_points = points; @@ -673,6 +666,7 @@ void mark_oom_victim(struct task_struct *tsk) /* OOM killer might race with memcg OOM */ if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE)) return; + atomic_inc(&tsk->signal->oom_victims); /* * Make sure that the task is woken up from uninterruptible sleep * if it is frozen because OOM killer wouldn't be able to free @@ -690,6 +684,7 @@ void exit_oom_victim(struct task_struct *tsk) { if (!test_and_clear_tsk_thread_flag(tsk, TIF_MEMDIE)) return; + atomic_dec(&tsk->signal->oom_victims); if (!atomic_dec_return(&oom_victims)) wake_up_all(&oom_victims_wait); -- cgit v1.2.3 From d2005e3f41d4f9299e2df6a967c8beb5086967a9 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 20 May 2016 16:58:36 -0700 Subject: userfaultfd: don't pin the user memory in userfaultfd_file_create() userfaultfd_file_create() increments mm->mm_users; this means that the memory won't be unmapped/freed if mm owner exits/execs, and UFFDIO_COPY after that can populate the orphaned mm more. Change userfaultfd_file_create() and userfaultfd_ctx_put() to use mm->mm_count to pin mm_struct. This means that atomic_inc_not_zero(mm->mm_users) is needed when we are going to actually play with this memory. Except handle_userfault() path doesn't need this, the caller must already have a reference. The patch adds the new trivial helper, mmget_not_zero(), it can have more users. Link: http://lkml.kernel.org/r/20160516172254.GA8595@redhat.com Signed-off-by: Oleg Nesterov Cc: Andrea Arcangeli Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/userfaultfd.c | 41 ++++++++++++++++++++++++++++------------- include/linux/sched.h | 7 ++++++- 2 files changed, 34 insertions(+), 14 deletions(-) (limited to 'include/linux/sched.h') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 66cdb44616d5..2d97952e341a 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -137,7 +137,7 @@ static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx) VM_BUG_ON(waitqueue_active(&ctx->fault_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fd_wqh)); - mmput(ctx->mm); + mmdrop(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); } } @@ -434,6 +434,9 @@ static int userfaultfd_release(struct inode *inode, struct file *file) ACCESS_ONCE(ctx->released) = true; + if (!mmget_not_zero(mm)) + goto wakeup; + /* * Flush page faults out of all CPUs. NOTE: all page faults * must be retried without returning VM_FAULT_SIGBUS if @@ -466,7 +469,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } up_write(&mm->mmap_sem); - + mmput(mm); +wakeup: /* * After no new page faults can wait on this fault_*wqh, flush * the last page faults that may have been already waiting on @@ -760,10 +764,12 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, start = uffdio_register.range.start; end = start + uffdio_register.range.len; + ret = -ENOMEM; + if (!mmget_not_zero(mm)) + goto out; + down_write(&mm->mmap_sem); vma = find_vma_prev(mm, start, &prev); - - ret = -ENOMEM; if (!vma) goto out_unlock; @@ -864,6 +870,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, } while (vma && vma->vm_start < end); out_unlock: up_write(&mm->mmap_sem); + mmput(mm); if (!ret) { /* * Now that we scanned all vmas we can already tell @@ -902,10 +909,12 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, start = uffdio_unregister.start; end = start + uffdio_unregister.len; + ret = -ENOMEM; + if (!mmget_not_zero(mm)) + goto out; + down_write(&mm->mmap_sem); vma = find_vma_prev(mm, start, &prev); - - ret = -ENOMEM; if (!vma) goto out_unlock; @@ -998,6 +1007,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, } while (vma && vma->vm_start < end); out_unlock: up_write(&mm->mmap_sem); + mmput(mm); out: return ret; } @@ -1067,9 +1077,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, goto out; if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE) goto out; - - ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src, - uffdio_copy.len); + if (mmget_not_zero(ctx->mm)) { + ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src, + uffdio_copy.len); + mmput(ctx->mm); + } if (unlikely(put_user(ret, &user_uffdio_copy->copy))) return -EFAULT; if (ret < 0) @@ -1110,8 +1122,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE) goto out; - ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start, - uffdio_zeropage.range.len); + if (mmget_not_zero(ctx->mm)) { + ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start, + uffdio_zeropage.range.len); + mmput(ctx->mm); + } if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) return -EFAULT; if (ret < 0) @@ -1289,12 +1304,12 @@ static struct file *userfaultfd_file_create(int flags) ctx->released = false; ctx->mm = current->mm; /* prevent the mm struct to be freed */ - atomic_inc(&ctx->mm->mm_users); + atomic_inc(&ctx->mm->mm_count); file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, ctx, O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS)); if (IS_ERR(file)) { - mmput(ctx->mm); + mmdrop(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); } out: diff --git a/include/linux/sched.h b/include/linux/sched.h index 01fe1bb68754..6b3213d96da6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2723,12 +2723,17 @@ extern struct mm_struct * mm_alloc(void); /* mmdrop drops the mm and the page tables */ extern void __mmdrop(struct mm_struct *); -static inline void mmdrop(struct mm_struct * mm) +static inline void mmdrop(struct mm_struct *mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } +static inline bool mmget_not_zero(struct mm_struct *mm) +{ + return atomic_inc_not_zero(&mm->mm_users); +} + /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); /* same as above but performs the slow path from the async kontext. Can -- cgit v1.2.3 From 5f56a5dfdb9bcb3bca03df59980d4d2f012cbb53 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 20 May 2016 17:00:16 -0700 Subject: exit_thread: remove empty bodies Define HAVE_EXIT_THREAD for archs which want to do something in exit_thread. For others, let's define exit_thread as an empty inline. This is a cleanup before we change the prototype of exit_thread to accept a task parameter. [akpm@linux-foundation.org: fix mips] Signed-off-by: Jiri Slaby Cc: "David S. Miller" Cc: "H. Peter Anvin" Cc: "James E.J. Bottomley" Cc: Aurelien Jacquiot Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Chen Liqin Cc: Chris Metcalf Cc: Chris Zankel Cc: David Howells Cc: Fenghua Yu Cc: Geert Uytterhoeven Cc: Guan Xuetao Cc: Haavard Skinnemoen Cc: Hans-Christian Egtvedt Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: James Hogan Cc: Jeff Dike Cc: Jesper Nilsson Cc: Jiri Slaby Cc: Jonas Bonn Cc: Koichi Yasutake Cc: Lennox Wu Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Mikael Starvik Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Rich Felker Cc: Richard Henderson Cc: Richard Kuo Cc: Richard Weinberger Cc: Russell King Cc: Steven Miao Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/Kconfig | 5 +++++ arch/alpha/kernel/process.c | 8 -------- arch/arc/kernel/process.c | 7 ------- arch/arm/Kconfig | 1 + arch/arm64/kernel/process.c | 7 ------- arch/avr32/Kconfig | 1 + arch/blackfin/include/asm/processor.h | 7 ------- arch/c6x/kernel/process.c | 4 ---- arch/cris/Kconfig | 1 + arch/cris/arch-v10/kernel/process.c | 9 --------- arch/frv/include/asm/processor.h | 7 ------- arch/h8300/include/asm/processor.h | 7 ------- arch/hexagon/kernel/process.c | 7 ------- arch/ia64/Kconfig | 1 + arch/m32r/kernel/process.c | 9 --------- arch/m68k/include/asm/processor.h | 7 ------- arch/metag/Kconfig | 1 + arch/metag/include/asm/processor.h | 2 -- arch/microblaze/include/asm/processor.h | 10 ---------- arch/mips/kernel/process.c | 4 ---- arch/mn10300/Kconfig | 1 + arch/nios2/include/asm/processor.h | 5 ----- arch/openrisc/include/asm/processor.h | 9 --------- arch/parisc/kernel/process.c | 7 ------- arch/powerpc/kernel/process.c | 4 ---- arch/s390/Kconfig | 1 + arch/score/kernel/process.c | 2 -- arch/sh/Kconfig | 1 + arch/sh/kernel/process_32.c | 7 ------- arch/sparc/Kconfig | 1 + arch/tile/Kconfig | 1 + arch/um/kernel/process.c | 4 ---- arch/unicore32/kernel/process.c | 7 ------- arch/x86/Kconfig | 1 + arch/xtensa/Kconfig | 1 + include/linux/sched.h | 7 +++++++ 36 files changed, 24 insertions(+), 140 deletions(-) (limited to 'include/linux/sched.h') diff --git a/arch/Kconfig b/arch/Kconfig index 81869a5e7e17..0f298f9123dc 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -517,6 +517,11 @@ config HAVE_ARCH_MMAP_RND_BITS - ARCH_MMAP_RND_BITS_MIN - ARCH_MMAP_RND_BITS_MAX +config HAVE_EXIT_THREAD + bool + help + An architecture implements exit_thread. + config ARCH_MMAP_RND_BITS_MIN int diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 84d13263ce46..b483156698d5 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -210,14 +210,6 @@ start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp) } EXPORT_SYMBOL(start_thread); -/* - * Free current thread data structures etc.. - */ -void -exit_thread(void) -{ -} - void flush_thread(void) { diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index a3f750e76b68..b5db9e7fd649 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -183,13 +183,6 @@ void flush_thread(void) { } -/* - * Free any architecture-specific thread data structures, etc. - */ -void exit_thread(void) -{ -} - int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) { return 0; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index b99d25b4133e..956d3575426c 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -50,6 +50,7 @@ config ARM select HAVE_DMA_CONTIGUOUS if MMU select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL) && !CPU_ENDIAN_BE32 && MMU select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU + select HAVE_EXIT_THREAD select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL) select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL) select HAVE_FUNCTION_TRACER if (!XIP_KERNEL) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 48eea6866c67..6cd2612236dc 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -200,13 +200,6 @@ void show_regs(struct pt_regs * regs) __show_regs(regs); } -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ -} - static void tls_thread_flush(void) { asm ("msr tpidr_el0, xzr"); diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig index 18b88779e701..e43519a2ca89 100644 --- a/arch/avr32/Kconfig +++ b/arch/avr32/Kconfig @@ -4,6 +4,7 @@ config AVR32 # that we usually don't need on AVR32. select EXPERT select HAVE_CLK + select HAVE_EXIT_THREAD select HAVE_OPROFILE select HAVE_KPROBES select VIRT_TO_BUS diff --git a/arch/blackfin/include/asm/processor.h b/arch/blackfin/include/asm/processor.h index 7acd46653df3..0c265aba94ad 100644 --- a/arch/blackfin/include/asm/processor.h +++ b/arch/blackfin/include/asm/processor.h @@ -75,13 +75,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* - * Free current thread data structures etc.. - */ -static inline void exit_thread(void) -{ -} - /* * Return saved PC of a blocked thread. */ diff --git a/arch/c6x/kernel/process.c b/arch/c6x/kernel/process.c index 3ae9f5a166a0..0ee7686a78f3 100644 --- a/arch/c6x/kernel/process.c +++ b/arch/c6x/kernel/process.c @@ -82,10 +82,6 @@ void flush_thread(void) { } -void exit_thread(void) -{ -} - /* * Do necessary setup to start up a newly executed thread. */ diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig index 99bda1ba3d2f..5c0ca8ae9293 100644 --- a/arch/cris/Kconfig +++ b/arch/cris/Kconfig @@ -59,6 +59,7 @@ config CRIS select GENERIC_IOMAP select MODULES_USE_ELF_RELA select CLONE_BACKWARDS2 + select HAVE_EXIT_THREAD if ETRAX_ARCH_V32 select OLD_SIGSUSPEND select OLD_SIGACTION select GPIOLIB diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c index 02b783457be0..96e5afef6b47 100644 --- a/arch/cris/arch-v10/kernel/process.c +++ b/arch/cris/arch-v10/kernel/process.c @@ -35,15 +35,6 @@ void default_idle(void) local_irq_enable(); } -/* - * Free current thread data structures etc.. - */ - -void exit_thread(void) -{ - /* Nothing needs to be done. */ -} - /* if the watchdog is enabled, we can simply disable interrupts and go * into an eternal loop, and the watchdog will reset the CPU after 0.1s * if on the other hand the watchdog wasn't enabled, we just enable it and wait diff --git a/arch/frv/include/asm/processor.h b/arch/frv/include/asm/processor.h index ae8d423e79d9..73f0a79ad8e6 100644 --- a/arch/frv/include/asm/processor.h +++ b/arch/frv/include/asm/processor.h @@ -96,13 +96,6 @@ extern asmlinkage void *restore_user_regs(const struct user_context *target, ... #define release_segments(mm) do { } while (0) #define forget_segments() do { } while (0) -/* - * Free current thread data structures etc.. - */ -static inline void exit_thread(void) -{ -} - /* * Return saved PC of a blocked thread. */ diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h index 54e3fd83c336..111df7397ac7 100644 --- a/arch/h8300/include/asm/processor.h +++ b/arch/h8300/include/asm/processor.h @@ -110,13 +110,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* - * Free current thread data structures etc.. - */ -static inline void exit_thread(void) -{ -} - /* * Return saved PC of a blocked thread. */ diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index a9ebd471823a..d9edfd3fc52a 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -136,13 +136,6 @@ void release_thread(struct task_struct *dead_task) { } -/* - * Free any architecture-specific thread data structures, etc. - */ -void exit_thread(void) -{ -} - /* * Some archs flush debug and FPU info here */ diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index b534ebab36ea..f80758cb7157 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -18,6 +18,7 @@ config IA64 select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select HAVE_UNSTABLE_SCHED_CLOCK + select HAVE_EXIT_THREAD select HAVE_IDE select HAVE_OPROFILE select HAVE_KPROBES diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index e69221d581d5..a88b1f01e91f 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -101,15 +101,6 @@ void show_regs(struct pt_regs * regs) #endif } -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ - /* Nothing to do. */ - DPRINTK("pid = %d\n", current->pid); -} - void flush_thread(void) { DPRINTK("pid = %d\n", current->pid); diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index 20dda1d4b860..a6ce2ec8d693 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -153,13 +153,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* - * Free current thread data structures etc.. - */ -static inline void exit_thread(void) -{ -} - extern unsigned long thread_saved_pc(struct task_struct *tsk); unsigned long get_wchan(struct task_struct *p); diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig index a0fa88da3e31..e47a08d72819 100644 --- a/arch/metag/Kconfig +++ b/arch/metag/Kconfig @@ -11,6 +11,7 @@ config METAG select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_STACKOVERFLOW select HAVE_DYNAMIC_FTRACE + select HAVE_EXIT_THREAD select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_TRACER select HAVE_KERNEL_BZIP2 diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h index 0838ca699764..a0333ebcac35 100644 --- a/arch/metag/include/asm/processor.h +++ b/arch/metag/include/asm/processor.h @@ -134,8 +134,6 @@ static inline void release_thread(struct task_struct *dead_task) #define copy_segments(tsk, mm) do { } while (0) #define release_segments(mm) do { } while (0) -extern void exit_thread(void); - /* * Return saved PC of a blocked thread. */ diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h index 497a988d79c2..c38d0dd91134 100644 --- a/arch/microblaze/include/asm/processor.h +++ b/arch/microblaze/include/asm/processor.h @@ -70,11 +70,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* Free all resources held by a thread. */ -static inline void exit_thread(void) -{ -} - extern unsigned long thread_saved_pc(struct task_struct *t); extern unsigned long get_wchan(struct task_struct *p); @@ -127,11 +122,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* Free current thread data structures etc. */ -static inline void exit_thread(void) -{ -} - /* Return saved (kernel) PC of a blocked thread. */ # define thread_saved_pc(tsk) \ ((tsk)->thread.regs ? (tsk)->thread.regs->r15 : 0) diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index a6b3dc54260a..411c971e3417 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -73,10 +73,6 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp) regs->regs[29] = sp; } -void exit_thread(void) -{ -} - int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { /* diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig index 06ddb5501ab1..9627e81a6cbb 100644 --- a/arch/mn10300/Kconfig +++ b/arch/mn10300/Kconfig @@ -1,5 +1,6 @@ config MN10300 def_bool y + select HAVE_EXIT_THREAD select HAVE_OPROFILE select HAVE_UID16 select GENERIC_IRQ_SHOW diff --git a/arch/nios2/include/asm/processor.h b/arch/nios2/include/asm/processor.h index c2ba45c159c7..1c953f0cadbf 100644 --- a/arch/nios2/include/asm/processor.h +++ b/arch/nios2/include/asm/processor.h @@ -75,11 +75,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* Free current thread data structures etc.. */ -static inline void exit_thread(void) -{ -} - /* Return saved PC of a blocked thread. */ #define thread_saved_pc(tsk) ((tsk)->thread.kregs->ea) diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h index 4d235e3d2534..70334c9f7d24 100644 --- a/arch/openrisc/include/asm/processor.h +++ b/arch/openrisc/include/asm/processor.h @@ -84,15 +84,6 @@ void start_thread(struct pt_regs *regs, unsigned long nip, unsigned long sp); void release_thread(struct task_struct *); unsigned long get_wchan(struct task_struct *p); -/* - * Free current thread data structures etc.. - */ - -extern inline void exit_thread(void) -{ - /* Nothing needs to be done. */ -} - /* * Return saved PC of a blocked thread. For now, this is the "user" PC */ diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 809905a811ed..40639439d8b3 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -144,13 +144,6 @@ void machine_power_off(void) void (*pm_power_off)(void) = machine_power_off; EXPORT_SYMBOL(pm_power_off); -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ -} - void flush_thread(void) { /* Only needs to handle fpu stuff or perf monitors. diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index ea8a28fd6f31..e2f12cbcade9 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1329,10 +1329,6 @@ void show_regs(struct pt_regs * regs) show_instructions(regs); } -void exit_thread(void) -{ -} - void flush_thread(void) { #ifdef CONFIG_HAVE_HW_BREAKPOINT diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index de0fcc08dff5..e2c9aaaf64b2 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -134,6 +134,7 @@ config S390 select HAVE_DMA_API_DEBUG select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS + select HAVE_EXIT_THREAD select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c index a1519ad3d49d..aae9480706c2 100644 --- a/arch/score/kernel/process.c +++ b/arch/score/kernel/process.c @@ -56,8 +56,6 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) regs->regs[0] = sp; } -void exit_thread(void) {} - /* * When a process does an "exec", machine state like FPU and debug * registers need to be reset. This is a hook function for that. diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 7ed20fc3fc81..cb93af8f8017 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -71,6 +71,7 @@ config SUPERH32 config SUPERH64 def_bool ARCH = "sh64" + select HAVE_EXIT_THREAD select KALLSYMS config ARCH_DEFCONFIG diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 2885fc9d9dcd..ee12e9451874 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -76,13 +76,6 @@ void start_thread(struct pt_regs *regs, unsigned long new_pc, } EXPORT_SYMBOL(start_thread); -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ -} - void flush_thread(void) { struct task_struct *tsk = current; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index db0a26cffa97..27b3a0ad40a0 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -20,6 +20,7 @@ config SPARC select HAVE_OPROFILE select HAVE_ARCH_KGDB if !SMP || SPARC64 select HAVE_ARCH_TRACEHOOK + select HAVE_EXIT_THREAD select SYSCTL_EXCEPTION_TRACE select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select RTC_CLASS diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 81719302b056..174746225577 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -3,6 +3,7 @@ config TILE def_bool y + select HAVE_EXIT_THREAD select HAVE_PERF_EVENTS select USE_PMC if PERF_EVENTS select HAVE_DMA_API_DEBUG diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 48af59aae129..0b04711f1f18 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -103,10 +103,6 @@ void interrupt_end(void) tracehook_notify_resume(regs); } -void exit_thread(void) -{ -} - int get_current_pid(void) { return task_pid_nr(current); diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c index b008e9961465..00299c927852 100644 --- a/arch/unicore32/kernel/process.c +++ b/arch/unicore32/kernel/process.c @@ -201,13 +201,6 @@ void show_regs(struct pt_regs *regs) __backtrace(); } -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ -} - void flush_thread(void) { struct thread_info *thread = current_thread_info(); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ace79d2da2c3..8ff5b3be95d4 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -105,6 +105,7 @@ config X86 select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EFFICIENT_UNALIGNED_ACCESS + select HAVE_EXIT_THREAD select HAVE_FENTRY if X86_64 select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_FP_TEST diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 85257afe71c3..64336f666fb6 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -14,6 +14,7 @@ config XTENSA select GENERIC_PCI_IOMAP select GENERIC_SCHED_CLOCK select HAVE_DMA_API_DEBUG + select HAVE_EXIT_THREAD select HAVE_FUNCTION_TRACER select HAVE_FUTEX_CMPXCHG if !MMU select HAVE_HW_BREAKPOINT if PERF_EVENTS diff --git a/include/linux/sched.h b/include/linux/sched.h index 6b3213d96da6..167c0d4bf3fa 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2769,7 +2769,14 @@ static inline int copy_thread_tls( } #endif extern void flush_thread(void); + +#ifdef CONFIG_HAVE_EXIT_THREAD extern void exit_thread(void); +#else +static inline void exit_thread(void) +{ +} +#endif extern void exit_files(struct task_struct *); extern void __cleanup_sighand(struct sighand_struct *); -- cgit v1.2.3 From e64646946ed32902fd597fa6e514b1da84642de3 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 20 May 2016 17:00:20 -0700 Subject: exit_thread: accept a task parameter to be exited We need to call exit_thread from copy_process in a fail path. So make it accept task_struct as a parameter. [v2] * s390: exit_thread_runtime_instr doesn't make sense to be called for non-current tasks. * arm: fix the comment in vfp_thread_copy * change 'me' to 'tsk' for task_struct * now we can change only archs that actually have exit_thread [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Jiri Slaby Cc: "David S. Miller" Cc: "H. Peter Anvin" Cc: "James E.J. Bottomley" Cc: Aurelien Jacquiot Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Chen Liqin Cc: Chris Metcalf Cc: Chris Zankel Cc: David Howells Cc: Fenghua Yu Cc: Geert Uytterhoeven Cc: Guan Xuetao Cc: Haavard Skinnemoen Cc: Hans-Christian Egtvedt Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: James Hogan Cc: Jeff Dike Cc: Jesper Nilsson Cc: Jiri Slaby Cc: Jonas Bonn Cc: Koichi Yasutake Cc: Lennox Wu Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Mikael Starvik Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Rich Felker Cc: Richard Henderson Cc: Richard Kuo Cc: Richard Weinberger Cc: Russell King Cc: Steven Miao Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/kernel/process.c | 4 ++-- arch/arm/vfp/vfpmodule.c | 4 ---- arch/avr32/kernel/process.c | 4 ++-- arch/cris/arch-v32/kernel/process.c | 4 ++-- arch/ia64/kernel/perfmon.c | 4 ++-- arch/ia64/kernel/process.c | 14 +++++++------- arch/metag/kernel/process.c | 6 +++--- arch/mn10300/kernel/process.c | 4 ++-- arch/s390/kernel/process.c | 5 +++-- arch/sh/kernel/process_64.c | 5 ++--- arch/sparc/kernel/process_32.c | 12 ++++++------ arch/sparc/kernel/process_64.c | 4 ++-- arch/tile/kernel/process.c | 4 ++-- arch/x86/kernel/process.c | 5 ++--- arch/xtensa/kernel/process.c | 4 ++-- include/linux/sched.h | 4 ++-- kernel/exit.c | 2 +- 17 files changed, 42 insertions(+), 47 deletions(-) (limited to 'include/linux/sched.h') diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 4adfb46e3ee9..a647d6642f3e 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -193,9 +193,9 @@ EXPORT_SYMBOL_GPL(thread_notify_head); /* * Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - thread_notify(THREAD_NOTIFY_EXIT, current_thread_info()); + thread_notify(THREAD_NOTIFY_EXIT, task_thread_info(tsk)); } void flush_thread(void) diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 2a61e4b04600..73085d3482ed 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -156,10 +156,6 @@ static void vfp_thread_copy(struct thread_info *thread) * - we could be preempted if tree preempt rcu is enabled, so * it is unsafe to use thread->cpu. * THREAD_NOTIFY_EXIT - * - the thread (v) will be running on the local CPU, so - * v === current_thread_info() - * - thread->cpu is the local CPU number at the time it is accessed, - * but may change at any time. * - we could be preempted if tree preempt rcu is enabled, so * it is unsafe to use thread->cpu. */ diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index 42a53e740a7e..68e5b9dac059 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -62,9 +62,9 @@ void machine_restart(char *cmd) /* * Free current thread data structures etc */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - ocd_disable(current); + ocd_disable(tsk); } void flush_thread(void) diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c index c7ce784a393c..4d1afa9f9fd3 100644 --- a/arch/cris/arch-v32/kernel/process.c +++ b/arch/cris/arch-v32/kernel/process.c @@ -33,9 +33,9 @@ void default_idle(void) */ extern void deconfigure_bp(long pid); -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - deconfigure_bp(current->pid); + deconfigure_bp(tsk->pid); } /* diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 9cd607b06964..2436ad5f92c1 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -4542,8 +4542,8 @@ pfm_context_unload(pfm_context_t *ctx, void *arg, int count, struct pt_regs *reg /* - * called only from exit_thread(): task == current - * we come here only if current has a context attached (loaded or masked) + * called only from exit_thread() + * we come here only if the task has a context attached (loaded or masked) */ void pfm_exit_thread(struct task_struct *task) diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index b51514957620..aae6c4dc7ae7 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -570,22 +570,22 @@ flush_thread (void) } /* - * Clean up state associated with current thread. This is called when + * Clean up state associated with a thread. This is called when * the thread calls exit(). */ void -exit_thread (void) +exit_thread (struct task_struct *tsk) { - ia64_drop_fpu(current); + ia64_drop_fpu(tsk); #ifdef CONFIG_PERFMON /* if needed, stop monitoring and flush state to perfmon context */ - if (current->thread.pfm_context) - pfm_exit_thread(current); + if (tsk->thread.pfm_context) + pfm_exit_thread(tsk); /* free debug register resources */ - if (current->thread.flags & IA64_THREAD_DBG_VALID) - pfm_release_debug_registers(current); + if (tsk->thread.flags & IA64_THREAD_DBG_VALID) + pfm_release_debug_registers(tsk); #endif } diff --git a/arch/metag/kernel/process.c b/arch/metag/kernel/process.c index 7f546183a0f0..35062796edf2 100644 --- a/arch/metag/kernel/process.c +++ b/arch/metag/kernel/process.c @@ -345,10 +345,10 @@ void flush_thread(void) /* * Free current thread data structures etc. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - clear_fpu(¤t->thread); - clear_dsp(¤t->thread); + clear_fpu(&tsk->thread); + clear_dsp(&tsk->thread); } /* TODO: figure out how to unwind the kernel stack here to figure out diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 74a96ccf7451..cbede4e88dee 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -103,9 +103,9 @@ void show_regs(struct pt_regs *regs) /* * free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - exit_fpu(current); + exit_fpu(tsk); } void flush_thread(void) diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 481d7a83efc6..bba4fa74b321 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -68,9 +68,10 @@ extern void kernel_thread_starter(void); /* * Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - exit_thread_runtime_instr(); + if (tsk == current) + exit_thread_runtime_instr(); } void flush_thread(void) diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c index e2062e643341..9d3e9916555d 100644 --- a/arch/sh/kernel/process_64.c +++ b/arch/sh/kernel/process_64.c @@ -288,7 +288,7 @@ void show_regs(struct pt_regs *regs) /* * Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { /* * See arch/sparc/kernel/process.c for the precedent for doing @@ -307,9 +307,8 @@ void exit_thread(void) * which it would get safely nulled. */ #ifdef CONFIG_SH_FPU - if (last_task_used_math == current) { + if (last_task_used_math == tsk) last_task_used_math = NULL; - } #endif } diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index c5113c7ce2fd..b7780a5bef11 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -184,21 +184,21 @@ unsigned long thread_saved_pc(struct task_struct *tsk) /* * Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { #ifndef CONFIG_SMP - if(last_task_used_math == current) { + if (last_task_used_math == tsk) { #else - if (test_thread_flag(TIF_USEDFPU)) { + if (test_ti_thread_flag(task_thread_info(tsk), TIF_USEDFPU)) { #endif /* Keep process from leaving FPU in a bogon state. */ put_psr(get_psr() | PSR_EF); - fpsave(¤t->thread.float_regs[0], ¤t->thread.fsr, - ¤t->thread.fpqueue[0], ¤t->thread.fpqdepth); + fpsave(&tsk->thread.float_regs[0], &tsk->thread.fsr, + &tsk->thread.fpqueue[0], &tsk->thread.fpqdepth); #ifndef CONFIG_SMP last_task_used_math = NULL; #else - clear_thread_flag(TIF_USEDFPU); + clear_ti_thread_flag(task_thread_info(tsk), TIF_USEDFPU); #endif } } diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index c16ef1af1843..fa14402b33f9 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -417,9 +417,9 @@ unsigned long thread_saved_pc(struct task_struct *tsk) } /* Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - struct thread_info *t = current_thread_info(); + struct thread_info *t = task_thread_info(tsk); if (t->utraps) { if (t->utraps[0] < 2) diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index b5f30d376ce1..6b705ccc9cc1 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -541,7 +541,7 @@ void flush_thread(void) /* * Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { #ifdef CONFIG_HARDWALL /* @@ -550,7 +550,7 @@ void exit_thread(void) * the last reference to a hardwall fd, it would already have * been released and deactivated at this point.) */ - hardwall_deactivate_all(current); + hardwall_deactivate_all(tsk); #endif } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 2915d54e9dd5..96becbbb52e0 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -97,10 +97,9 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) /* * Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - struct task_struct *me = current; - struct thread_struct *t = &me->thread; + struct thread_struct *t = &tsk->thread; unsigned long *bp = t->io_bitmap_ptr; struct fpu *fpu = &t->fpu; diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 5bbfed81c97b..e0ded48561db 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -115,10 +115,10 @@ void arch_cpu_idle(void) /* * This is called when the thread calls exit(). */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { #if XTENSA_HAVE_COPROCESSORS - coprocessor_release_all(current_thread_info()); + coprocessor_release_all(task_thread_info(tsk)); #endif } diff --git a/include/linux/sched.h b/include/linux/sched.h index 167c0d4bf3fa..02bdab4d6db7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2771,9 +2771,9 @@ static inline int copy_thread_tls( extern void flush_thread(void); #ifdef CONFIG_HAVE_EXIT_THREAD -extern void exit_thread(void); +extern void exit_thread(struct task_struct *tsk); #else -static inline void exit_thread(void) +static inline void exit_thread(struct task_struct *tsk) { } #endif diff --git a/kernel/exit.c b/kernel/exit.c index fd90195667e1..75b34fe835b2 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -746,7 +746,7 @@ void do_exit(long code) disassociate_ctty(1); exit_task_namespaces(tsk); exit_task_work(tsk); - exit_thread(); + exit_thread(tsk); /* * Flush inherited counters to the parent - before the parent -- cgit v1.2.3 From c96fc2d85f4a827e3bb2abe7de2394a1fb8a0fe7 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 23 May 2016 16:23:57 -0700 Subject: signal: make oom_flags a bool Currently the size of "struct signal_struct"->oom_flags member is sizeof(unsigned) bytes, but only one flag OOM_FLAG_ORIGIN which is updated by current thread is defined. We can convert OOM_FLAG_ORIGIN into a bool, and reuse the saved bytes for updating from the OOM killer and/or the OOM reaper thread. By the way, do we care about a race window between run_store() and swapoff() because it would be theoretically possible that two threads sharing the "struct signal_struct" concurrently call respective functions? If we care, we can make oom_flags an atomic_t. Signed-off-by: Tetsuo Handa Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 9 +++------ include/linux/sched.h | 6 +++++- include/linux/types.h | 1 - 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/oom.h b/include/linux/oom.h index d3f533f2f481..83469522690a 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -50,24 +50,21 @@ enum oom_scan_t { OOM_SCAN_SELECT, /* always select this thread first */ }; -/* Thread is the potential origin of an oom condition; kill first on oom */ -#define OOM_FLAG_ORIGIN ((__force oom_flags_t)0x1) - extern struct mutex oom_lock; static inline void set_current_oom_origin(void) { - current->signal->oom_flags |= OOM_FLAG_ORIGIN; + current->signal->oom_flag_origin = true; } static inline void clear_current_oom_origin(void) { - current->signal->oom_flags &= ~OOM_FLAG_ORIGIN; + current->signal->oom_flag_origin = false; } static inline bool oom_task_origin(const struct task_struct *p) { - return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN); + return p->signal->oom_flag_origin; } extern void mark_oom_victim(struct task_struct *tsk); diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c036de6c1ee..21c26e78aec5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -794,7 +794,11 @@ struct signal_struct { struct tty_audit_buf *tty_audit_buf; #endif - oom_flags_t oom_flags; + /* + * Thread is the potential origin of an oom condition; kill first on + * oom + */ + bool oom_flag_origin; short oom_score_adj; /* OOM kill score adjustment */ short oom_score_adj_min; /* OOM kill score adjustment min value. * Only settable by CAP_SYS_RESOURCE. */ diff --git a/include/linux/types.h b/include/linux/types.h index 70dd3dfde631..baf718324f4a 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -156,7 +156,6 @@ typedef u32 dma_addr_t; typedef unsigned __bitwise__ gfp_t; typedef unsigned __bitwise__ fmode_t; -typedef unsigned __bitwise__ oom_flags_t; #ifdef CONFIG_PHYS_ADDR_T_64BIT typedef u64 phys_addr_t; -- cgit v1.2.3 From b7e7ade34e6188bee2e3b0d42b51d25137d9e2a5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 23 May 2016 11:19:07 +0200 Subject: sched/core: Fix remote wakeups Commit: b5179ac70de8 ("sched/fair: Prepare to fix fairness problems on migration") ... introduced a bug: Mike Galbraith found that it introduced a performance regression, while Paul E. McKenney reported lost wakeups and bisected it to this commit. The reason is that I mis-read ttwu_queue() such that I assumed any wakeup that got a remote queue must have had the task migrated. Since this is not so; we need to transfer this information between queueing the wakeup and actually doing the wakeup. Use a new task_struct::sched_flag for this, we already write to sched_contributes_to_load in the wakeup path so this is a hot and modified cacheline. Reported-by: Paul E. McKenney Reported-by: Mike Galbraith Tested-by: Mike Galbraith Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Hunter Cc: Andy Lutomirski Cc: Ben Segall Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Matt Fleming Cc: Morten Rasmussen Cc: Oleg Nesterov Cc: Paul Turner Cc: Pavan Kondeti Cc: Peter Zijlstra Cc: Quentin Casasnovas Cc: Thomas Gleixner Cc: byungchul.park@lge.com Fixes: b5179ac70de8 ("sched/fair: Prepare to fix fairness problems on migration") Link: http://lkml.kernel.org/r/20160523091907.GD15728@worktop.ger.corp.intel.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + kernel/sched/core.c | 18 +++++++++++------- 2 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6cc0df970f1a..e053517a88b6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1533,6 +1533,7 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; + unsigned sched_remote_wakeup:1; unsigned :0; /* force alignment to the next boundary */ /* unserialized, strictly 'current' */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 404c0784b1fc..7f2cae4620c7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1768,13 +1768,15 @@ void sched_ttwu_pending(void) cookie = lockdep_pin_lock(&rq->lock); while (llist) { + int wake_flags = 0; + p = llist_entry(llist, struct task_struct, wake_entry); llist = llist_next(llist); - /* - * See ttwu_queue(); we only call ttwu_queue_remote() when - * its a x-cpu wakeup. - */ - ttwu_do_activate(rq, p, WF_MIGRATED, cookie); + + if (p->sched_remote_wakeup) + wake_flags = WF_MIGRATED; + + ttwu_do_activate(rq, p, wake_flags, cookie); } lockdep_unpin_lock(&rq->lock, cookie); @@ -1819,10 +1821,12 @@ void scheduler_ipi(void) irq_exit(); } -static void ttwu_queue_remote(struct task_struct *p, int cpu) +static void ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags) { struct rq *rq = cpu_rq(cpu); + p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED); + if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) { if (!set_nr_if_polling(rq->idle)) smp_send_reschedule(cpu); @@ -1869,7 +1873,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) #if defined(CONFIG_SMP) if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { sched_clock_cpu(cpu); /* sync clocks x-cpu */ - ttwu_queue_remote(p, cpu); + ttwu_queue_remote(p, cpu, wake_flags); return; } #endif -- cgit v1.2.3 From 7ef949d77f95f0d129f0d404b336459a34a00101 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 26 May 2016 15:16:22 -0700 Subject: mm: oom_reaper: remove some bloat mmput_async is currently used only from the oom_reaper which is defined only for CONFIG_MMU. We can save work_struct in mm_struct for !CONFIG_MMU. [akpm@linux-foundation.org: fix typo, per Minchan] Link: http://lkml.kernel.org/r/20160520061658.GB19172@dhcp22.suse.cz Reported-by: Minchan Kim Signed-off-by: Michal Hocko Acked-by: Minchan Kim Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 ++ include/linux/sched.h | 4 +++- kernel/fork.c | 2 ++ 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index d553855503e6..ca3e517980a0 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -514,7 +514,9 @@ struct mm_struct { #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif +#ifdef CONFIG_MMU struct work_struct async_put_work; +#endif }; static inline void mm_init_cpumask(struct mm_struct *mm) diff --git a/include/linux/sched.h b/include/linux/sched.h index 23e075dcdfe4..6e42ada26345 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2745,10 +2745,12 @@ static inline bool mmget_not_zero(struct mm_struct *mm) /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); -/* same as above but performs the slow path from the async kontext. Can +#ifdef CONFIG_MMU +/* same as above but performs the slow path from the async context. Can * be called from the atomic context as well */ extern void mmput_async(struct mm_struct *); +#endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); diff --git a/kernel/fork.c b/kernel/fork.c index 47887bba944f..5c2c355aa97f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -736,6 +736,7 @@ void mmput(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmput); +#ifdef CONFIG_MMU static void mmput_async_fn(struct work_struct *work) { struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); @@ -749,6 +750,7 @@ void mmput_async(struct mm_struct *mm) schedule_work(&mm->async_put_work); } } +#endif /** * set_mm_exe_file - change a reference to the mm's executable file -- cgit v1.2.3 From b235beea9e996a4d36fed6cfef4801a3e7d7a9a5 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 24 Jun 2016 15:09:37 -0700 Subject: Clarify naming of thread info/stack allocators We've had the thread info allocated together with the thread stack for most architectures for a long time (since the thread_info was split off from the task struct), but that is about to change. But the patches that move the thread info to be off-stack (and a part of the task struct instead) made it clear how confused the allocator and freeing functions are. Because the common case was that we share an allocation with the thread stack and the thread_info, the two pointers were identical. That identity then meant that we would have things like ti = alloc_thread_info_node(tsk, node); ... tsk->stack = ti; which certainly _worked_ (since stack and thread_info have the same value), but is rather confusing: why are we assigning a thread_info to the stack? And if we move the thread_info away, the "confusing" code just gets to be entirely bogus. So remove all this confusion, and make it clear that we are doing the stack allocation by renaming and clarifying the function names to be about the stack. The fact that the thread_info then shares the allocation is an implementation detail, and not really about the allocation itself. This is a pure renaming and type fix: we pass in the same pointer, it's just that we clarify what the pointer means. The ia64 code that actually only has one single allocation (for all of task_struct, thread_info and kernel thread stack) now looks a bit odd, but since "tsk->stack" is actually not even used there, that oddity doesn't matter. It would be a separate thing to clean that up, I intentionally left the ia64 changes as a pure brute-force renaming and type change. Acked-by: Andy Lutomirski Signed-off-by: Linus Torvalds --- arch/Kconfig | 4 +-- arch/ia64/Kconfig | 2 +- arch/ia64/include/asm/thread_info.h | 8 +++--- arch/mn10300/include/asm/thread_info.h | 2 +- arch/mn10300/kernel/kgdb.c | 3 +- arch/tile/include/asm/thread_info.h | 2 +- arch/tile/kernel/process.c | 3 +- include/linux/sched.h | 2 +- init/main.c | 4 +-- kernel/fork.c | 50 +++++++++++++++++----------------- 10 files changed, 41 insertions(+), 39 deletions(-) (limited to 'include/linux/sched.h') diff --git a/arch/Kconfig b/arch/Kconfig index e9734796531f..15996290fed4 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -226,8 +226,8 @@ config ARCH_INIT_TASK config ARCH_TASK_STRUCT_ALLOCATOR bool -# Select if arch has its private alloc_thread_info() function -config ARCH_THREAD_INFO_ALLOCATOR +# Select if arch has its private alloc_thread_stack() function +config ARCH_THREAD_STACK_ALLOCATOR bool # Select if arch wants to size task_struct dynamically via arch_task_struct_size: diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index f80758cb7157..e109ee95e919 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -45,7 +45,7 @@ config IA64 select GENERIC_SMP_IDLE_THREAD select ARCH_INIT_TASK select ARCH_TASK_STRUCT_ALLOCATOR - select ARCH_THREAD_INFO_ALLOCATOR + select ARCH_THREAD_STACK_ALLOCATOR select ARCH_CLOCKSOURCE_DATA select GENERIC_TIME_VSYSCALL_OLD select SYSCTL_ARCH_UNALIGN_NO_WARN diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index aa995b67c3f5..d1212b84fb83 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -48,15 +48,15 @@ struct thread_info { #ifndef ASM_OFFSETS_C /* how to get the thread information struct from C */ #define current_thread_info() ((struct thread_info *) ((char *) current + IA64_TASK_SIZE)) -#define alloc_thread_info_node(tsk, node) \ - ((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE)) +#define alloc_thread_stack_node(tsk, node) \ + ((unsigned long *) ((char *) (tsk) + IA64_TASK_SIZE)) #define task_thread_info(tsk) ((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE)) #else #define current_thread_info() ((struct thread_info *) 0) -#define alloc_thread_info_node(tsk, node) ((struct thread_info *) 0) +#define alloc_thread_stack_node(tsk, node) ((unsigned long *) 0) #define task_thread_info(tsk) ((struct thread_info *) 0) #endif -#define free_thread_info(ti) /* nothing */ +#define free_thread_stack(ti) /* nothing */ #define task_stack_page(tsk) ((void *)(tsk)) #define __HAVE_THREAD_FUNCTIONS diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h index 4861a78c7160..f5f90bbf019d 100644 --- a/arch/mn10300/include/asm/thread_info.h +++ b/arch/mn10300/include/asm/thread_info.h @@ -115,7 +115,7 @@ static inline unsigned long current_stack_pointer(void) } #ifndef CONFIG_KGDB -void arch_release_thread_info(struct thread_info *ti); +void arch_release_thread_stack(unsigned long *stack); #endif #define get_thread_info(ti) get_task_struct((ti)->task) #define put_thread_info(ti) put_task_struct((ti)->task) diff --git a/arch/mn10300/kernel/kgdb.c b/arch/mn10300/kernel/kgdb.c index 99770823451a..2d7986c386fe 100644 --- a/arch/mn10300/kernel/kgdb.c +++ b/arch/mn10300/kernel/kgdb.c @@ -397,8 +397,9 @@ static bool kgdb_arch_undo_singlestep(struct pt_regs *regs) * single-step state is cleared. At this point the breakpoints should have * been removed by __switch_to(). */ -void arch_release_thread_info(struct thread_info *ti) +void arch_release_thread_stack(unsigned long *stack) { + struct thread_info *ti = (void *)stack; if (kgdb_sstep_thread == ti) { kgdb_sstep_thread = NULL; diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h index 4b7cef9e94e0..c1467ac59ce6 100644 --- a/arch/tile/include/asm/thread_info.h +++ b/arch/tile/include/asm/thread_info.h @@ -78,7 +78,7 @@ struct thread_info { #ifndef __ASSEMBLY__ -void arch_release_thread_info(struct thread_info *info); +void arch_release_thread_stack(unsigned long *stack); /* How to get the thread information struct from C. */ register unsigned long stack_pointer __asm__("sp"); diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 6b705ccc9cc1..a465d8372edd 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -73,8 +73,9 @@ void arch_cpu_idle(void) /* * Release a thread_info structure */ -void arch_release_thread_info(struct thread_info *info) +void arch_release_thread_stack(unsigned long *stack) { + struct thread_info *info = (void *)stack; struct single_step_state *step_state = info->step_state; if (step_state) { diff --git a/include/linux/sched.h b/include/linux/sched.h index 6e42ada26345..253538f29ade 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -3007,7 +3007,7 @@ static inline int object_is_on_stack(void *obj) return (obj >= stack) && (obj < (stack + THREAD_SIZE)); } -extern void thread_info_cache_init(void); +extern void thread_stack_cache_init(void); #ifdef CONFIG_DEBUG_STACK_USAGE static inline unsigned long stack_not_used(struct task_struct *p) diff --git a/init/main.c b/init/main.c index 4c17fda5c2ff..826fd57fa3aa 100644 --- a/init/main.c +++ b/init/main.c @@ -453,7 +453,7 @@ void __init __weak smp_setup_processor_id(void) } # if THREAD_SIZE >= PAGE_SIZE -void __init __weak thread_info_cache_init(void) +void __init __weak thread_stack_cache_init(void) { } #endif @@ -627,7 +627,7 @@ asmlinkage __visible void __init start_kernel(void) /* Should be run before the first non-init thread is created */ init_espfix_bsp(); #endif - thread_info_cache_init(); + thread_stack_cache_init(); cred_init(); fork_init(); proc_caches_init(); diff --git a/kernel/fork.c b/kernel/fork.c index 5c2c355aa97f..37b9439b8c07 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -148,18 +148,18 @@ static inline void free_task_struct(struct task_struct *tsk) } #endif -void __weak arch_release_thread_info(struct thread_info *ti) +void __weak arch_release_thread_stack(unsigned long *stack) { } -#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR +#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ # if THREAD_SIZE >= PAGE_SIZE -static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, +static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP, @@ -172,33 +172,33 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, return page ? page_address(page) : NULL; } -static inline void free_thread_info(struct thread_info *ti) +static inline void free_thread_stack(unsigned long *stack) { - struct page *page = virt_to_page(ti); + struct page *page = virt_to_page(stack); memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, -(1 << THREAD_SIZE_ORDER)); __free_kmem_pages(page, THREAD_SIZE_ORDER); } # else -static struct kmem_cache *thread_info_cache; +static struct kmem_cache *thread_stack_cache; -static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, +static struct thread_info *alloc_thread_stack_node(struct task_struct *tsk, int node) { - return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node); + return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); } -static void free_thread_info(struct thread_info *ti) +static void free_stack(unsigned long *stack) { - kmem_cache_free(thread_info_cache, ti); + kmem_cache_free(thread_stack_cache, stack); } -void thread_info_cache_init(void) +void thread_stack_cache_init(void) { - thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE, + thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, NULL); - BUG_ON(thread_info_cache == NULL); + BUG_ON(thread_stack_cache == NULL); } # endif #endif @@ -221,9 +221,9 @@ struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; -static void account_kernel_stack(struct thread_info *ti, int account) +static void account_kernel_stack(unsigned long *stack, int account) { - struct zone *zone = page_zone(virt_to_page(ti)); + struct zone *zone = page_zone(virt_to_page(stack)); mod_zone_page_state(zone, NR_KERNEL_STACK, account); } @@ -231,8 +231,8 @@ static void account_kernel_stack(struct thread_info *ti, int account) void free_task(struct task_struct *tsk) { account_kernel_stack(tsk->stack, -1); - arch_release_thread_info(tsk->stack); - free_thread_info(tsk->stack); + arch_release_thread_stack(tsk->stack); + free_thread_stack(tsk->stack); rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); put_seccomp_filter(tsk); @@ -343,7 +343,7 @@ void set_task_stack_end_magic(struct task_struct *tsk) static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; - struct thread_info *ti; + unsigned long *stack; int err; if (node == NUMA_NO_NODE) @@ -352,15 +352,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) if (!tsk) return NULL; - ti = alloc_thread_info_node(tsk, node); - if (!ti) + stack = alloc_thread_stack_node(tsk, node); + if (!stack) goto free_tsk; err = arch_dup_task_struct(tsk, orig); if (err) - goto free_ti; + goto free_stack; - tsk->stack = ti; + tsk->stack = stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under @@ -392,14 +392,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; - account_kernel_stack(ti, 1); + account_kernel_stack(stack, 1); kcov_task_init(tsk); return tsk; -free_ti: - free_thread_info(ti); +free_stack: + free_thread_stack(stack); free_tsk: free_task_struct(tsk); return NULL; -- cgit v1.2.3