All of lore.kernel.org
 help / color / mirror / Atom feed
From: Hugh Dickins <hughd@google.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Hugh Dickins <hughd@google.com>,
	Shakeel Butt <shakeelb@google.com>,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
	Yang Shi <shy828301@gmail.com>, Miaohe Lin <linmiaohe@huawei.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Michal Hocko <mhocko@suse.com>, Rik van Riel <riel@surriel.com>,
	Christoph Hellwig <hch@infradead.org>,
	Matthew Wilcox <willy@infradead.org>,
	"Eric W. Biederman" <ebiederm@xmission.com>,
	Alexey Gladkov <legion@kernel.org>,
	Chris Wilson <chris@chris-wilson.co.uk>,
	Matthew Auld <matthew.auld@intel.com>,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-api@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH 07/16] memfd: memfd_create(name, MFD_HUGEPAGE) for shmem huge pages
Date: Fri, 30 Jul 2021 00:45:49 -0700 (PDT)	[thread overview]
Message-ID: <c140f56a-1aa3-f7ae-b7d1-93da7d5a3572@google.com> (raw)
In-Reply-To: <2862852d-badd-7486-3a8e-c5ea9666d6fb@google.com>

Commit 749df87bd7be ("mm/shmem: add hugetlbfs support to memfd_create()")
in 4.14 added the MFD_HUGETLB flag to memfd_create(), to use hugetlbfs
pages instead of tmpfs pages: now add the MFD_HUGEPAGE flag, to use tmpfs
Transparent Huge Pages when they can be allocated (flag named to follow
the precedent of madvise's MADV_HUGEPAGE for THPs).

/sys/kernel/mm/transparent_hugepage/shmem_enabled "always" or "force"
already made this possible: but that is much too blunt an instrument,
affecting all the very different kinds of files on the internal shmem
mount, and was intended just for ease of testing hugepage loads.

MFD_HUGEPAGE is implemented internally by VM_HUGEPAGE in the shmem inode
flags: do not permit a PR_SET_THP_DISABLE (MMF_DISABLE_THP) task to set
this flag, and do not set it if THPs are not allowed at all; but let the
memfd_create() succeed even in those cases - the caller wants to create a
memfd, just hinting how it's best allocated if huge pages are available.

shmem_is_huge() (at allocation time or khugepaged time) applies its
SHMEM_HUGE_DENY and vma VM_NOHUGEPAGE and vm_mm MMF_DISABLE_THP checks
first, and only then allows the memfd's MFD_HUGEPAGE to take effect.

Signed-off-by: Hugh Dickins <hughd@google.com>
---
 include/uapi/linux/memfd.h |  3 ++-
 mm/memfd.c                 | 24 ++++++++++++++++++------
 mm/shmem.c                 | 33 +++++++++++++++++++++++++++++++--
 3 files changed, 51 insertions(+), 9 deletions(-)

diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h
index 7a8a26751c23..8358a69e78cc 100644
--- a/include/uapi/linux/memfd.h
+++ b/include/uapi/linux/memfd.h
@@ -7,7 +7,8 @@
 /* flags for memfd_create(2) (unsigned int) */
 #define MFD_CLOEXEC		0x0001U
 #define MFD_ALLOW_SEALING	0x0002U
-#define MFD_HUGETLB		0x0004U
+#define MFD_HUGETLB		0x0004U		/* Use hugetlbfs */
+#define MFD_HUGEPAGE		0x0008U		/* Use huge tmpfs */
 
 /*
  * Huge page size encoding when MFD_HUGETLB is specified, and a huge page
diff --git a/mm/memfd.c b/mm/memfd.c
index 081dd33e6a61..0d1a504d2fc9 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -245,7 +245,10 @@ long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)
 #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
 
-#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB)
+#define MFD_ALL_FLAGS  (MFD_CLOEXEC | \
+			MFD_ALLOW_SEALING | \
+			MFD_HUGETLB | \
+			MFD_HUGEPAGE)
 
 SYSCALL_DEFINE2(memfd_create,
 		const char __user *, uname,
@@ -257,14 +260,17 @@ SYSCALL_DEFINE2(memfd_create,
 	char *name;
 	long len;
 
-	if (!(flags & MFD_HUGETLB)) {
-		if (flags & ~(unsigned int)MFD_ALL_FLAGS)
+	if (flags & MFD_HUGETLB) {
+		/* Disallow huge tmpfs when choosing hugetlbfs */
+		if (flags & MFD_HUGEPAGE)
 			return -EINVAL;
-	} else {
 		/* Allow huge page size encoding in flags. */
 		if (flags & ~(unsigned int)(MFD_ALL_FLAGS |
 				(MFD_HUGE_MASK << MFD_HUGE_SHIFT)))
 			return -EINVAL;
+	} else {
+		if (flags & ~(unsigned int)MFD_ALL_FLAGS)
+			return -EINVAL;
 	}
 
 	/* length includes terminating zero */
@@ -303,8 +309,14 @@ SYSCALL_DEFINE2(memfd_create,
 					HUGETLB_ANONHUGE_INODE,
 					(flags >> MFD_HUGE_SHIFT) &
 					MFD_HUGE_MASK);
-	} else
-		file = shmem_file_setup(name, 0, VM_NORESERVE);
+	} else {
+		unsigned long vm_flags = VM_NORESERVE;
+
+		if (flags & MFD_HUGEPAGE)
+			vm_flags |= VM_HUGEPAGE;
+		file = shmem_file_setup(name, 0, vm_flags);
+	}
+
 	if (IS_ERR(file)) {
 		error = PTR_ERR(file);
 		goto err_fd;
diff --git a/mm/shmem.c b/mm/shmem.c
index 6def7391084c..e2bcf3313686 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -476,6 +476,20 @@ static bool shmem_confirm_swap(struct address_space *mapping,
 
 static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER;
 
+/*
+ * Does either /sys/kernel/mm/transparent_hugepage/shmem_enabled or
+ * /sys/kernel/mm/transparent_hugepage/enabled allow transparent hugepages?
+ * (Can only return true when the machine has_transparent_hugepage() too.)
+ */
+static bool transparent_hugepage_allowed(void)
+{
+	return	shmem_huge > SHMEM_HUGE_NEVER ||
+		test_bit(TRANSPARENT_HUGEPAGE_FLAG,
+			&transparent_hugepage_flags) ||
+		test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
+			&transparent_hugepage_flags);
+}
+
 bool shmem_is_huge(struct vm_area_struct *vma,
 		   struct inode *inode, pgoff_t index)
 {
@@ -486,6 +500,8 @@ bool shmem_is_huge(struct vm_area_struct *vma,
 	if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) ||
 	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)))
 		return false;
+	if (SHMEM_I(inode)->flags & VM_HUGEPAGE)
+		return true;
 	if (shmem_huge == SHMEM_HUGE_FORCE)
 		return true;
 
@@ -676,6 +692,11 @@ static long shmem_unused_huge_count(struct super_block *sb,
 
 #define shmem_huge SHMEM_HUGE_DENY
 
+bool transparent_hugepage_allowed(void)
+{
+	return false;
+}
+
 bool shmem_is_huge(struct vm_area_struct *vma,
 		   struct inode *inode, pgoff_t index)
 {
@@ -2171,10 +2192,14 @@ unsigned long shmem_get_unmapped_area(struct file *file,
 
 	if (shmem_huge != SHMEM_HUGE_FORCE) {
 		struct super_block *sb;
+		struct inode *inode;
 
 		if (file) {
 			VM_BUG_ON(file->f_op != &shmem_file_operations);
-			sb = file_inode(file)->i_sb;
+			inode = file_inode(file);
+			if (SHMEM_I(inode)->flags & VM_HUGEPAGE)
+				goto huge;
+			sb = inode->i_sb;
 		} else {
 			/*
 			 * Called directly from mm/mmap.c, or drivers/char/mem.c
@@ -2187,7 +2212,7 @@ unsigned long shmem_get_unmapped_area(struct file *file,
 		if (SHMEM_SB(sb)->huge == SHMEM_HUGE_NEVER)
 			return addr;
 	}
-
+huge:
 	offset = (pgoff << PAGE_SHIFT) & (HPAGE_PMD_SIZE-1);
 	if (offset && offset + len < 2 * HPAGE_PMD_SIZE)
 		return addr;
@@ -2308,6 +2333,10 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 		atomic_set(&info->stop_eviction, 0);
 		info->seals = F_SEAL_SEAL;
 		info->flags = flags & VM_NORESERVE;
+		if ((flags & VM_HUGEPAGE) &&
+		    transparent_hugepage_allowed() &&
+		    !test_bit(MMF_DISABLE_THP, &current->mm->flags))
+			info->flags |= VM_HUGEPAGE;
 		INIT_LIST_HEAD(&info->shrinklist);
 		INIT_LIST_HEAD(&info->swaplist);
 		simple_xattrs_init(&info->xattrs);
-- 
2.26.2


  parent reply	other threads:[~2021-07-30  7:46 UTC|newest]

Thread overview: 91+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-30  7:22 [PATCH 00/16] tmpfs: HUGEPAGE and MEM_LOCK fcntls and memfds Hugh Dickins
2021-07-30  7:22 ` Hugh Dickins
2021-07-30  7:25 ` [PATCH 01/16] huge tmpfs: fix fallocate(vanilla) advance over huge pages Hugh Dickins
2021-07-30  7:25   ` Hugh Dickins
2021-07-30 21:36   ` Yang Shi
2021-07-30 21:36     ` Yang Shi
2021-08-01  3:38     ` Hugh Dickins
2021-08-01  3:38       ` Hugh Dickins
2021-08-02 20:36       ` Yang Shi
2021-08-02 20:36         ` Yang Shi
2021-07-30  7:28 ` [PATCH 02/16] huge tmpfs: fix split_huge_page() after FALLOC_FL_KEEP_SIZE Hugh Dickins
2021-07-30  7:28   ` Hugh Dickins
2021-07-30 23:48   ` Yang Shi
2021-07-30 23:48     ` Yang Shi
2021-07-30  7:30 ` [PATCH 03/16] huge tmpfs: remove shrinklist addition from shmem_setattr() Hugh Dickins
2021-07-30  7:30   ` Hugh Dickins
2021-07-30 21:50   ` Yang Shi
2021-07-30 21:50     ` Yang Shi
2021-07-30  7:36 ` [PATCH 04/16] huge tmpfs: revert shmem's use of transhuge_vma_enabled() Hugh Dickins
2021-07-30  7:36   ` Hugh Dickins
2021-07-30 21:56   ` Yang Shi
2021-07-30 21:56     ` Yang Shi
2021-08-01  4:01     ` Hugh Dickins
2021-08-01  4:01       ` Hugh Dickins
2021-08-02 20:39       ` Yang Shi
2021-08-02 20:39         ` Yang Shi
2021-07-30  7:39 ` [PATCH 05/16] huge tmpfs: move shmem_huge_enabled() upwards Hugh Dickins
2021-07-30  7:39   ` Hugh Dickins
2021-07-30 21:57   ` Yang Shi
2021-07-30 21:57     ` Yang Shi
2021-07-30  7:42 ` [PATCH 06/16] huge tmpfs: shmem_is_huge(vma, inode, index) Hugh Dickins
2021-07-30  7:42   ` Hugh Dickins
2021-07-30 23:34   ` Yang Shi
2021-07-30 23:34     ` Yang Shi
2021-08-01  5:22     ` Hugh Dickins
2021-08-01  5:22       ` Hugh Dickins
2021-08-01  5:37       ` Hugh Dickins
2021-08-01  5:37         ` Hugh Dickins
2021-08-02 21:14       ` Yang Shi
2021-08-02 21:14         ` Yang Shi
2021-08-04  8:28         ` Hugh Dickins
2021-08-04  8:28           ` Hugh Dickins
2021-08-04 19:01           ` Yang Shi
2021-08-04 19:01             ` Yang Shi
2021-08-06  5:21             ` Hugh Dickins
2021-08-06  5:21               ` Hugh Dickins
2021-08-06 17:41               ` Yang Shi
2021-08-06 17:41                 ` Yang Shi
2021-08-05 23:04         ` Yang Shi
2021-08-05 23:04           ` Yang Shi
2021-08-06  5:43           ` Hugh Dickins
2021-08-06  5:43             ` Hugh Dickins
2021-08-06 17:57             ` Yang Shi
2021-08-06 17:57               ` Yang Shi
2021-08-12 18:19               ` Yang Shi
2021-08-12 18:19                 ` Yang Shi
2021-07-30  7:45 ` Hugh Dickins [this message]
2021-07-30  7:45   ` [PATCH 07/16] memfd: memfd_create(name, MFD_HUGEPAGE) for shmem huge pages Hugh Dickins
2021-07-30 12:01   ` kernel test robot
2021-07-30 12:01     ` kernel test robot
2021-08-04 14:03   ` Kirill A. Shutemov
2021-08-06  3:33     ` Hugh Dickins
2021-08-06  3:33       ` Hugh Dickins
2021-07-30  7:48 ` [PATCH 08/16] huge tmpfs: fcntl(fd, F_HUGEPAGE) and fcntl(fd, F_NOHUGEPAGE) Hugh Dickins
2021-07-30  7:48   ` Hugh Dickins
2021-08-04 14:08   ` Kirill A. Shutemov
2021-08-06  4:34     ` Hugh Dickins
2021-08-06  4:34       ` Hugh Dickins
2021-07-30  7:51 ` [PATCH 09/16] huge tmpfs: decide stat.st_blksize by shmem_is_huge() Hugh Dickins
2021-07-30  7:51   ` Hugh Dickins
2021-07-30 23:40   ` Yang Shi
2021-07-30 23:40     ` Yang Shi
2021-07-30  7:55 ` [PATCH 10/16] tmpfs: fcntl(fd, F_MEM_LOCK) to memlock a tmpfs file Hugh Dickins
2021-07-30  7:55   ` Hugh Dickins
2021-08-03  1:38   ` Matthew Wilcox
2021-08-04  9:15     ` Hugh Dickins
2021-08-04  9:15       ` Hugh Dickins
2021-07-30  7:57 ` [PATCH 11/16] tmpfs: fcntl(fd, F_MEM_LOCKED) to test if memlocked Hugh Dickins
2021-07-30  7:57   ` Hugh Dickins
2021-07-30  8:00 ` [PATCH 12/16] tmpfs: refuse memlock when fallocated beyond i_size Hugh Dickins
2021-07-30  8:00   ` Hugh Dickins
2021-07-30  8:03 ` [PATCH 13/16] mm: bool user_shm_lock(loff_t size, struct ucounts *) Hugh Dickins
2021-07-30  8:03   ` Hugh Dickins
2021-07-30  8:06 ` [PATCH 14/16] mm: user_shm_lock(,,getuc) and user_shm_unlock(,,putuc) Hugh Dickins
2021-07-30  8:06   ` Hugh Dickins
2021-07-30  8:09 ` [PATCH 15/16] tmpfs: permit changing size of memlocked file Hugh Dickins
2021-07-30  8:09   ` Hugh Dickins
2021-07-30  8:13 ` [PATCH 16/16] memfd: memfd_create(name, MFD_MEM_LOCK) for memlocked shmem Hugh Dickins
2021-07-30  8:13   ` Hugh Dickins
2021-07-30 11:24   ` kernel test robot
2021-07-30 11:24     ` kernel test robot

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=c140f56a-1aa3-f7ae-b7d1-93da7d5a3572@google.com \
    --to=hughd@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=chris@chris-wilson.co.uk \
    --cc=ebiederm@xmission.com \
    --cc=hch@infradead.org \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=legion@kernel.org \
    --cc=linmiaohe@huawei.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=matthew.auld@intel.com \
    --cc=mhocko@suse.com \
    --cc=mike.kravetz@oracle.com \
    --cc=riel@surriel.com \
    --cc=shakeelb@google.com \
    --cc=shy828301@gmail.com \
    --cc=willy@infradead.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.