[PATCH v5 0/2] make hvc pass dma capable memory to its backend

[PATCH v5 0/2] make hvc pass dma capable memory to its backend

[Xianting Tian]

Dear all,

This patch series make hvc framework pass DMA capable memory to
put_chars() of hvc backend(eg, virtio-console), and revert commit
c4baad5029 ("virtio-console: avoid DMA from stack”)

V1
virtio-console: avoid DMA from vmalloc area
https://lkml.org/lkml/2021/7/27/494

For v1 patch, Arnd Bergmann suggests to fix the issue in the first
place:
Make hvc pass DMA capable memory to put_chars()
The fix suggestion is included in v2.

V2
[PATCH 1/2] tty: hvc: pass DMA capable memory to put_chars()
https://lkml.org/lkml/2021/8/1/8
[PATCH 2/2] virtio-console: remove unnecessary kmemdup()
https://lkml.org/lkml/2021/8/1/9

For v2 patch, Arnd Bergmann suggests to make new buf part of the
hvc_struct structure, and fix the compile issue.
The fix suggestion is included in v3.

V3
[PATCH v3 1/2] tty: hvc: pass DMA capable memory to put_chars()
https://lkml.org/lkml/2021/8/3/1347
[PATCH v3 2/2] virtio-console: remove unnecessary kmemdup()
https://lkml.org/lkml/2021/8/3/1348

For v3 patch, Jiri Slaby suggests to make 'char c[N_OUTBUF]' part of
hvc_struct, and make 'hp->outbuf' aligned and use struct_size() to
calculate the size of hvc_struct. The fix suggestion is included in
v4.

V4
[PATCH v4 0/2] make hvc pass dma capable memory to its backend
https://lkml.org/lkml/2021/8/5/1350
[PATCH v4 1/2] tty: hvc: pass DMA capable memory to put_chars()
https://lkml.org/lkml/2021/8/5/1351
[PATCH v4 2/2] virtio-console: remove unnecessary kmemdup()
https://lkml.org/lkml/2021/8/5/1352

For v4 patch, Arnd Bergmann suggests to introduce another
array(cons_outbuf[]) for the buffer pointers next to the cons_ops[]
and vtermnos[] arrays. This fix included in this v5 patch.

drivers/char/virtio_console.c | 12 ++----------
drivers/tty/hvc/hvc_console.c | 40 +++++++++++++++++++++--------------
drivers/tty/hvc/hvc_console.h | 16 ++++++++++++--
3 file changed

[PATCH v5 1/2] tty: hvc: pass DMA capable memory to put_chars()

[Xianting Tian]

As well known, hvc backend can register its opertions to hvc backend.
the opertions contain put_chars(), get_chars() and so on.

Some hvc backend may do dma in its opertions. eg, put_chars() of
virtio-console. But in the code of hvc framework, it may pass DMA
incapable memory to put_chars() under a specific configuration, which
is explained in commit c4baad5029(virtio-console: avoid DMA from stack):
1, c[] is on stack,
   hvc_console_print():
	char c[N_OUTBUF] __ALIGNED__;
	cons_ops[index]->put_chars(vtermnos[index], c, i);
2, ch is on stack,
   static void hvc_poll_put_char(,,char ch)
   {
	struct tty_struct *tty = driver->ttys[0];
	struct hvc_struct *hp = tty->driver_data;
	int n;

	do {
		n = hp->ops->put_chars(hp->vtermno, &ch, 1);
	} while (n <= 0);
   }

Commit c4baad5029 is just the fix to avoid DMA from stack memory, which
is passed to virtio-console by hvc framework in above code. But I think
the fix is aggressive, it directly uses kmemdup() to alloc new buffer
from kmalloc area and do memcpy no matter the memory is in kmalloc area
or not. But most importantly, it should better be fixed in the hvc
framework, by changing it to never pass stack memory to the put_chars()
function in the first place. Otherwise, we still face the same issue if
a new hvc backend using dma added in the furture.

We make 'char c[N_OUTBUF]' part of 'struct hvc_struct', so hp->c is no
longer the stack memory. we can use it in above two cases.

Other cleanup is use ARCH_DMA_MINALIGN for align, and make 'hp->outbuf'
aligned and use struct_size() for the size parameter of kzalloc().

With the patch, we can remove the fix c4baad5029.

Signed-off-by: Xianting Tian <xianting.tian@linux.alibaba.com>
Tested-by: Xianting Tian <xianting.tian@linux.alibaba.com>
---
 drivers/tty/hvc/hvc_console.c | 40 +++++++++++++++++++++--------------
 drivers/tty/hvc/hvc_console.h | 16 ++++++++++++--
 2 files changed, 38 insertions(+), 18 deletions(-)

diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index 5bb8c4e44..c56564eb7 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -41,16 +41,6 @@
  */
 #define HVC_CLOSE_WAIT (HZ/100) /* 1/10 of a second */
 
-/*
- * These sizes are most efficient for vio, because they are the
- * native transfer size. We could make them selectable in the
- * future to better deal with backends that want other buffer sizes.
- */
-#define N_OUTBUF	16
-#define N_INBUF		16
-
-#define __ALIGNED__ __attribute__((__aligned__(sizeof(long))))
-
 static struct tty_driver *hvc_driver;
 static struct task_struct *hvc_task;
 
@@ -142,6 +132,7 @@ static int hvc_flush(struct hvc_struct *hp)
 static const struct hv_ops *cons_ops[MAX_NR_HVC_CONSOLES];
 static uint32_t vtermnos[MAX_NR_HVC_CONSOLES] =
 	{[0 ... MAX_NR_HVC_CONSOLES - 1] = -1};
+static char *cons_outbuf[MAX_NR_HVC_CONSOLES];
 
 /*
  * Console APIs, NOT TTY.  These APIs are available immediately when
@@ -151,18 +142,23 @@ static uint32_t vtermnos[MAX_NR_HVC_CONSOLES] =
 static void hvc_console_print(struct console *co, const char *b,
 			      unsigned count)
 {
-	char c[N_OUTBUF] __ALIGNED__;
+	char *c;
 	unsigned i = 0, n = 0;
 	int r, donecr = 0, index = co->index;
+	unsigned long flags;
+	struct hvc_struct *hp;
 
 	/* Console access attempt outside of acceptable console range. */
 	if (index >= MAX_NR_HVC_CONSOLES)
 		return;
 
 	/* This console adapter was removed so it is not usable. */
-	if (vtermnos[index] == -1)
+	if (vtermnos[index] == -1 || !cons_outbuf[index])
 		return;
 
+	c = cons_outbuf[index];
+
+	spin_lock_irqsave(&hp->c_lock, flags);
 	while (count > 0 || i > 0) {
 		if (count > 0 && i < sizeof(c)) {
 			if (b[n] == '\n' && !donecr) {
@@ -191,6 +187,7 @@ static void hvc_console_print(struct console *co, const char *b,
 			}
 		}
 	}
+	spin_unlock_irqrestore(&hp->c_lock, flags);
 	hvc_console_flush(cons_ops[index], vtermnos[index]);
 }
 
@@ -878,9 +875,19 @@ static void hvc_poll_put_char(struct tty_driver *driver, int line, char ch)
 	struct tty_struct *tty = driver->ttys[0];
 	struct hvc_struct *hp = tty->driver_data;
 	int n;
+	unsigned long flags;
+	char *c;
+
+	if (!hp || !cons_outbuf[hp->index])
+		return;
+
+	c = cons_outbuf[hp->index];
 
 	do {
-		n = hp->ops->put_chars(hp->vtermno, &ch, 1);
+		spin_lock_irqsave(&hp->c_lock, flags);
+		c[0] = ch;
+		n = hp->ops->put_chars(hp->vtermno, c, 1);
+		spin_unlock_irqrestore(&hp->c_lock, flags);
 	} while (n <= 0);
 }
 #endif
@@ -922,8 +929,7 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 			return ERR_PTR(err);
 	}
 
-	hp = kzalloc(ALIGN(sizeof(*hp), sizeof(long)) + outbuf_size,
-			GFP_KERNEL);
+	hp = kzalloc(struct_size(hp, outbuf, outbuf_size), GFP_KERNEL);
 	if (!hp)
 		return ERR_PTR(-ENOMEM);
 
@@ -931,13 +937,13 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 	hp->data = data;
 	hp->ops = ops;
 	hp->outbuf_size = outbuf_size;
-	hp->outbuf = &((char *)hp)[ALIGN(sizeof(*hp), sizeof(long))];
 
 	tty_port_init(&hp->port);
 	hp->port.ops = &hvc_port_ops;
 
 	INIT_WORK(&hp->tty_resize, hvc_set_winsz);
 	spin_lock_init(&hp->lock);
+	spin_lock_init(&hp->c_lock);
 	mutex_lock(&hvc_structs_mutex);
 
 	/*
@@ -964,6 +970,7 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 	if (i < MAX_NR_HVC_CONSOLES) {
 		cons_ops[i] = ops;
 		vtermnos[i] = vtermno;
+		cons_outbuf[i] = hp->c;
 	}
 
 	list_add_tail(&(hp->next), &hvc_structs);
@@ -988,6 +995,7 @@ int hvc_remove(struct hvc_struct *hp)
 	if (hp->index < MAX_NR_HVC_CONSOLES) {
 		vtermnos[hp->index] = -1;
 		cons_ops[hp->index] = NULL;
+		cons_outbuf[hp->index] = NULL;
 	}
 
 	/* Don't whack hp->irq because tty_hangup() will need to free the irq. */
diff --git a/drivers/tty/hvc/hvc_console.h b/drivers/tty/hvc/hvc_console.h
index 18d005814..52374e2da 100644
--- a/drivers/tty/hvc/hvc_console.h
+++ b/drivers/tty/hvc/hvc_console.h
@@ -32,13 +32,21 @@
  */
 #define HVC_ALLOC_TTY_ADAPTERS	8
 
+/*
+ * These sizes are most efficient for vio, because they are the
+ * native transfer size. We could make them selectable in the
+ * future to better deal with backends that want other buffer sizes.
+ */
+#define N_OUTBUF	16
+#define N_INBUF		16
+
+#define __ALIGNED__ __attribute__((__aligned__(sizeof(long))))
+
 struct hvc_struct {
 	struct tty_port port;
 	spinlock_t lock;
 	int index;
 	int do_wakeup;
-	char *outbuf;
-	int outbuf_size;
 	int n_outbuf;
 	uint32_t vtermno;
 	const struct hv_ops *ops;
@@ -48,6 +56,10 @@ struct hvc_struct {
 	struct work_struct tty_resize;
 	struct list_head next;
 	unsigned long flags;
+	spinlock_t c_lock;
+	char c[N_OUTBUF] __ALIGNED__;
+	int outbuf_size;
+	char outbuf[0] __ALIGNED__;
 };
 
 /* implemented by a low level driver */
-- 
2.17.1

[PATCH v5 2/2] virtio-console: remove unnecessary kmemdup()

[Xianting Tian]

hvc framework will never pass stack memory to the put_chars() function,
So the calling of kmemdup() is unnecessary, we can remove it.

This revert commit c4baad5029 ("virtio-console: avoid DMA from stack")

Signed-off-by: Xianting Tian <xianting.tian@linux.alibaba.com>
---
 drivers/char/virtio_console.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 7eaf303a7..4ed3ffb1d 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1117,8 +1117,6 @@ static int put_chars(u32 vtermno, const char *buf, int count)
 {
 	struct port *port;
 	struct scatterlist sg[1];
-	void *data;
-	int ret;
 
 	if (unlikely(early_put_chars))
 		return early_put_chars(vtermno, buf, count);
@@ -1127,14 +1125,8 @@ static int put_chars(u32 vtermno, const char *buf, int count)
 	if (!port)
 		return -EPIPE;
 
-	data = kmemdup(buf, count, GFP_ATOMIC);
-	if (!data)
-		return -ENOMEM;
-
-	sg_init_one(sg, data, count);
-	ret = __send_to_port(port, sg, 1, count, data, false);
-	kfree(data);
-	return ret;
+	sg_init_one(sg, buf, count);
+	return __send_to_port(port, sg, 1, count, (void *)buf, false);
 }
 
 /*
-- 
2.17.1