The patch titled Subject: fork/exec: cleanup mm initialization has been added to the -mm tree. Its filename is fork-exec-cleanup-mm-initialization.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/fork-exec-cleanup-mm-initialization.patch and later at http://ozlabs.org/~akpm/mmotm/broken-out/fork-exec-cleanup-mm-initialization.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx> Subject: fork/exec: cleanup mm initialization mm initialization on fork/exec is spread all over the place, which makes the code look inconsistent. We have mm_init(), which is supposed to init/nullify mm's internals, but it doesn't init all the fields it should: - on fork ->mmap,mm_rb,vmacache_seqnum,map_count,mm_cpumask,locked_vm are zeroed in dup_mmap(); - on fork ->pmd_huge_pte is zeroed in dup_mm(), immediately before calling mm_init(); - ->cpu_vm_mask_var ptr is initialized by mm_init_cpumask(), which is called before mm_init() on both fork and exec; - ->context is initialized by init_new_context(), which is called after mm_init() on both fork and exec; Let's consolidate all the initializations in mm_init() to make the code look cleaner. Signed-off-by: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx> Cc: Oleg Nesterov <oleg@xxxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Cc: Christoph Lameter <cl@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- fs/exec.c | 4 --- include/linux/mm_types.h | 1 kernel/fork.c | 47 +++++++++++++++---------------------- 3 files changed, 21 insertions(+), 31 deletions(-) diff -puN fs/exec.c~fork-exec-cleanup-mm-initialization fs/exec.c --- a/fs/exec.c~fork-exec-cleanup-mm-initialization +++ a/fs/exec.c @@ -368,10 +368,6 @@ static int bprm_mm_init(struct linux_bin if (!mm) goto err; - err = init_new_context(current, mm); - if (err) - goto err; - err = __bprm_mm_init(bprm); if (err) goto err; diff -puN include/linux/mm_types.h~fork-exec-cleanup-mm-initialization include/linux/mm_types.h --- a/include/linux/mm_types.h~fork-exec-cleanup-mm-initialization +++ a/include/linux/mm_types.h @@ -461,6 +461,7 @@ static inline void mm_init_cpumask(struc #ifdef CONFIG_CPUMASK_OFFSTACK mm->cpu_vm_mask_var = &mm->cpumask_allocation; #endif + cpumask_clear(mm->cpu_vm_mask_var); } /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ diff -puN kernel/fork.c~fork-exec-cleanup-mm-initialization kernel/fork.c --- a/kernel/fork.c~fork-exec-cleanup-mm-initialization +++ a/kernel/fork.c @@ -365,12 +365,6 @@ static int dup_mmap(struct mm_struct *mm */ down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING); - mm->locked_vm = 0; - mm->mmap = NULL; - mm->vmacache_seqnum = 0; - mm->map_count = 0; - cpumask_clear(mm_cpumask(mm)); - mm->mm_rb = RB_ROOT; rb_link = &mm->mm_rb.rb_node; rb_parent = NULL; pprev = &mm->mmap; @@ -529,17 +523,27 @@ static void mm_init_aio(struct mm_struct static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) { + mm->mmap = NULL; + mm->mm_rb = RB_ROOT; + mm->vmacache_seqnum = 0; atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); init_rwsem(&mm->mmap_sem); INIT_LIST_HEAD(&mm->mmlist); mm->core_state = NULL; atomic_long_set(&mm->nr_ptes, 0); + mm->map_count = 0; + mm->locked_vm = 0; memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); + mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); + mmu_notifier_mm_init(mm); clear_tlb_flush_pending(mm); +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS + mm->pmd_huge_pte = NULL; +#endif if (current->mm) { mm->flags = current->mm->flags & MMF_INIT_MASK; @@ -549,11 +553,17 @@ static struct mm_struct *mm_init(struct mm->def_flags = 0; } - if (likely(!mm_alloc_pgd(mm))) { - mmu_notifier_mm_init(mm); - return mm; - } + if (mm_alloc_pgd(mm)) + goto fail_nopgd; + + if (init_new_context(p, mm)) + goto fail_nocontext; + return mm; + +fail_nocontext: + mm_free_pgd(mm); +fail_nopgd: free_mm(mm); return NULL; } @@ -587,7 +597,6 @@ struct mm_struct *mm_alloc(void) return NULL; memset(mm, 0, sizeof(*mm)); - mm_init_cpumask(mm); return mm_init(mm, current); } @@ -819,17 +828,10 @@ static struct mm_struct *dup_mm(struct t goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); - mm_init_cpumask(mm); -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS - mm->pmd_huge_pte = NULL; -#endif if (!mm_init(mm, tsk)) goto fail_nomem; - if (init_new_context(tsk, mm)) - goto fail_nocontext; - dup_mm_exe_file(oldmm, mm); err = dup_mmap(mm, oldmm); @@ -851,15 +853,6 @@ free_pt: fail_nomem: return NULL; - -fail_nocontext: - /* - * If init_new_context() failed, we cannot use mmput() to free the mm - * because it calls destroy_context() - */ - mm_free_pgd(mm); - free_mm(mm); - return NULL; } static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) _ Patches currently in -mm which might be from vdavydov@xxxxxxxxxxxxx are slab-fix-oops-when-reading-proc-slab_allocators.patch slab-fix-oops-when-reading-proc-slab_allocators-v2.patch memcg-cleanup-memcg_cache_params-refcnt-usage.patch memcg-destroy-kmem-caches-when-last-slab-is-freed.patch memcg-mark-caches-that-belong-to-offline-memcgs-as-dead.patch slub-dont-fail-kmem_cache_shrink-if-slab-placement-optimization-fails.patch slub-make-slab_free-non-preemptable.patch memcg-wait-for-kfrees-to-finish-before-destroying-cache.patch slub-make-dead-memcg-caches-discard-free-slabs-immediately.patch slab-do-not-keep-free-objects-slabs-on-dead-memcg-caches.patch mm-memcontrol-fold-mem_cgroup_do_charge.patch mm-memcontrol-rearrange-charging-fast-path.patch mm-memcontrol-reclaim-at-least-once-for-__gfp_noretry.patch mm-huge_memory-use-gfp_transhuge-when-charging-huge-pages.patch mm-memcontrol-retry-reclaim-for-oom-disabled-and-__gfp_nofail-charges.patch mm-memcontrol-remove-explicit-oom-parameter-in-charge-path.patch mm-memcontrol-simplify-move-precharge-function.patch mm-memcontrol-catch-root-bypass-in-move-precharge.patch mm-memcontrol-use-root_mem_cgroup-res_counter.patch mm-memcontrol-remove-ordering-between-pc-mem_cgroup-and-pagecgroupused.patch mm-memcontrol-do-not-acquire-page_cgroup-lock-for-kmem-pages.patch mm-memcontrol-rewrite-charge-api.patch mm-memcontrol-rewrite-uncharge-api.patch fork-exec-cleanup-mm-initialization.patch fork-reset-mm-pinned_vm.patch fork-copy-mms-vm-usage-counters-under-mmap_sem.patch linux-next.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html