linux-api.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Axel Rasmussen <axelrasmussen@google.com>
To: Alexander Viro <viro@zeniv.linux.org.uk>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Daniel Colascione <dancol@google.com>,
	Hugh Dickins <hughd@google.com>,
	Jerome Glisse <jglisse@redhat.com>, Joe Perches <joe@perches.com>,
	Lokesh Gidra <lokeshgidra@google.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Mike Rapoport <rppt@linux.vnet.ibm.com>,
	Peter Xu <peterx@redhat.com>, Shaohua Li <shli@fb.com>,
	Shuah Khan <shuah@kernel.org>,
	Stephen Rothwell <sfr@canb.auug.org.au>,
	Wang Qing <wangqing@vivo.com>
Cc: linux-api@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org,
	linux-mm@kvack.org, Axel Rasmussen <axelrasmussen@google.com>,
	Brian Geffon <bgeffon@google.com>,
	"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
	Mina Almasry <almasrymina@google.com>,
	Oliver Upton <oupton@google.com>
Subject: [PATCH 3/9] userfaultfd/shmem: support minor fault registration for shmem
Date: Thu,  8 Apr 2021 16:43:21 -0700	[thread overview]
Message-ID: <20210408234327.624367-4-axelrasmussen@google.com> (raw)
In-Reply-To: <20210408234327.624367-1-axelrasmussen@google.com>

This patch allows shmem-backed VMAs to be registered for minor faults.
Minor faults are appropriately relayed to userspace in the fault path,
for VMAs with the relevant flag.

This commit doesn't hook up the UFFDIO_CONTINUE ioctl for shmem-backed
minor faults, though, so userspace doesn't yet have a way to resolve
such faults.

Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
---
 fs/userfaultfd.c                 |  6 +++---
 include/uapi/linux/userfaultfd.h |  7 ++++++-
 mm/memory.c                      |  8 +++++---
 mm/shmem.c                       | 20 ++++++++++++++++----
 4 files changed, 30 insertions(+), 11 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 14f92285d04f..9f3b8684cf3c 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1267,8 +1267,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 	}
 
 	if (vm_flags & VM_UFFD_MINOR) {
-		/* FIXME: Add minor fault interception for shmem. */
-		if (!is_vm_hugetlb_page(vma))
+		if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma)))
 			return false;
 	}
 
@@ -1941,7 +1940,8 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 	/* report all available features and ioctls to userland */
 	uffdio_api.features = UFFD_API_FEATURES;
 #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
-	uffdio_api.features &= ~UFFD_FEATURE_MINOR_HUGETLBFS;
+	uffdio_api.features &=
+		~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM);
 #endif
 	uffdio_api.ioctls = UFFD_API_IOCTLS;
 	ret = -EFAULT;
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index bafbeb1a2624..159a74e9564f 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -31,7 +31,8 @@
 			   UFFD_FEATURE_MISSING_SHMEM |		\
 			   UFFD_FEATURE_SIGBUS |		\
 			   UFFD_FEATURE_THREAD_ID |		\
-			   UFFD_FEATURE_MINOR_HUGETLBFS)
+			   UFFD_FEATURE_MINOR_HUGETLBFS |	\
+			   UFFD_FEATURE_MINOR_SHMEM)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -185,6 +186,9 @@ struct uffdio_api {
 	 * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults
 	 * can be intercepted (via REGISTER_MODE_MINOR) for
 	 * hugetlbfs-backed pages.
+	 *
+	 * UFFD_FEATURE_MINOR_SHMEM indicates the same support as
+	 * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead.
 	 */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
@@ -196,6 +200,7 @@ struct uffdio_api {
 #define UFFD_FEATURE_SIGBUS			(1<<7)
 #define UFFD_FEATURE_THREAD_ID			(1<<8)
 #define UFFD_FEATURE_MINOR_HUGETLBFS		(1<<9)
+#define UFFD_FEATURE_MINOR_SHMEM		(1<<10)
 	__u64 features;
 
 	__u64 ioctls;
diff --git a/mm/memory.c b/mm/memory.c
index c8e357627318..a1e5ff55027e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3929,9 +3929,11 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf)
 	 * something).
 	 */
 	if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
-		ret = do_fault_around(vmf);
-		if (ret)
-			return ret;
+		if (likely(!userfaultfd_minor(vmf->vma))) {
+			ret = do_fault_around(vmf);
+			if (ret)
+				return ret;
+		}
 	}
 
 	ret = __do_fault(vmf);
diff --git a/mm/shmem.c b/mm/shmem.c
index c21f20cc4204..99c54b165c16 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1785,7 +1785,7 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
  * vm. If we swap it in we mark it dirty since we also free the swap
  * entry since a page cannot live in both the swap and page cache.
  *
- * vmf and fault_type are only supplied by shmem_fault:
+ * vma, vmf, and fault_type are only supplied by shmem_fault:
  * otherwise they are NULL.
  */
 static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
@@ -1802,6 +1802,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	pgoff_t hindex = index;
 	gfp_t huge_gfp;
 	int error;
+	bool swapped;
 	int once = 0;
 	int alloced = 0;
 
@@ -1820,16 +1821,27 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 
 	page = pagecache_get_page(mapping, index,
 					FGP_ENTRY | FGP_HEAD | FGP_LOCK, 0);
-	if (xa_is_value(page)) {
+	swapped = xa_is_value(page);
+	if (swapped) {
 		error = shmem_swapin_page(inode, index, &page,
 					  sgp, gfp, vma, fault_type);
 		if (error == -EEXIST)
 			goto repeat;
-
 		*pagep = page;
-		return error;
+		if (error)
+			return error;
 	}
 
+	if (page && vma && userfaultfd_minor(vma)) {
+		unlock_page(page);
+		put_page(page);
+		*fault_type = handle_userfault(vmf, VM_UFFD_MINOR);
+		return 0;
+	}
+
+	if (swapped)
+		return 0;
+
 	if (page)
 		hindex = page->index;
 	if (page && sgp == SGP_WRITE)
-- 
2.31.1.295.g9ea45b61b8-goog


  parent reply	other threads:[~2021-04-08 23:43 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-08 23:43 [PATCH 0/9] userfaultfd: add minor fault handling for shmem Axel Rasmussen
2021-04-08 23:43 ` [PATCH 1/9] userfaultfd/hugetlbfs: avoid including userfaultfd_k.h in hugetlb.h Axel Rasmussen
2021-04-12 23:47   ` Peter Xu
2021-04-08 23:43 ` [PATCH 2/9] userfaultfd/shmem: combine shmem_{mcopy_atomic,mfill_zeropage}_pte Axel Rasmussen
2021-04-12 23:57   ` Peter Xu
2021-04-08 23:43 ` Axel Rasmussen [this message]
2021-04-09 16:50   ` [PATCH 3/9] userfaultfd/shmem: support minor fault registration for shmem Peter Xu
2021-04-08 23:43 ` [PATCH 4/9] userfaultfd/shmem: support UFFDIO_CONTINUE " Axel Rasmussen
2021-04-12 23:17   ` Peter Xu
2021-04-13  4:40     ` Axel Rasmussen
2021-04-13 18:12       ` Peter Xu
2021-04-15 18:18         ` Axel Rasmussen
2021-04-08 23:43 ` [PATCH 5/9] userfaultfd/selftests: use memfd_create for shmem test type Axel Rasmussen
2021-04-08 23:43 ` [PATCH 6/9] userfaultfd/selftests: create alias mappings in the shmem test Axel Rasmussen
2021-04-08 23:43 ` [PATCH 7/9] userfaultfd/selftests: reinitialize test context in each test Axel Rasmussen
2021-04-08 23:43 ` [PATCH 8/9] userfaultfd/selftests: exercise minor fault handling shmem support Axel Rasmussen
2021-04-08 23:43 ` [PATCH 9/9] userfaultfd/shmem: modify shmem_mcopy_atomic_pte to use install_ptes Axel Rasmussen
2021-04-09  5:04 ` [PATCH 0/9] userfaultfd: add minor fault handling for shmem Andrew Morton
2021-04-09 17:03   ` Axel Rasmussen
2021-04-09 21:18     ` Peter Xu
2021-04-09 22:16       ` Mike Kravetz

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=20210408234327.624367-4-axelrasmussen@google.com \
    --to=axelrasmussen@google.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=almasrymina@google.com \
    --cc=bgeffon@google.com \
    --cc=dancol@google.com \
    --cc=dgilbert@redhat.com \
    --cc=hughd@google.com \
    --cc=jglisse@redhat.com \
    --cc=joe@perches.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lokeshgidra@google.com \
    --cc=mike.kravetz@oracle.com \
    --cc=oupton@google.com \
    --cc=peterx@redhat.com \
    --cc=rppt@linux.vnet.ibm.com \
    --cc=sfr@canb.auug.org.au \
    --cc=shli@fb.com \
    --cc=shuah@kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=wangqing@vivo.com \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).