From patchwork Tue Jan 5 14:12:48 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Gleb Natapov X-Patchwork-Id: 71023 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter.kernel.org (8.14.3/8.14.2) with ESMTP id o05EFnYg011659 for ; Tue, 5 Jan 2010 14:16:13 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754684Ab0AEOOs (ORCPT ); Tue, 5 Jan 2010 09:14:48 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754447Ab0AEOOp (ORCPT ); Tue, 5 Jan 2010 09:14:45 -0500 Received: from mx1.redhat.com ([209.132.183.28]:43893 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754620Ab0AEONk (ORCPT ); Tue, 5 Jan 2010 09:13:40 -0500 Received: from int-mx04.intmail.prod.int.phx2.redhat.com (int-mx04.intmail.prod.int.phx2.redhat.com [10.5.11.17]) by mx1.redhat.com (8.13.8/8.13.8) with ESMTP id o05ECw9e003430 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Tue, 5 Jan 2010 09:12:58 -0500 Received: from dhcp-1-237.tlv.redhat.com (dhcp-1-237.tlv.redhat.com [10.35.1.237]) by int-mx04.intmail.prod.int.phx2.redhat.com (8.13.8/8.13.8) with ESMTP id o05ECvCa006718; Tue, 5 Jan 2010 09:12:57 -0500 Received: by dhcp-1-237.tlv.redhat.com (Postfix, from userid 13519) id 1CE551336D3; Tue, 5 Jan 2010 16:12:55 +0200 (IST) From: Gleb Natapov To: kvm@vger.kernel.org Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, avi@redhat.com, mingo@elte.hu, a.p.zijlstra@chello.nl, tglx@linutronix.de, hpa@zytor.com, riel@redhat.com, cl@linux-foundation.org Subject: [PATCH v3 06/12] Add get_user_pages() variant that fails if major fault is required. Date: Tue, 5 Jan 2010 16:12:48 +0200 Message-Id: <1262700774-1808-7-git-send-email-gleb@redhat.com> In-Reply-To: <1262700774-1808-1-git-send-email-gleb@redhat.com> References: <1262700774-1808-1-git-send-email-gleb@redhat.com> X-Scanned-By: MIMEDefang 2.67 on 10.5.11.17 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c index 15458de..338527e 100644 --- a/fs/ncpfs/mmap.c +++ b/fs/ncpfs/mmap.c @@ -39,6 +39,8 @@ static int ncp_file_mmap_fault(struct vm_area_struct *area, int bufsize; int pos; /* XXX: loff_t ? */ + if (vmf->flags & FAULT_FLAG_MINOR) + return VM_FAULT_MAJOR | VM_FAULT_ERROR; /* * ncpfs has nothing against high pages as long * as recvmsg and memset works on it diff --git a/include/linux/mm.h b/include/linux/mm.h index 2265f28..32e9c6e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -136,6 +136,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */ #define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */ #define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */ +#define FAULT_FLAG_MINOR 0x08 /* Do only minor fault */ /* * This interface is used by x86 PAT code to identify a pfn mapping that is @@ -836,6 +837,9 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void * int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas); +int get_user_pages_noio(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, int nr_pages, int write, int force, + struct page **pages, struct vm_area_struct **vmas); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); @@ -1257,6 +1261,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address, #define FOLL_GET 0x04 /* do get_page on page */ #define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ +#define FOLL_MINOR 0x20 /* do only minor page faults */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); diff --git a/mm/filemap.c b/mm/filemap.c index 96ac6b0..25768ad 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1509,6 +1509,9 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) goto no_cached_page; } } else { + if (vmf->flags & FAULT_FLAG_MINOR) + return VM_FAULT_MAJOR | VM_FAULT_ERROR; + /* No page in the page cache at all */ do_sync_mmap_readahead(vma, ra, file, offset); count_vm_event(PGMAJFAULT); diff --git a/mm/memory.c b/mm/memory.c index 09e4b1b..89e0074 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1336,10 +1336,13 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, cond_resched(); while (!(page = follow_page(vma, start, foll_flags))) { int ret; + unsigned int fault_fl = + ((foll_flags & FOLL_WRITE) ? + FAULT_FLAG_WRITE : 0) | + ((foll_flags & FOLL_MINOR) ? + FAULT_FLAG_MINOR : 0); - ret = handle_mm_fault(mm, vma, start, - (foll_flags & FOLL_WRITE) ? - FAULT_FLAG_WRITE : 0); + ret = handle_mm_fault(mm, vma, start, fault_fl); if (ret & VM_FAULT_ERROR) { if (ret & VM_FAULT_OOM) @@ -1347,6 +1350,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (ret & (VM_FAULT_HWPOISON|VM_FAULT_SIGBUS)) return i ? i : -EFAULT; + else if (ret & VM_FAULT_MAJOR) + return i ? i : -EFAULT; BUG(); } if (ret & VM_FAULT_MAJOR) @@ -1457,6 +1462,23 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, } EXPORT_SYMBOL(get_user_pages); +int get_user_pages_noio(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, int nr_pages, int write, int force, + struct page **pages, struct vm_area_struct **vmas) +{ + int flags = FOLL_TOUCH | FOLL_MINOR; + + if (pages) + flags |= FOLL_GET; + if (write) + flags |= FOLL_WRITE; + if (force) + flags |= FOLL_FORCE; + + return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas); +} +EXPORT_SYMBOL(get_user_pages_noio); + /** * get_dump_page() - pin user page in memory while writing it to core dump * @addr: user address @@ -2536,6 +2558,9 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, delayacct_set_flag(DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry); if (!page) { + if (flags & FAULT_FLAG_MINOR) + return VM_FAULT_MAJOR | VM_FAULT_ERROR; + grab_swap_token(mm); /* Contend for token _before_ read-in */ page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vma, address); diff --git a/mm/shmem.c b/mm/shmem.c index eef4ebe..ab3a255 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1225,6 +1225,7 @@ static int shmem_getpage(struct inode *inode, unsigned long idx, swp_entry_t swap; gfp_t gfp; int error; + int flags = type ? *type : 0; if (idx >= SHMEM_MAX_INDEX) return -EFBIG; @@ -1273,6 +1274,11 @@ repeat: swappage = lookup_swap_cache(swap); if (!swappage) { shmem_swp_unmap(entry); + if (flags & FAULT_FLAG_MINOR) { + spin_unlock(&info->lock); + *type = VM_FAULT_MAJOR | VM_FAULT_ERROR; + goto failed; + } /* here we actually do the io */ if (type && !(*type & VM_FAULT_MAJOR)) { __count_vm_event(PGMAJFAULT); @@ -1481,7 +1487,7 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct inode *inode = vma->vm_file->f_path.dentry->d_inode; int error; - int ret; + int ret = (int)vmf->flags; if (((loff_t)vmf->pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode)) return VM_FAULT_SIGBUS;