Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752703Ab1DRMSz (ORCPT ); Mon, 18 Apr 2011 08:18:55 -0400 Received: from fgwmail6.fujitsu.co.jp ([192.51.44.36]:51661 "EHLO fgwmail6.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751869Ab1DRMSt (ORCPT ); Mon, 18 Apr 2011 08:18:49 -0400 X-SecurityPolicyCheck-FJ: OK by FujitsuOutboundMailChecker v1.3.1 From: KOSAKI Motohiro To: KOSAKI Motohiro Subject: [PATCH 3/3] mm: convert mm->cpu_vm_cpumask into cpumask_var_t Cc: kosaki.motohiro@jp.fujitsu.com, LKML , linux-mm , Andrew Morton , Hugh Dickins In-Reply-To: <20110418211455.9359.A69D9226@jp.fujitsu.com> References: <20110418211455.9359.A69D9226@jp.fujitsu.com> Message-Id: <20110418211950.9365.A69D9226@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit X-Mailer: Becky! ver. 2.56.05 [ja] Date: Mon, 18 Apr 2011 21:18:47 +0900 (JST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5763 Lines: 191 cpumask_t is very big struct and cpu_vm_mask is placed wrong position. It might lead to reduce cache hit ratio. This patch has two change. 1) Move the place of cpumask into last of mm_struct. Because usually cpumask is accessed only front bits when the system has cpu-hotplug capability 2) Convert cpu_vm_mask into cpumask_var_t. It may help to reduce memory footprint if cpumask_size() will use nr_cpumask_bits properly in future. In addition, this patch change the name of cpu_vm_mask with cpu_vm_mask_var. It may help to detect out of tree cpu_vm_mask users. This patch has no functional change. Signed-off-by: KOSAKI Motohiro --- Documentation/cachetlb.txt | 2 +- include/linux/mm_types.h | 9 ++++++--- include/linux/sched.h | 1 + init/main.c | 2 ++ kernel/fork.c | 37 ++++++++++++++++++++++++++++++++++--- mm/init-mm.c | 1 - 6 files changed, 44 insertions(+), 8 deletions(-) This patch don't touch x86/kerrnel/tboot.c. because it can't be compiled. diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt index 9164ae3..9b728dc 100644 --- a/Documentation/cachetlb.txt +++ b/Documentation/cachetlb.txt @@ -16,7 +16,7 @@ on all processors in the system. Don't let this scare you into thinking SMP cache/tlb flushing must be so inefficient, this is in fact an area where many optimizations are possible. For example, if it can be proven that a user address space has never executed -on a cpu (see vma->cpu_vm_mask), one need not perform a flush +on a cpu (see mm_cpumask()), one need not perform a flush for this address space on that cpu. First, the TLB flushing interfaces, since they are the simplest. The diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ca01ab2..070c7f2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -267,8 +267,6 @@ struct mm_struct { struct linux_binfmt *binfmt; - cpumask_t cpu_vm_mask; - /* Architecture-specific MM context */ mm_context_t context; @@ -318,9 +316,14 @@ struct mm_struct { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif + + cpumask_var_t cpu_vm_mask_var; }; /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ -#define mm_cpumask(mm) (&(mm)->cpu_vm_mask) +static inline cpumask_t* mm_cpumask(struct mm_struct *mm) +{ + return mm->cpu_vm_mask_var; +} #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 3f7d3f9..7068380 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2170,6 +2170,7 @@ static inline void mmdrop(struct mm_struct * mm) if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } +extern int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm); /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); diff --git a/init/main.c b/init/main.c index 4a9479e..8451425 100644 --- a/init/main.c +++ b/init/main.c @@ -509,6 +509,8 @@ asmlinkage void __init start_kernel(void) sort_main_extable(); trap_init(); mm_init(); + BUG_ON(mm_init_cpumask(&init_mm, 0)); + /* * Set up the scheduler prior starting any interrupts (such as the * timer interrupt). Full topology setup happens at smp_init() diff --git a/kernel/fork.c b/kernel/fork.c index cc04197..5d303a2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -486,6 +486,20 @@ static void mm_init_aio(struct mm_struct *mm) #endif } +int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm) +{ +#ifdef CONFIG_CPUMASK_OFFSTACK + if (!alloc_cpumask_var(&mm->cpu_vm_mask_var, GFP_KERNEL)) + return -ENOMEM; + + if (oldmm) + cpumask_copy(mm_cpumask(mm), mm_cpumask(oldmm)); + else + memset(mm_cpumask(mm), 0, cpumask_size()); +#endif + return 0; +} + static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) { atomic_set(&mm->mm_users, 1); @@ -522,10 +536,20 @@ struct mm_struct * mm_alloc(void) struct mm_struct * mm; mm = allocate_mm(); - if (mm) { - memset(mm, 0, sizeof(*mm)); - mm = mm_init(mm, current); + if (!mm) + return NULL; + + memset(mm, 0, sizeof(*mm)); + mm = mm_init(mm, current); + if (!mm) + return NULL; + + if (mm_init_cpumask(mm, NULL)) { + mm_free_pgd(mm); + free_mm(mm); + return NULL; } + return mm; } @@ -537,6 +561,7 @@ struct mm_struct * mm_alloc(void) void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); + free_cpumask_var(mm->cpu_vm_mask_var); mm_free_pgd(mm); destroy_context(mm); mmu_notifier_mm_destroy(mm); @@ -691,6 +716,9 @@ struct mm_struct *dup_mm(struct task_struct *tsk) if (!mm_init(mm, tsk)) goto fail_nomem; + if (mm_init_cpumask(mm, oldmm)) + goto fail_nocpumask; + if (init_new_context(tsk, mm)) goto fail_nocontext; @@ -717,6 +745,9 @@ fail_nomem: return NULL; fail_nocontext: + free_cpumask_var(mm->cpu_vm_mask_var); + +fail_nocpumask: /* * If init_new_context() failed, we cannot use mmput() to free the mm * because it calls destroy_context() diff --git a/mm/init-mm.c b/mm/init-mm.c index 1d29cdf..4019979 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -21,6 +21,5 @@ struct mm_struct init_mm = { .mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem), .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(init_mm.mmlist), - .cpu_vm_mask = CPU_MASK_ALL, INIT_MM_CONTEXT(init_mm) }; -- 1.7.3.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/