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 --- kernel/fork.c | 50 +++++++++++++++++++++++++++++++++++--------------- 1 file changed, 35 insertions(+), 15 deletions(-) (limited to 'kernel/fork.c') 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 -- cgit v1.2.3-71-gd317 From 0740aa5f6375681c57488c4ea55d05a0341cfc9c Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 20 May 2016 17:00:25 -0700 Subject: fork: free thread in copy_process on failure When using this program (as root): #include #include #include #include #include #include #include #define ITER 1000 #define FORKERS 15 #define THREADS (6000/FORKERS) // 1850 is proc max static void fork_100_wait() { unsigned a, to_wait = 0; printf("\t%d forking %d\n", THREADS, getpid()); for (a = 0; a < THREADS; a++) { switch (fork()) { case 0: usleep(1000); exit(0); break; case -1: break; default: to_wait++; break; } } printf("\t%d forked from %d, waiting for %d\n", THREADS, getpid(), to_wait); for (a = 0; a < to_wait; a++) wait(NULL); printf("\t%d waited from %d\n", THREADS, getpid()); } static void run_forkers() { pid_t forkers[FORKERS]; unsigned a; for (a = 0; a < FORKERS; a++) { switch ((forkers[a] = fork())) { case 0: fork_100_wait(); exit(0); break; case -1: err(1, "DIE fork of %d'th forker", a); break; default: break; } } for (a = 0; a < FORKERS; a++) waitpid(forkers[a], NULL, 0); } int main() { unsigned a; int ret; ret = ioperm(10, 20, 0); if (ret < 0) err(1, "ioperm"); for (a = 0; a < ITER; a++) run_forkers(); return 0; } kmemleak reports many occurences of this leak: unreferenced object 0xffff8805917c8000 (size 8192): comm "fork-leak", pid 2932, jiffies 4295354292 (age 1871.028s) hex dump (first 32 bytes): ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ................ ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ................ backtrace: [] kmemdup+0x25/0x50 [] copy_thread_tls+0x6c3/0x9a0 [] copy_process+0x1a84/0x5790 [] wake_up_new_task+0x2d5/0x6f0 [] _do_fork+0x12d/0x820 ... Due to the leakage of the memory items which should have been freed in arch/x86/kernel/process.c:exit_thread(). Make sure the memory is freed when fork fails later in copy_process. This is done by calling exit_thread with the thread to kill. 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 --- kernel/fork.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 8fbed7194af1..103d78fd8f75 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1490,7 +1490,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, pid = alloc_pid(p->nsproxy->pid_ns_for_children); if (IS_ERR(pid)) { retval = PTR_ERR(pid); - goto bad_fork_cleanup_io; + goto bad_fork_cleanup_thread; } } @@ -1652,6 +1652,8 @@ bad_fork_cancel_cgroup: bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); +bad_fork_cleanup_thread: + exit_thread(p); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); -- cgit v1.2.3-71-gd317 From 725fc629ff2545b061407305ae51016c9f928fce Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 23 May 2016 16:24:05 -0700 Subject: kernek/fork.c: allocate idle task for a CPU always on its local node Linux preallocates the task structs of the idle tasks for all possible CPUs. This currently means they all end up on node 0. This also implies that the cache line of MWAIT, which is around the flags field in the task struct, are all located in node 0. We see a noticeable performance improvement on Knights Landing CPUs when the cache lines used for MWAIT are located in the local nodes of the CPUs using them. I would expect this to give a (likely slight) improvement on other systems too. The patch implements placing the idle task in the node of its CPUs, by passing the right target node to copy_process() [akpm@linux-foundation.org: use NUMA_NO_NODE, not a bare -1] Link: http://lkml.kernel.org/r/1463492694-15833-1-git-send-email-andi@firstfloor.org Signed-off-by: Andi Kleen Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 103d78fd8f75..e67d7b773348 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -340,13 +340,14 @@ void set_task_stack_end_magic(struct task_struct *tsk) *stackend = STACK_END_MAGIC; /* for overflow detection */ } -static struct task_struct *dup_task_struct(struct task_struct *orig) +static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; struct thread_info *ti; - int node = tsk_fork_get_node(orig); int err; + if (node == NUMA_NO_NODE) + node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; @@ -1276,7 +1277,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, int __user *child_tidptr, struct pid *pid, int trace, - unsigned long tls) + unsigned long tls, + int node) { int retval; struct task_struct *p; @@ -1328,7 +1330,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto fork_out; retval = -ENOMEM; - p = dup_task_struct(current); + p = dup_task_struct(current, node); if (!p) goto fork_out; @@ -1706,7 +1708,8 @@ static inline void init_idle_pids(struct pid_link *links) struct task_struct *fork_idle(int cpu) { struct task_struct *task; - task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0); + task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0, + cpu_to_node(cpu)); if (!IS_ERR(task)) { init_idle_pids(task->pids); init_idle(task, cpu); @@ -1751,7 +1754,7 @@ long _do_fork(unsigned long clone_flags, } p = copy_process(clone_flags, stack_start, stack_size, - child_tidptr, NULL, trace, tls); + child_tidptr, NULL, trace, tls, NUMA_NO_NODE); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. -- cgit v1.2.3-71-gd317 From 7c051267931a9be9c6620cc17b362bc6ee6dedc8 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Mon, 23 May 2016 16:25:48 -0700 Subject: mm, fork: make dup_mmap wait for mmap_sem for write killable dup_mmap needs to lock current's mm mmap_sem for write. If the waiting task gets killed by the oom killer it would block oom_reaper from asynchronous address space reclaim and reduce the chances of timely OOM resolving. Wait for the lock in the killable mode and return with EINTR if the task got killed while waiting. Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Oleg Nesterov Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index e67d7b773348..47887bba944f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -414,7 +414,10 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) unsigned long charge; uprobe_start_dup_mmap(); - down_write(&oldmm->mmap_sem); + if (down_write_killable(&oldmm->mmap_sem)) { + retval = -EINTR; + goto fail_uprobe_end; + } flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* @@ -526,6 +529,7 @@ out: up_write(&mm->mmap_sem); flush_tlb_mm(oldmm); up_write(&oldmm->mmap_sem); +fail_uprobe_end: uprobe_end_dup_mmap(); return retval; fail_nomem_anon_vma_fork: -- cgit v1.2.3-71-gd317 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 'kernel/fork.c') 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 v1.2.3-71-gd317 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 'kernel/fork.c') 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 v1.2.3-71-gd317 From 9521d39976db20f8ef9b56af66661482a17d5364 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Sat, 25 Jun 2016 21:53:30 +1000 Subject: Fix build break in fork.c when THREAD_SIZE < PAGE_SIZE Commit b235beea9e99 ("Clarify naming of thread info/stack allocators") breaks the build on some powerpc configs, where THREAD_SIZE < PAGE_SIZE: kernel/fork.c:235:2: error: implicit declaration of function 'free_thread_stack' kernel/fork.c:355:8: error: assignment from incompatible pointer type stack = alloc_thread_stack_node(tsk, node); ^ Fix it by renaming free_stack() to free_thread_stack(), and updating the return type of alloc_thread_stack_node(). Fixes: b235beea9e99 ("Clarify naming of thread info/stack allocators") Signed-off-by: Michael Ellerman Signed-off-by: Linus Torvalds --- kernel/fork.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 37b9439b8c07..4a7ec0c6c88c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -183,13 +183,13 @@ static inline void free_thread_stack(unsigned long *stack) # else static struct kmem_cache *thread_stack_cache; -static struct thread_info *alloc_thread_stack_node(struct task_struct *tsk, +static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); } -static void free_stack(unsigned long *stack) +static void free_thread_stack(unsigned long *stack) { kmem_cache_free(thread_stack_cache, stack); } -- cgit v1.2.3-71-gd317