All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrea Arcangeli <aarcange@redhat.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org, Michael Rapoport <RAPOPORT@il.ibm.com>,
	"Dr. David Alan Gilbert"@v2.random, " <dgilbert@redhat.com>,
	 Mike Kravetz <mike.kravetz@oracle.com>,
	 Shaohua Li <shli@fb.com>,
	 Pavel Emelyanov <xemul@parallels.com>"@v2.random
Subject: [PATCH 12/33] userfaultfd: non-cooperative: Add madvise() event for MADV_DONTNEED request
Date: Wed,  2 Nov 2016 20:33:44 +0100	[thread overview]
Message-ID: <1478115245-32090-13-git-send-email-aarcange@redhat.com> (raw)
In-Reply-To: <1478115245-32090-1-git-send-email-aarcange@redhat.com>

From: Pavel Emelyanov <xemul@parallels.com>

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 <xemul@parallels.com>
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
---
 fs/userfaultfd.c                 | 26 ++++++++++++++++++++++++++
 include/linux/userfaultfd_k.h    | 12 ++++++++++++
 include/uapi/linux/userfaultfd.h | 10 +++++++++-
 mm/madvise.c                     |  2 ++
 4 files changed, 49 insertions(+), 1 deletion(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 2fcbd6b..9357dcf 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -598,6 +598,32 @@ 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 bfab4ef..efb06d7 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -61,6 +61,11 @@ 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 */
@@ -106,6 +111,13 @@ 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 79a85e5..2bbf323 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -19,7 +19,8 @@
  */
 #define UFFD_API ((__u64)0xAA)
 #define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK |	    \
-			   UFFD_FEATURE_EVENT_REMAP)
+			   UFFD_FEATURE_EVENT_REMAP |	    \
+			   UFFD_FEATURE_EVENT_MADVDONTNEED)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -84,6 +85,11 @@ struct uffd_msg {
 		} remap;
 
 		struct {
+			__u64	start;
+			__u64	end;
+		} madv_dn;
+
+		struct {
 			/* unused reserved fields */
 			__u64	reserved1;
 			__u64	reserved2;
@@ -98,6 +104,7 @@ 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 */
@@ -119,6 +126,7 @@ struct uffdio_api {
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #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 93fb63e..7168bc6 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -10,6 +10,7 @@
 #include <linux/syscalls.h>
 #include <linux/mempolicy.h>
 #include <linux/page-isolation.h>
+#include <linux/userfaultfd_k.h>
 #include <linux/hugetlb.h>
 #include <linux/falloc.h>
 #include <linux/sched.h>
@@ -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;
 }
 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2016-11-02 19:34 UTC|newest]

Thread overview: 69+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-11-02 19:33 [PATCH 00/33] userfaultfd tmpfs/hugetlbfs/non-cooperative Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 01/33] userfaultfd: document _IOR/_IOW Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 02/33] userfaultfd: correct comment about UFFD_FEATURE_PAGEFAULT_FLAG_WP Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 03/33] userfaultfd: convert BUG() to WARN_ON_ONCE() Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 04/33] userfaultfd: use vma_is_anonymous Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 05/33] userfaultfd: non-cooperative: Split the find_userfault() routine Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 06/33] userfaultfd: non-cooperative: Add ability to report non-PF events from uffd descriptor Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 07/33] userfaultfd: non-cooperative: report all available features to userland Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 08/33] userfaultfd: non-cooperative: Add fork() event Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 09/33] userfaultfd: non-cooperative: Add fork() event, build warning fix Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 10/33] userfaultfd: non-cooperative: dup_userfaultfd: use mm_count instead of mm_users Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 11/33] userfaultfd: non-cooperative: Add mremap() event Andrea Arcangeli
2016-11-03  7:41   ` Hillf Danton
2016-11-03 17:52     ` Mike Rapoport
2016-11-04 15:40     ` Mike Rapoport
2016-11-02 19:33 ` Andrea Arcangeli [this message]
2016-11-03  8:01   ` [PATCH 12/33] userfaultfd: non-cooperative: Add madvise() event for MADV_DONTNEED request Hillf Danton
2016-11-03 17:24     ` Mike Rapoport
2016-11-04 16:40       ` [PATCH 12/33] userfaultfd: non-cooperative: Add madvise() event for MADV_DONTNEED requestg Andrea Arcangeli
2016-11-04 15:42     ` [PATCH 12/33] userfaultfd: non-cooperative: Add madvise() event for MADV_DONTNEED request Mike Rapoport
2016-11-02 19:33 ` [PATCH 13/33] userfaultfd: hugetlbfs: add copy_huge_page_from_user for hugetlb userfaultfd support Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 14/33] userfaultfd: hugetlbfs: add hugetlb_mcopy_atomic_pte for " Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 15/33] userfaultfd: hugetlbfs: add __mcopy_atomic_hugetlb for huge page UFFDIO_COPY Andrea Arcangeli
2016-11-03 10:15   ` Hillf Danton
2016-11-03 17:33     ` Mike Kravetz
2016-11-03 19:14       ` Mike Kravetz
2016-11-04  6:43         ` Hillf Danton
2016-11-04 19:36         ` Andrea Arcangeli
2016-11-04 20:34           ` Mike Kravetz
2016-11-08 21:06           ` Mike Kravetz
2016-11-16 18:28             ` Andrea Arcangeli
2016-11-16 18:53               ` Mike Kravetz
2016-11-17 15:40                 ` Andrea Arcangeli
2016-11-17 19:26                   ` Mike Kravetz
2016-11-18  0:05                     ` Andrea Arcangeli
2016-11-18  5:52                       ` Mike Kravetz
2016-11-22  1:16                         ` Mike Kravetz
2016-11-23  6:38                           ` Hillf Danton
2016-12-15 19:02                             ` Andrea Arcangeli
2016-12-16  3:54                               ` Hillf Danton
2016-11-17 19:41               ` Mike Kravetz
2016-11-04 16:35       ` Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 16/33] userfaultfd: hugetlbfs: add userfaultfd hugetlb hook Andrea Arcangeli
2016-11-04  7:02   ` Hillf Danton
2016-11-02 19:33 ` [PATCH 17/33] userfaultfd: hugetlbfs: allow registration of ranges containing huge pages Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 18/33] userfaultfd: hugetlbfs: add userfaultfd_hugetlb test Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 19/33] userfaultfd: hugetlbfs: userfaultfd_huge_must_wait for hugepmd ranges Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 20/33] userfaultfd: introduce vma_can_userfault Andrea Arcangeli
2016-11-04  7:39   ` Hillf Danton
2016-11-02 19:33 ` [PATCH 21/33] userfaultfd: shmem: add shmem_mcopy_atomic_pte for userfaultfd support Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 22/33] userfaultfd: shmem: introduce vma_is_shmem Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 23/33] userfaultfd: shmem: add tlbflush.h header for microblaze Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 24/33] userfaultfd: shmem: use shmem_mcopy_atomic_pte for shared memory Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 25/33] userfaultfd: shmem: add userfaultfd hook for shared memory faults Andrea Arcangeli
2016-11-04  8:59   ` Hillf Danton
2016-11-04 14:53     ` Mike Rapoport
2016-11-04 15:44     ` Mike Rapoport
2016-11-04 16:56       ` Andrea Arcangeli
2016-11-18  0:37       ` Andrea Arcangeli
2016-11-20 12:10         ` Mike Rapoport
2016-11-02 19:33 ` [PATCH 26/33] userfaultfd: shmem: allow registration of shared memory ranges Andrea Arcangeli
2016-11-02 19:33 ` [PATCH 27/33] userfaultfd: shmem: add userfaultfd_shmem test Andrea Arcangeli
2016-11-02 19:34 ` [PATCH 28/33] userfaultfd: shmem: lock the page before adding it to pagecache Andrea Arcangeli
2016-11-02 19:34 ` [PATCH 29/33] userfaultfd: shmem: avoid leaking blocks and used blocks in UFFDIO_COPY Andrea Arcangeli
2016-11-02 19:34 ` [PATCH 30/33] userfaultfd: non-cooperative: selftest: introduce userfaultfd_open Andrea Arcangeli
2016-11-02 19:34 ` [PATCH 31/33] userfaultfd: non-cooperative: selftest: add ufd parameter to copy_page Andrea Arcangeli
2016-11-02 19:34 ` [PATCH 32/33] userfaultfd: non-cooperative: selftest: add test for FORK, MADVDONTNEED and REMAP events Andrea Arcangeli
2016-11-02 19:34 ` [PATCH 33/33] mm: mprotect: use pmd_trans_unstable instead of taking the pmd_lock Andrea Arcangeli
2016-11-02 20:07 ` [PATCH 00/33] userfaultfd tmpfs/hugetlbfs/non-cooperative Andrea Arcangeli

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1478115245-32090-13-git-send-email-aarcange@redhat.com \
    --to=aarcange@redhat.com \
    --cc=" <dgilbert@redhat.com>,  Mike Kravetz <mike.kravetz@oracle.com>,  Shaohua Li <shli@fb.com>,  Pavel Emelyanov <xemul@parallels.com>"@v2.random \
    --cc="Dr. David Alan Gilbert"@v2.random \
    --cc=RAPOPORT@il.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=linux-mm@kvack.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.