Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755706AbcCTMnO (ORCPT ); Sun, 20 Mar 2016 08:43:14 -0400 Received: from e06smtp12.uk.ibm.com ([195.75.94.108]:56441 "EHLO e06smtp12.uk.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755548AbcCTMmr (ORCPT ); Sun, 20 Mar 2016 08:42:47 -0400 X-IBM-Helo: d06dlp03.portsmouth.uk.ibm.com X-IBM-MailFrom: rapoport@il.ibm.com X-IBM-RcptTo: linux-kernel@vger.kernel.org From: Mike Rapoport To: Andrea Arcangeli Cc: Pavel Emelyanov , LKML , linux-mm@kvack.org, Mike Rapoport , Mike Rapoport Subject: [PATCH 5/5] uffd: Add madvise() event for MADV_DONTNEED request Date: Sun, 20 Mar 2016 14:42:21 +0200 Message-Id: <1458477741-6942-6-git-send-email-rapoport@il.ibm.com> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1458477741-6942-1-git-send-email-rapoport@il.ibm.com> References: <1458477741-6942-1-git-send-email-rapoport@il.ibm.com> X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 16032012-0009-0000-0000-000008D2039C Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4488 Lines: 145 From: Pavel Emelyanov If the page is punched out of the address space the uffd reader should know this and zeromap the respective area in case of the #PF event. Signed-off-by: Pavel Emelyanov Signed-off-by: Mike Rapoport --- fs/userfaultfd.c | 26 ++++++++++++++++++++++++++ include/linux/userfaultfd_k.h | 12 ++++++++++++ include/uapi/linux/userfaultfd.h | 9 ++++++++- mm/madvise.c | 2 ++ 4 files changed, 48 insertions(+), 1 deletion(-) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index a7771bd..e65ca84 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -599,6 +599,32 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx vm_ctx, userfaultfd_event_wait_completion(ctx, &ewq); } +void madvise_userfault_dontneed(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + struct userfaultfd_ctx *ctx; + struct userfaultfd_wait_queue ewq; + + ctx = vma->vm_userfaultfd_ctx.ctx; + if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_MADVDONTNEED)) + return; + + userfaultfd_ctx_get(ctx); + *prev = NULL; /* We wait for ACK w/o the mmap semaphore */ + up_read(&vma->vm_mm->mmap_sem); + + msg_init(&ewq.msg); + + ewq.msg.event = UFFD_EVENT_MADVDONTNEED; + ewq.msg.arg.madv_dn.start = start; + ewq.msg.arg.madv_dn.end = end; + + userfaultfd_event_wait_completion(ctx, &ewq); + + down_read(&vma->vm_mm->mmap_sem); +} + static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 42ea277..7e22a3d 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -62,6 +62,11 @@ extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx, unsigned long from, unsigned long to, unsigned long len); +extern void madvise_userfault_dontneed(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, + unsigned long end); + #else /* CONFIG_USERFAULTFD */ /* mm helpers */ @@ -109,6 +114,13 @@ static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx ctx, unsigned long len) { } + +static inline void madvise_userfault_dontneed(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, + unsigned long end) +{ +} #endif /* CONFIG_USERFAULTFD */ #endif /* _LINUX_USERFAULTFD_K_H */ diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 46bbb6f..cbcb3a5 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -16,7 +16,7 @@ * After implementing the respective features it will become: * #define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP) */ -#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_EVENT_REMAP) +#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_EVENT_REMAP|UFFD_FEATURE_EVENT_MADVDONTNEED) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -81,6 +81,11 @@ struct uffd_msg { } remap; struct { + __u64 start; + __u64 end; + } madv_dn; + + struct { /* unused reserved fields */ __u64 reserved1; __u64 reserved2; @@ -95,6 +100,7 @@ struct uffd_msg { #define UFFD_EVENT_PAGEFAULT 0x12 #define UFFD_EVENT_FORK 0x13 #define UFFD_EVENT_REMAP 0x14 +#define UFFD_EVENT_MADVDONTNEED 0x15 /* flags for UFFD_EVENT_PAGEFAULT */ #define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ @@ -118,6 +124,7 @@ struct uffdio_api { #endif #define UFFD_FEATURE_EVENT_FORK (1<<1) #define UFFD_FEATURE_EVENT_REMAP (1<<2) +#define UFFD_FEATURE_EVENT_MADVDONTNEED (1<<3) __u64 features; __u64 ioctls; diff --git a/mm/madvise.c b/mm/madvise.c index a011473..7b66d6b 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -476,6 +477,7 @@ static long madvise_dontneed(struct vm_area_struct *vma, return -EINVAL; zap_page_range(vma, start, end - start, NULL); + madvise_userfault_dontneed(vma, prev, start, end); return 0; } -- 1.9.1