linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Roman Penyaev <rpenyaev@suse.de>
To: unlisted-recipients:; (no To-header on input)
Cc: Roman Penyaev <rpenyaev@suse.de>,
	Andrew Morton <akpm@linux-foundation.org>,
	Al Viro <viro@zeniv.linux.org.uk>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v5 03/14] epoll: allocate user header and user events ring for polling from userspace
Date: Mon, 24 Jun 2019 16:41:40 +0200	[thread overview]
Message-ID: <20190624144151.22688-4-rpenyaev@suse.de> (raw)
In-Reply-To: <20190624144151.22688-1-rpenyaev@suse.de>

This one allocates user header and user events ring according to max items
number, passed as a parameter.  User events (index) ring is in a pow2.
Pages, which will be shared between kernel and userspace, are accounted
through user->locked_vm counter.

No support on architectures with reduced set of atomic ops, namely
arc-plat-eznps, sparc32, parisc.  These architectures have a single
atomic op (something like xchg) and others ops are fudged in kernel
with a support of a spinlock, thus it is impossible to safely share
a variable with a userspace and expect that this variable will not
to be corrupted or observed correctly.  For these archs -EOPNOTSUP
is returned.

Signed-off-by: Roman Penyaev <rpenyaev@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 fs/eventpoll.c                 | 160 +++++++++++++++++++++++++++++++--
 include/uapi/linux/eventpoll.h |   3 +-
 2 files changed, 155 insertions(+), 8 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 6d7a5fe4a831..b6682365d970 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -228,6 +228,33 @@ struct eventpoll {
 
 	struct file *file;
 
+	/* User header with array of items */
+	struct epoll_uheader *user_header;
+
+	/* User index, which acts as a ring of coming events */
+	unsigned int *user_index;
+
+	/* Actual length of user header, always aligned on page */
+	unsigned int header_length;
+
+	/* Actual length of user index, always pow2 */
+	unsigned int index_length;
+
+	/* Maximum possible event items */
+	unsigned int max_items_nr;
+
+	/* Items bitmap, is used to get a free bit for new registered epi */
+	unsigned long *items_bm;
+
+	/* Length of both items bitmaps, always aligned on page */
+	unsigned int items_bm_length;
+
+	/*
+	 * Counter to support atomic and lockless ->tail updates.
+	 * See add_event_to_uring() for details of counter layout.
+	 */
+	atomic64_t shadow_cnt;
+
 	/* used to optimize loop detection check */
 	int visited;
 	struct list_head visited_list_link;
@@ -377,6 +404,44 @@ static void ep_nested_calls_init(struct nested_calls *ncalls)
 	spin_lock_init(&ncalls->lock);
 }
 
+static inline unsigned int ep_to_items_length(unsigned int nr)
+{
+	struct epoll_uheader *user_header;
+
+	return PAGE_ALIGN(struct_size(user_header, items, nr));
+}
+
+static inline unsigned int ep_to_index_length(unsigned int nr)
+{
+	struct eventpoll *ep;
+	unsigned int size;
+
+	size = roundup_pow_of_two(nr << ilog2(sizeof(*ep->user_index)));
+	return max_t(typeof(size), size, PAGE_SIZE);
+}
+
+static inline unsigned int ep_to_items_bm_length(unsigned int nr)
+{
+	return PAGE_ALIGN(ALIGN(nr, 8) >> 3);
+}
+
+static inline bool ep_userpoll_supported(void)
+{
+	/*
+	 * These architectures have a single atomic op (something like
+	 * xchg) and others ops are fudged in kernel with a support of
+	 * a spinlock, thus it is impossible to safely share a variable
+	 * with a userspace and expect that this variable will not to
+	 * be corrupted or observed correctly.  The problematic variable
+	 * is ->ready_events, which has to be atomically cleared on
+	 * userspace, but on the kernel side cmpxchg() is called, which
+	 * uses a spinlock as a method of synchronization.
+	 */
+	return !(IS_ENABLED(CONFIG_ARC_PLAT_EZNPS) ||
+		 IS_ENABLED(CONFIG_SPARC32) ||
+		 IS_ENABLED(CONFIG_PARISC));
+}
+
 /**
  * ep_events_available - Checks if ready events might be available.
  *
@@ -832,6 +897,38 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
 	return 0;
 }
 
+static int ep_account_mem(struct eventpoll *ep, struct user_struct *user)
+{
+	unsigned long nr_pages, page_limit, cur_pages, new_pages;
+
+	nr_pages  = ep->header_length >> PAGE_SHIFT;
+	nr_pages += ep->index_length >> PAGE_SHIFT;
+
+	/* Don't allow more pages than we can safely lock */
+	page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+
+	do {
+		cur_pages = atomic_long_read(&user->locked_vm);
+		new_pages = cur_pages + nr_pages;
+		if (new_pages > page_limit && !capable(CAP_IPC_LOCK))
+			return -ENOMEM;
+	} while (atomic_long_cmpxchg(&user->locked_vm, cur_pages,
+				     new_pages) != cur_pages);
+
+	return 0;
+}
+
+static void ep_unaccount_mem(struct eventpoll *ep, struct user_struct *user)
+{
+	unsigned long nr_pages;
+
+	nr_pages  = ep->header_length >> PAGE_SHIFT;
+	nr_pages += ep->index_length >> PAGE_SHIFT;
+	if (nr_pages)
+		/* When polled by user */
+		atomic_long_sub(nr_pages, &user->locked_vm);
+}
+
 static void ep_free(struct eventpoll *ep)
 {
 	struct rb_node *rbp;
@@ -879,8 +976,12 @@ static void ep_free(struct eventpoll *ep)
 
 	mutex_unlock(&epmutex);
 	mutex_destroy(&ep->mtx);
-	free_uid(ep->user);
 	wakeup_source_unregister(ep->ws);
+	vfree(ep->user_header);
+	vfree(ep->user_index);
+	vfree(ep->items_bm);
+	ep_unaccount_mem(ep, ep->user);
+	free_uid(ep->user);
 	kfree(ep);
 }
 
@@ -1033,7 +1134,7 @@ void eventpoll_release_file(struct file *file)
 	mutex_unlock(&epmutex);
 }
 
-static int ep_alloc(struct eventpoll **pep)
+static int ep_alloc(struct eventpoll **pep, int flags, size_t max_items)
 {
 	int error;
 	struct user_struct *user;
@@ -1045,6 +1146,44 @@ static int ep_alloc(struct eventpoll **pep)
 	if (unlikely(!ep))
 		goto free_uid;
 
+	if (flags & EPOLL_USERPOLL) {
+		BUILD_BUG_ON(sizeof(*ep->user_header) !=
+			     EPOLL_USERPOLL_HEADER_SIZE);
+		BUILD_BUG_ON(sizeof(ep->user_header->items[0]) != 16);
+
+		error = -EOPNOTSUPP;
+		if (!ep_userpoll_supported())
+			goto free_ep;
+
+		error = -EINVAL;
+		if (!max_items || max_items > EP_USERPOLL_MAX_ITEMS_NR)
+			goto free_ep;
+
+		ep->max_items_nr = max_items;
+		ep->header_length = ep_to_items_length(max_items);
+		ep->index_length = ep_to_index_length(max_items);
+		ep->items_bm_length = ep_to_items_bm_length(max_items);
+
+		error = ep_account_mem(ep, user);
+		if (error)
+			goto free_ep;
+
+		error = -ENOMEM;
+		ep->user_header = vmalloc_user(ep->header_length);
+		ep->user_index = vmalloc_user(ep->index_length);
+		ep->items_bm = vzalloc(ep->items_bm_length);
+		if (!ep->user_header || !ep->user_index || !ep->items_bm)
+			goto unaccount_mem;
+
+		*ep->user_header = (typeof(*ep->user_header)) {
+			.magic         = EPOLL_USERPOLL_HEADER_MAGIC,
+			.header_length = ep->header_length,
+			.index_length  = ep->index_length,
+			.max_items_nr  = ep->max_items_nr,
+		};
+	}
+
+	atomic64_set(&ep->shadow_cnt, 0);
 	mutex_init(&ep->mtx);
 	rwlock_init(&ep->lock);
 	init_waitqueue_head(&ep->wq);
@@ -1058,6 +1197,13 @@ static int ep_alloc(struct eventpoll **pep)
 
 	return 0;
 
+unaccount_mem:
+	ep_unaccount_mem(ep, user);
+	vfree(ep->user_header);
+	vfree(ep->user_index);
+	vfree(ep->items_bm);
+free_ep:
+	kfree(ep);
 free_uid:
 	free_uid(user);
 	return error;
@@ -2062,7 +2208,7 @@ static void clear_tfile_check_list(void)
 /*
  * Open an eventpoll file descriptor.
  */
-static int do_epoll_create(int flags)
+static int do_epoll_create(int flags, size_t size)
 {
 	int error, fd;
 	struct eventpoll *ep = NULL;
@@ -2071,12 +2217,12 @@ static int do_epoll_create(int flags)
 	/* Check the EPOLL_* constant for consistency.  */
 	BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);
 
-	if (flags & ~EPOLL_CLOEXEC)
+	if (flags & ~(EPOLL_CLOEXEC | EPOLL_USERPOLL))
 		return -EINVAL;
 	/*
 	 * Create the internal data structure ("struct eventpoll").
 	 */
-	error = ep_alloc(&ep);
+	error = ep_alloc(&ep, flags, size);
 	if (error < 0)
 		return error;
 	/*
@@ -2107,7 +2253,7 @@ static int do_epoll_create(int flags)
 
 SYSCALL_DEFINE1(epoll_create1, int, flags)
 {
-	return do_epoll_create(flags);
+	return do_epoll_create(flags, 0);
 }
 
 SYSCALL_DEFINE1(epoll_create, int, size)
@@ -2115,7 +2261,7 @@ SYSCALL_DEFINE1(epoll_create, int, size)
 	if (size <= 0)
 		return -EINVAL;
 
-	return do_epoll_create(0);
+	return do_epoll_create(0, 0);
 }
 
 /*
diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h
index 3317901b19c4..efd58e9177c2 100644
--- a/include/uapi/linux/eventpoll.h
+++ b/include/uapi/linux/eventpoll.h
@@ -20,7 +20,8 @@
 #include <linux/types.h>
 
 /* Flags for epoll_create1.  */
-#define EPOLL_CLOEXEC O_CLOEXEC
+#define EPOLL_CLOEXEC  O_CLOEXEC
+#define EPOLL_USERPOLL 1
 
 /* Valid opcodes to issue to sys_epoll_ctl() */
 #define EPOLL_CTL_ADD 1
-- 
2.21.0


  parent reply	other threads:[~2019-06-24 14:42 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-24 14:41 [PATCH v5 00/14] epoll: support pollable epoll " Roman Penyaev
2019-06-24 14:41 ` [PATCH v5 01/14] epoll: move private helpers from a header to the source Roman Penyaev
2019-06-24 14:41 ` [PATCH v5 02/14] epoll: introduce user structures for polling from userspace Roman Penyaev
2019-06-24 14:41 ` Roman Penyaev [this message]
2019-06-24 14:41 ` [PATCH v5 04/14] epoll: some sanity flags checks for epoll syscalls " Roman Penyaev
2019-06-24 14:41 ` [PATCH v5 05/14] epoll: offload polling to a work in case of epfd polled " Roman Penyaev
2019-06-24 14:41 ` [PATCH v5 06/14] epoll: introduce helpers for adding/removing events to uring Roman Penyaev
2019-06-24 14:41 ` [PATCH v5 07/14] epoll: call ep_add_event_to_uring() from ep_poll_callback() Roman Penyaev
2019-06-24 14:41 ` [PATCH v5 08/14] epoll: support polling from userspace for ep_insert() Roman Penyaev
2019-06-24 14:41 ` [PATCH v5 09/14] epoll: support polling from userspace for ep_remove() Roman Penyaev
2019-06-24 14:41 ` [PATCH v5 10/14] epoll: support polling from userspace for ep_modify() Roman Penyaev
2019-06-24 14:41 ` [PATCH v5 11/14] epoll: support polling from userspace for ep_poll() Roman Penyaev
2019-06-24 14:41 ` [PATCH v5 12/14] epoll: support mapping for epfd when polled from userspace Roman Penyaev
2019-06-24 14:41 ` [PATCH v5 13/14] epoll: implement epoll_create2() syscall Roman Penyaev
2019-06-24 16:14   ` Arnd Bergmann
2019-06-24 16:25     ` Roman Penyaev
2019-06-25 18:29   ` Eric Wong
2019-06-24 14:41 ` [PATCH v5 14/14] kselftest: add uepoll-test which tests polling from userspace Roman Penyaev
2019-06-24 20:38 ` [PATCH v5 00/14] epoll: support pollable epoll " Linus Torvalds
2019-06-25 11:19   ` Roman Penyaev
2019-06-25  0:24 ` Eric Wong
2019-06-25 11:07   ` Roman Penyaev

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=20190624144151.22688-4-rpenyaev@suse.de \
    --to=rpenyaev@suse.de \
    --cc=akpm@linux-foundation.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=torvalds@linux-foundation.org \
    --cc=viro@zeniv.linux.org.uk \
    --subject='Re: [PATCH v5 03/14] epoll: allocate user header and user events ring for polling from userspace' \
    /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

This is a public inbox, see mirroring instructions
on how to clone and mirror all data and code used for this inbox