Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757471Ab3IPLZ5 (ORCPT ); Mon, 16 Sep 2013 07:25:57 -0400 Received: from mga02.intel.com ([134.134.136.20]:25419 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755309Ab3IPLZ4 (ORCPT ); Mon, 16 Sep 2013 07:25:56 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.90,914,1371106800"; d="scan'208";a="396283038" From: "Kirill A. Shutemov" To: Alex Thorlton , Ingo Molnar , Andrew Morton , Naoya Horiguchi Cc: "Eric W . Biederman" , "Paul E . McKenney" , Al Viro , Andi Kleen , Andrea Arcangeli , Dave Hansen , Dave Jones , David Howells , Frederic Weisbecker , Johannes Weiner , Kees Cook , Mel Gorman , Michael Kerrisk , Oleg Nesterov , Peter Zijlstra , Rik van Riel , Robin Holt , Sedat Dilek , Srikar Dronamraju , Thomas Gleixner , linux-kernel@vger.kernel.org, linux-mm@kvack.org, "Kirill A. Shutemov" Subject: [PATCHv2 4/9] mm, thp: change pmd_trans_huge_lock() to return taken lock Date: Mon, 16 Sep 2013 14:25:35 +0300 Message-Id: <1379330740-5602-5-git-send-email-kirill.shutemov@linux.intel.com> X-Mailer: git-send-email 1.8.4.rc3 In-Reply-To: <1379330740-5602-1-git-send-email-kirill.shutemov@linux.intel.com> References: <1379330740-5602-1-git-send-email-kirill.shutemov@linux.intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 9438 Lines: 289 With split ptlock it's important to know which lock pmd_trans_huge_lock() took. This patch adds one more parameter to the function to return the lock. In most places migration to new api is trivial. Exception is move_huge_pmd(): we need to take two locks if pmd tables are different. Signed-off-by: Naoya Horiguchi Signed-off-by: Kirill A. Shutemov --- fs/proc/task_mmu.c | 13 +++++++------ include/linux/huge_mm.h | 14 +++++++------- mm/huge_memory.c | 40 +++++++++++++++++++++++++++------------- mm/memcontrol.c | 10 +++++----- 4 files changed, 46 insertions(+), 31 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 8e124ac..4599519 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -505,9 +505,9 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pte_t *pte; spinlock_t *ptl; - if (pmd_trans_huge_lock(pmd, vma) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk); - spin_unlock(&walk->mm->page_table_lock); + spin_unlock(ptl); mss->anonymous_thp += HPAGE_PMD_SIZE; return 0; } @@ -993,13 +993,14 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, { struct vm_area_struct *vma; struct pagemapread *pm = walk->private; + spinlock_t *ptl; pte_t *pte; int err = 0; pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2)); /* find the first VMA at or above 'addr' */ vma = find_vma(walk->mm, addr); - if (vma && pmd_trans_huge_lock(pmd, vma) == 1) { + if (vma && pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { int pmd_flags2; if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd)) @@ -1017,7 +1018,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, if (err) break; } - spin_unlock(&walk->mm->page_table_lock); + spin_unlock(ptl); return err; } @@ -1319,7 +1320,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, md = walk->private; - if (pmd_trans_huge_lock(pmd, md->vma) == 1) { + if (pmd_trans_huge_lock(pmd, md->vma, &ptl) == 1) { pte_t huge_pte = *(pte_t *)pmd; struct page *page; @@ -1327,7 +1328,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, if (page) gather_stats(page, md, pte_dirty(huge_pte), HPAGE_PMD_SIZE/PAGE_SIZE); - spin_unlock(&walk->mm->page_table_lock); + spin_unlock(ptl); return 0; } diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 3935428..4aca0d8 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -129,15 +129,15 @@ extern void __vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); -extern int __pmd_trans_huge_lock(pmd_t *pmd, - struct vm_area_struct *vma); +extern int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, + spinlock_t **ptl); /* mmap_sem must be held on entry */ -static inline int pmd_trans_huge_lock(pmd_t *pmd, - struct vm_area_struct *vma) +static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, + spinlock_t **ptl) { VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem)); if (pmd_trans_huge(*pmd)) - return __pmd_trans_huge_lock(pmd, vma); + return __pmd_trans_huge_lock(pmd, vma, ptl); else return 0; } @@ -215,8 +215,8 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, long adjust_next) { } -static inline int pmd_trans_huge_lock(pmd_t *pmd, - struct vm_area_struct *vma) +static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, + spinlock_t **ptl) { return 0; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index bbd41a2..59a1340 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1342,9 +1342,10 @@ out_unlock: int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr) { + spinlock_t *ptl; int ret = 0; - if (__pmd_trans_huge_lock(pmd, vma) == 1) { + if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { struct page *page; pgtable_t pgtable; pmd_t orig_pmd; @@ -1359,7 +1360,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd); if (is_huge_zero_pmd(orig_pmd)) { atomic_dec(&tlb->mm->nr_ptes); - spin_unlock(&tlb->mm->page_table_lock); + spin_unlock(ptl); put_huge_zero_page(); } else { page = pmd_page(orig_pmd); @@ -1368,7 +1369,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); VM_BUG_ON(!PageHead(page)); atomic_dec(&tlb->mm->nr_ptes); - spin_unlock(&tlb->mm->page_table_lock); + spin_unlock(ptl); tlb_remove_page(tlb, page); } pte_free(tlb->mm, pgtable); @@ -1381,14 +1382,15 @@ int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned char *vec) { + spinlock_t *ptl; int ret = 0; - if (__pmd_trans_huge_lock(pmd, vma) == 1) { + if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { /* * All logical pages in the range are present * if backed by a huge page. */ - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); memset(vec, 1, (end - addr) >> PAGE_SHIFT); ret = 1; } @@ -1401,6 +1403,7 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long old_end, pmd_t *old_pmd, pmd_t *new_pmd) { + spinlock_t *old_ptl, *new_ptl; int ret = 0; pmd_t pmd; @@ -1421,12 +1424,21 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, goto out; } - ret = __pmd_trans_huge_lock(old_pmd, vma); + /* + * We don't have to worry about the ordering of src and dst + * ptlocks because exclusive mmap_sem prevents deadlock. + */ + ret = __pmd_trans_huge_lock(old_pmd, vma, &old_ptl); if (ret == 1) { + new_ptl = pmd_lockptr(mm, new_pmd); + if (new_ptl != old_ptl) + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); pmd = pmdp_get_and_clear(mm, old_addr, old_pmd); VM_BUG_ON(!pmd_none(*new_pmd)); set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd)); - spin_unlock(&mm->page_table_lock); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); + spin_unlock(old_ptl); } out: return ret; @@ -1436,9 +1448,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa) { struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; int ret = 0; - if (__pmd_trans_huge_lock(pmd, vma) == 1) { + if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { pmd_t entry; entry = pmdp_get_and_clear(mm, addr, pmd); if (!prot_numa) { @@ -1454,7 +1467,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, } } set_pmd_at(mm, addr, pmd, entry); - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); ret = 1; } @@ -1468,12 +1481,13 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * Note that if it returns 1, this routine returns without unlocking page * table locks. So callers must unlock them. */ -int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) +int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, + spinlock_t **ptl) { - spin_lock(&vma->vm_mm->page_table_lock); + *ptl = pmd_lock(vma->vm_mm, pmd); if (likely(pmd_trans_huge(*pmd))) { if (unlikely(pmd_trans_splitting(*pmd))) { - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(*ptl); wait_split_huge_page(vma->anon_vma, pmd); return -1; } else { @@ -1482,7 +1496,7 @@ int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) return 1; } } - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(*ptl); return 0; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d5ff3ce..5f35b2a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6376,10 +6376,10 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, pte_t *pte; spinlock_t *ptl; - if (pmd_trans_huge_lock(pmd, vma) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE) mc.precharge += HPAGE_PMD_NR; - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); return 0; } @@ -6568,9 +6568,9 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, * to be unlocked in __split_huge_page_splitting(), where the main * part of thp split is not executed yet. */ - if (pmd_trans_huge_lock(pmd, vma) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { if (mc.precharge < HPAGE_PMD_NR) { - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); return 0; } target_type = get_mctgt_type_thp(vma, addr, *pmd, &target); @@ -6587,7 +6587,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, } put_page(page); } - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); return 0; } -- 1.8.4.rc3 -- 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/