| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20120809123039.8542.18593.stgit@ltc189.sdl.hitachi.co.jp>
Date: Thu, 09 Aug 2012 21:30:39 +0900
From: Yoshihiro YUNOMAE <yoshihiro.yunomae.ez@...achi.com>
To: linux-kernel@...r.kernel.org
Cc: Amit Shah <amit.shah@...hat.com>,
Anthony Liguori <anthony@...emonkey.ws>,
Arnd Bergmann <arnd@...db.de>, Borislav Petkov <bp@...64.org>,
"Franch Ch. Eigler" <fche@...hat.com>,
Frederic Weisbecker <fweisbec@...il.com>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Herbert Xu <herbert@...dor.apana.org.au>,
Ingo Molnar <mingo@...hat.com>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>,
Rusty Russell <rusty@...tcorp.com.au>,
Steven Rostedt <rostedt@...dmis.org>,
virtualization@...ts.linux-foundation.org, qemu-devel@...gnu.org,
yrl.pp-manager.tt@...achi.com,
Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>
Subject: [PATCH V2 1/6] virtio/console: Add splice_write support
From: Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>
Enable to use splice_write from pipe to virtio-console port.
This steals pages from pipe and directly send it to host.
Note that this may accelerate only the guest to host path.
Changes in v2:
- Use GFP_KERNEL instead of GFP_ATOMIC in syscall context function.
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>
---
drivers/char/virtio_console.c | 136 +++++++++++++++++++++++++++++++++++++++--
1 files changed, 128 insertions(+), 8 deletions(-)
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index cdf2f54..730816c 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -24,6 +24,8 @@
#include <linux/err.h>
#include <linux/freezer.h>
#include <linux/fs.h>
+#include <linux/splice.h>
+#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/poll.h>
@@ -227,6 +229,7 @@ struct port {
bool guest_connected;
};
+#define MAX_SPLICE_PAGES 32
/* This is the very early arch-specified put chars function. */
static int (*early_put_chars)(u32, const char *, int);
@@ -474,26 +477,52 @@ static ssize_t send_control_msg(struct port *port, unsigned int event,
return 0;
}
+struct buffer_token {
+ union {
+ void *buf;
+ struct scatterlist *sg;
+ } u;
+ bool sgpages;
+};
+
+static void reclaim_sg_pages(struct scatterlist *sg)
+{
+ int i;
+ struct page *page;
+
+ for (i = 0; i < MAX_SPLICE_PAGES; i++) {
+ page = sg_page(&sg[i]);
+ if (!page)
+ break;
+ put_page(page);
+ }
+ kfree(sg);
+}
+
/* Callers must take the port->outvq_lock */
static void reclaim_consumed_buffers(struct port *port)
{
- void *buf;
+ struct buffer_token *tok;
unsigned int len;
if (!port->portdev) {
/* Device has been unplugged. vqs are already gone. */
return;
}
- while ((buf = virtqueue_get_buf(port->out_vq, &len))) {
- kfree(buf);
+ while ((tok = virtqueue_get_buf(port->out_vq, &len))) {
+ if (tok->sgpages)
+ reclaim_sg_pages(tok->u.sg);
+ else
+ kfree(tok->u.buf);
+ kfree(tok);
port->outvq_full = false;
}
}
-static ssize_t send_buf(struct port *port, void *in_buf, size_t in_count,
- bool nonblock)
+static ssize_t __send_to_port(struct port *port, struct scatterlist *sg,
+ int nents, size_t in_count,
+ struct buffer_token *tok, bool nonblock)
{
- struct scatterlist sg[1];
struct virtqueue *out_vq;
ssize_t ret;
unsigned long flags;
@@ -505,8 +534,7 @@ static ssize_t send_buf(struct port *port, void *in_buf, size_t in_count,
reclaim_consumed_buffers(port);
- sg_init_one(sg, in_buf, in_count);
- ret = virtqueue_add_buf(out_vq, sg, 1, 0, in_buf, GFP_ATOMIC);
+ ret = virtqueue_add_buf(out_vq, sg, nents, 0, tok, GFP_ATOMIC);
/* Tell Host to go! */
virtqueue_kick(out_vq);
@@ -544,6 +572,37 @@ done:
return in_count;
}
+static ssize_t send_buf(struct port *port, void *in_buf, size_t in_count,
+ bool nonblock)
+{
+ struct scatterlist sg[1];
+ struct buffer_token *tok;
+
+ tok = kmalloc(sizeof(*tok), GFP_ATOMIC);
+ if (!tok)
+ return -ENOMEM;
+ tok->sgpages = false;
+ tok->u.buf = in_buf;
+
+ sg_init_one(sg, in_buf, in_count);
+
+ return __send_to_port(port, sg, 1, in_count, tok, nonblock);
+}
+
+static ssize_t send_pages(struct port *port, struct scatterlist *sg, int nents,
+ size_t in_count, bool nonblock)
+{
+ struct buffer_token *tok;
+
+ tok = kmalloc(sizeof(*tok), GFP_ATOMIC);
+ if (!tok)
+ return -ENOMEM;
+ tok->sgpages = true;
+ tok->u.sg = sg;
+
+ return __send_to_port(port, sg, nents, in_count, tok, nonblock);
+}
+
/*
* Give out the data that's requested from the buffer that we have
* queued up.
@@ -725,6 +784,66 @@ out:
return ret;
}
+struct sg_list {
+ unsigned int n;
+ size_t len;
+ struct scatterlist *sg;
+};
+
+static int pipe_to_sg(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
+ struct splice_desc *sd)
+{
+ struct sg_list *sgl = sd->u.data;
+ unsigned int len = 0;
+
+ if (sgl->n == MAX_SPLICE_PAGES)
+ return 0;
+
+ /* Try lock this page */
+ if (buf->ops->steal(pipe, buf) == 0) {
+ /* Get reference and unlock page for moving */
+ get_page(buf->page);
+ unlock_page(buf->page);
+
+ len = min(buf->len, sd->len);
+ sg_set_page(&(sgl->sg[sgl->n]), buf->page, len, buf->offset);
+ sgl->n++;
+ sgl->len += len;
+ }
+
+ return len;
+}
+
+/* Faster zero-copy write by splicing */
+static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
+ struct file *filp, loff_t *ppos,
+ size_t len, unsigned int flags)
+{
+ struct port *port = filp->private_data;
+ struct sg_list sgl;
+ ssize_t ret;
+ struct splice_desc sd = {
+ .total_len = len,
+ .flags = flags,
+ .pos = *ppos,
+ .u.data = &sgl,
+ };
+
+ sgl.n = 0;
+ sgl.len = 0;
+ sgl.sg = kmalloc(sizeof(struct scatterlist) * MAX_SPLICE_PAGES,
+ GFP_KERNEL);
+ if (unlikely(!sgl.sg))
+ return -ENOMEM;
+
+ sg_init_table(sgl.sg, MAX_SPLICE_PAGES);
+ ret = __splice_from_pipe(pipe, &sd, pipe_to_sg);
+ if (likely(ret > 0))
+ ret = send_pages(port, sgl.sg, sgl.n, sgl.len, true);
+
+ return ret;
+}
+
static unsigned int port_fops_poll(struct file *filp, poll_table *wait)
{
struct port *port;
@@ -856,6 +975,7 @@ static const struct file_operations port_fops = {
.open = port_fops_open,
.read = port_fops_read,
.write = port_fops_write,
+ .splice_write = port_fops_splice_write,
.poll = port_fops_poll,
.release = port_fops_release,
.fasync = port_fops_fasync,
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists