hvc and powerpc opal console latency reduction

index 48fbb41af5d1..e695b836fd49 100644
@@ -388,7 +388,7 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 		/* Closed or other error drop */
 		if (rc != OPAL_SUCCESS && rc != OPAL_BUSY &&
 		    rc != OPAL_BUSY_EVENT) {
-			written = total_len;
+			written += total_len;
 			break;
 		}
 		if (rc == OPAL_SUCCESS) {

index e695b836fd49..6b621d47ac29 100644
@@ -378,33 +378,41 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 	/* We still try to handle partial completions, though they
 	 * should no longer happen.
 	 */
-	rc = OPAL_BUSY;
-	while(total_len > 0 && (rc == OPAL_BUSY ||
-				rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) {
+
+	while (total_len > 0) {
 		olen = cpu_to_be64(total_len);
-		rc = opal_console_write(vtermno, &olen, data);
+
+		rc = OPAL_BUSY;
+		while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+			rc = opal_console_write(vtermno, &olen, data);
+			if (rc == OPAL_BUSY_EVENT) {
+				mdelay(OPAL_BUSY_DELAY_MS);
+				opal_poll_events(NULL);
+			} else if (rc == OPAL_BUSY) {
+				mdelay(OPAL_BUSY_DELAY_MS);
+			}
+		}
+
 		len = be64_to_cpu(olen);
 
 		/* Closed or other error drop */
-		if (rc != OPAL_SUCCESS && rc != OPAL_BUSY &&
-		    rc != OPAL_BUSY_EVENT) {
-			written += total_len;
+		if (rc != OPAL_SUCCESS) {
+			written += total_len; /* drop remaining chars */
 			break;
 		}
-		if (rc == OPAL_SUCCESS) {
-			total_len -= len;
-			data += len;
-			written += len;
-		}
+
+		total_len -= len;
+		data += len;
+		written += len;
+
 		/* This is a bit nasty but we need that for the console to
 		 * flush when there aren't any interrupts. We will clean
 		 * things a bit later to limit that to synchronous path
 		 * such as the kernel console and xmon/udbg
 		 */
-		do
+		do {
 			opal_poll_events(&evt);
-		while(rc == OPAL_SUCCESS &&
-			(be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT));
+		} while (be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT);
 	}
 	spin_unlock_irqrestore(&opal_write_lock, flags);
 	return written;

index 6f1214d4de92..f8f41ccce75f 100644
@@ -12,6 +12,7 @@
  */
 
 #include <linux/kmsg_dump.h>
+#include <linux/delay.h>
 
 #include <asm/opal.h>
 #include <asm/opal-api.h>

@@ -26,8 +27,7 @@
 static void force_opal_console_flush(struct kmsg_dumper *dumper,
 				     enum kmsg_dump_reason reason)
 {
-	int i;
-	int64_t ret;
+	s64 rc;
 
 	/*
 	 * Outside of a panic context the pollers will continue to run,

@@ -37,14 +37,22 @@ static void force_opal_console_flush(struct kmsg_dumper *dumper,
 		return;
 
 	if (opal_check_token(OPAL_CONSOLE_FLUSH)) {
-		ret = opal_console_flush(0);
+		do  {
+			rc = OPAL_BUSY;
+			while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+				rc = opal_console_flush(0);
+				if (rc == OPAL_BUSY_EVENT) {
+					mdelay(OPAL_BUSY_DELAY_MS);
+					opal_poll_events(NULL);
+				} else if (rc == OPAL_BUSY) {
+					mdelay(OPAL_BUSY_DELAY_MS);
+				}
+			}
+		} while (rc == OPAL_PARTIAL); /* More to flush */
 
-		if (ret == OPAL_UNSUPPORTED || ret == OPAL_PARAMETER)
-			return;
-
-		/* Incrementally flush until there's nothing left */
-		while (opal_console_flush(0) != OPAL_SUCCESS);
 	} else {
+		int i;
+
 		/*
 		 * If OPAL_CONSOLE_FLUSH is not implemented in the firmware,
 		 * the console can still be flushed by calling the polling

index f8f41ccce75f..fd2bbf4fd6dc 100644
@@ -51,20 +51,17 @@ static void force_opal_console_flush(struct kmsg_dumper *dumper,
 		} while (rc == OPAL_PARTIAL); /* More to flush */
 
 	} else {
-		int i;
+		__be64 evt;
 
+		WARN_ONCE(1, "opal: OPAL_CONSOLE_FLUSH missing.\n");
 		/*
 		 * If OPAL_CONSOLE_FLUSH is not implemented in the firmware,
 		 * the console can still be flushed by calling the polling
-		 * function enough times to flush the buffer.  We don't know
-		 * how much output still needs to be flushed, but we can be
-		 * generous since the kernel is in panic and doesn't need
-		 * to do much else.
+		 * function while it has OPAL_EVENT_CONSOLE_OUTPUT events.
 		 */
-		printk(KERN_NOTICE "opal: OPAL_CONSOLE_FLUSH missing.\n");
-		for (i = 0; i < 1024; i++) {
-			opal_poll_events(NULL);
-		}
+		do {
+			opal_poll_events(&evt);
+		} while (be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT);
 	}
 }
 

index 03e1a920491e..bbff49fab0e5 100644
@@ -303,6 +303,7 @@ extern void opal_configure_cores(void);
 
 extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
 extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
+extern int opal_flush_console(uint32_t vtermno);
 
 extern void hvc_opal_init_early(void);
 

index fd2bbf4fd6dc..55691950d981 100644
@@ -12,7 +12,6 @@
  */
 
 #include <linux/kmsg_dump.h>
-#include <linux/delay.h>
 
 #include <asm/opal.h>
 #include <asm/opal-api.h>

@@ -24,11 +23,9 @@
  * may not be completely printed.  This function does not actually dump the
  * message, it just ensures that OPAL completely flushes the console buffer.
  */
-static void force_opal_console_flush(struct kmsg_dumper *dumper,
+static void kmsg_dump_opal_console_flush(struct kmsg_dumper *dumper,
 				     enum kmsg_dump_reason reason)
 {
-	s64 rc;
-
 	/*
 	 * Outside of a panic context the pollers will continue to run,
 	 * so we don't need to do any special flushing.

@@ -36,37 +33,11 @@ static void force_opal_console_flush(struct kmsg_dumper *dumper,
 	if (reason != KMSG_DUMP_PANIC)
 		return;
 
-	if (opal_check_token(OPAL_CONSOLE_FLUSH)) {
-		do  {
-			rc = OPAL_BUSY;
-			while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-				rc = opal_console_flush(0);
-				if (rc == OPAL_BUSY_EVENT) {
-					mdelay(OPAL_BUSY_DELAY_MS);
-					opal_poll_events(NULL);
-				} else if (rc == OPAL_BUSY) {
-					mdelay(OPAL_BUSY_DELAY_MS);
-				}
-			}
-		} while (rc == OPAL_PARTIAL); /* More to flush */
-
-	} else {
-		__be64 evt;
-
-		WARN_ONCE(1, "opal: OPAL_CONSOLE_FLUSH missing.\n");
-		/*
-		 * If OPAL_CONSOLE_FLUSH is not implemented in the firmware,
-		 * the console can still be flushed by calling the polling
-		 * function while it has OPAL_EVENT_CONSOLE_OUTPUT events.
-		 */
-		do {
-			opal_poll_events(&evt);
-		} while (be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT);
-	}
+	opal_flush_console(0);
 }
 
 static struct kmsg_dumper opal_kmsg_dumper = {
-	.dump = force_opal_console_flush
+	.dump = kmsg_dump_opal_console_flush
 };
 
 void __init opal_kmsg_init(void)

64 lines not on this page · raw message

index 6640fccbf30c..0ddb63226695 100644
@@ -346,10 +346,10 @@ int opal_get_chars(uint32_t vtermno, char *buf, int count)
 
 int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 {
-	int written = 0;
-	__be64 olen;
-	s64 len, rc;
 	unsigned long flags;
+	int written;
+	__be64 olen;
+	s64 rc;
 
 	if (!opal.entry)
 		return -ENODEV;

@@ -357,62 +357,56 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 	/* We want put_chars to be atomic to avoid mangling of hvsi
 	 * packets. To do that, we first test for room and return
 	 * -EAGAIN if there isn't enough.
-	 *
-	 * Unfortunately, opal_console_write_buffer_space() doesn't
-	 * appear to work on opal v1, so we just assume there is
-	 * enough room and be done with it
 	 */
 	spin_lock_irqsave(&opal_write_lock, flags);
 	rc = opal_console_write_buffer_space(vtermno, &olen);
-	len = be64_to_cpu(olen);
-	if (rc || len < total_len) {
-		spin_unlock_irqrestore(&opal_write_lock, flags);
+	if (rc || be64_to_cpu(olen) < total_len) {
 		/* Closed -> drop characters */
 		if (rc)
-			return total_len;
-		opal_flush_console(vtermno);
-		return -EAGAIN;
+			written = total_len;
+		else
+			written = -EAGAIN;
+		goto out;
 	}
 
-	/* We still try to handle partial completions, though they
-	 * should no longer happen.
-	 */
-
-	while (total_len > 0) {
-		olen = cpu_to_be64(total_len);
-
-		rc = OPAL_BUSY;
-		while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-			rc = opal_console_write(vtermno, &olen, data);
-			if (rc == OPAL_BUSY_EVENT) {
-				mdelay(OPAL_BUSY_DELAY_MS);
-				opal_poll_events(NULL);
-			} else if (rc == OPAL_BUSY) {
-				mdelay(OPAL_BUSY_DELAY_MS);
-			}
-		}
-
-		len = be64_to_cpu(olen);
-
-		/* Closed or other error drop */
-		if (rc != OPAL_SUCCESS) {
-			written += total_len; /* drop remaining chars */
-			break;
+	/* Should not get a partial write here because space is available. */
+	olen = cpu_to_be64(total_len);
+	rc = opal_console_write(vtermno, &olen, data);
+	if (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		if (rc == OPAL_BUSY_EVENT) {
+			mdelay(OPAL_BUSY_DELAY_MS);
+			opal_poll_events(NULL);
+		} else if (rc == OPAL_BUSY_EVENT) {
+			mdelay(OPAL_BUSY_DELAY_MS);
 		}
+		written = -EAGAIN;
+		goto out;
+	}
 
-		total_len -= len;
-		data += len;
-		written += len;
+	/* Closed or other error drop */
+	if (rc != OPAL_SUCCESS) {
+		written = opal_error_code(rc);
+		goto out;
+	}
 
-		/* This is a bit nasty but we need that for the console to
-		 * flush when there aren't any interrupts. We will clean
-		 * things a bit later to limit that to synchronous path
-		 * such as the kernel console and xmon/udbg
-		 */
-		opal_flush_console(vtermno);
+	written = be64_to_cpu(olen);
+	if (written < total_len) {
+		/* Should not happen */
+		pr_warn("atomic console write returned partial len=%d written=%d\n", total_len, written);
+		if (!written)
+			written = -EAGAIN;
 	}
+
+out:
 	spin_unlock_irqrestore(&opal_write_lock, flags);
 
+	/* This is a bit nasty but we need that for the console to
+	 * flush when there aren't any interrupts. We will clean
+	 * things a bit later to limit that to synchronous path
+	 * such as the kernel console and xmon/udbg
+	 */
+	opal_flush_console(vtermno);
+
 	return written;
 }
 

index 0ddb63226695..55d4b1983110 100644
@@ -400,12 +400,14 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 out:
 	spin_unlock_irqrestore(&opal_write_lock, flags);
 
-	/* This is a bit nasty but we need that for the console to
-	 * flush when there aren't any interrupts. We will clean
-	 * things a bit later to limit that to synchronous path
-	 * such as the kernel console and xmon/udbg
+	/* In the -EAGAIN case, callers loop, so we have to flush the console
+	 * here in case they have interrupts off (and we don't want to wait
+	 * for async flushing if we can make immediate progress here). If
+	 * necessary the API could be made entirely non-flushing if the
+	 * callers had a ->flush API to use.
 	 */
-	opal_flush_console(vtermno);
+	if (written == -EAGAIN)
+		opal_flush_console(vtermno);
 
 	return written;
 }

index 2ed07ca6389e..af122ad7f06d 100644
@@ -275,6 +275,11 @@ static void udbg_opal_putc(char c)
 			count = hvc_opal_hvsi_put_chars(termno, &c, 1);
 			break;
 		}
+
+		/* This is needed for the cosole to flush
+		 * when there aren't any interrupts.
+		 */
+		opal_flush_console(termno);
 	} while(count == 0 || count == -EAGAIN);
 }
 

index bbff49fab0e5..5d7072411561 100644
@@ -303,6 +303,7 @@ extern void opal_configure_cores(void);
 
 extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
 extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
+extern int opal_put_chars_atomic(uint32_t vtermno, const char *buf, int total_len);
 extern int opal_flush_console(uint32_t vtermno);
 
 extern void hvc_opal_init_early(void);

index 55d4b1983110..bcdb90ada938 100644
@@ -344,9 +344,9 @@ int opal_get_chars(uint32_t vtermno, char *buf, int count)
 	return 0;
 }
 
-int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
+static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, bool atomic)
 {
-	unsigned long flags;
+	unsigned long flags = 0 /* shut up gcc */;
 	int written;
 	__be64 olen;
 	s64 rc;

@@ -354,11 +354,8 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 	if (!opal.entry)
 		return -ENODEV;
 
-	/* We want put_chars to be atomic to avoid mangling of hvsi
-	 * packets. To do that, we first test for room and return
-	 * -EAGAIN if there isn't enough.
-	 */
-	spin_lock_irqsave(&opal_write_lock, flags);
+	if (atomic)
+		spin_lock_irqsave(&opal_write_lock, flags);
 	rc = opal_console_write_buffer_space(vtermno, &olen);
 	if (rc || be64_to_cpu(olen) < total_len) {
 		/* Closed -> drop characters */

@@ -391,14 +388,18 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 
 	written = be64_to_cpu(olen);
 	if (written < total_len) {
-		/* Should not happen */
-		pr_warn("atomic console write returned partial len=%d written=%d\n", total_len, written);
+		if (atomic) {
+			/* Should not happen */
+			pr_warn("atomic console write returned partial "
+				"len=%d written=%d\n", total_len, written);
+		}
 		if (!written)
 			written = -EAGAIN;
 	}
 
 out:
-	spin_unlock_irqrestore(&opal_write_lock, flags);
+	if (atomic)
+		spin_unlock_irqrestore(&opal_write_lock, flags);
 
 	/* In the -EAGAIN case, callers loop, so we have to flush the console
 	 * here in case they have interrupts off (and we don't want to wait

@@ -412,6 +413,22 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 	return written;
 }
 
+int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
+{
+	return __opal_put_chars(vtermno, data, total_len, false);
+}
+
+/*
+ * opal_put_chars_atomic will not perform partial-writes. Data will be
+ * atomically written to the terminal or not at all. This is not strictly
+ * true at the moment because console space can race with OPAL's console
+ * writes.
+ */
+int opal_put_chars_atomic(uint32_t vtermno, const char *data, int total_len)
+{
+	return __opal_put_chars(vtermno, data, total_len, true);
+}
+
 int opal_flush_console(uint32_t vtermno)
 {
 	s64 rc;

index af122ad7f06d..0a72f98ee082 100644
@@ -183,9 +183,15 @@ static int hvc_opal_probe(struct platform_device *dev)
 			return -ENOMEM;
 		pv->proto = proto;
 		hvc_opal_privs[termno] = pv;
-		if (proto == HV_PROTOCOL_HVSI)
-			hvsilib_init(&pv->hvsi, opal_get_chars, opal_put_chars,
+		if (proto == HV_PROTOCOL_HVSI) {
+			/*
+			 * We want put_chars to be atomic to avoid mangling of
+			 * hvsi packets.
+			 */
+			hvsilib_init(&pv->hvsi,
+				     opal_get_chars, opal_put_chars_atomic,
 				     termno, 0);
+		}
 
 		/* Instanciate now to establish a mapping index==vtermno */
 		hvc_instantiate(termno, termno, ops);

@@ -376,8 +382,9 @@ void __init hvc_opal_init_early(void)
 	else if (of_device_is_compatible(stdout_node,"ibm,opal-console-hvsi")) {
 		hvc_opal_boot_priv.proto = HV_PROTOCOL_HVSI;
 		ops = &hvc_opal_hvsi_ops;
-		hvsilib_init(&hvc_opal_boot_priv.hvsi, opal_get_chars,
-			     opal_put_chars, index, 1);
+		hvsilib_init(&hvc_opal_boot_priv.hvsi,
+			     opal_get_chars, opal_put_chars_atomic,
+			     index, 1);
 		/* HVSI, perform the handshake now */
 		hvsilib_establish(&hvc_opal_boot_priv.hvsi);
 		pr_devel("hvc_opal: Found HVSI console\n");

@@ -409,7 +416,8 @@ void __init udbg_init_debug_opal_hvsi(void)
 	hvc_opal_privs[index] = &hvc_opal_boot_priv;
 	hvc_opal_boot_termno = index;
 	udbg_init_opal_common();
-	hvsilib_init(&hvc_opal_boot_priv.hvsi, opal_get_chars, opal_put_chars,
+	hvsilib_init(&hvc_opal_boot_priv.hvsi,
+		     opal_get_chars, opal_put_chars_atomic,
 		     index, 1);
 	hvsilib_establish(&hvc_opal_boot_priv.hvsi);
 }

index 0a72f98ee082..786e76a1e06d 100644
@@ -313,14 +313,8 @@ static int udbg_opal_getc(void)
 	int ch;
 	for (;;) {
 		ch = udbg_opal_getc_poll();
-		if (ch == -1) {
-			/* This shouldn't be needed...but... */
-			volatile unsigned long delay;
-			for (delay=0; delay < 2000000; delay++)
-				;
-		} else {
+		if (ch != -1)
 			return ch;
-		}
 	}
 }
 

index 7709fcc707f4..fddb63322c67 100644
@@ -73,7 +73,7 @@ static LIST_HEAD(hvc_structs);
  * Protect the list of hvc_struct instances from inserts and removals during
  * list traversal.
  */
-static DEFINE_SPINLOCK(hvc_structs_lock);
+static DEFINE_MUTEX(hvc_structs_mutex);
 
 /*
  * This value is used to assign a tty->index value to a hvc_struct based

@@ -83,7 +83,7 @@ static DEFINE_SPINLOCK(hvc_structs_lock);
 static int last_hvc = -1;
 
 /*
- * Do not call this function with either the hvc_structs_lock or the hvc_struct
+ * Do not call this function with either the hvc_structs_mutex or the hvc_struct
  * lock held.  If successful, this function increments the kref reference
  * count against the target hvc_struct so it should be released when finished.
  */

@@ -92,25 +92,24 @@ static struct hvc_struct *hvc_get_by_index(int index)
 	struct hvc_struct *hp;
 	unsigned long flags;
 
-	spin_lock(&hvc_structs_lock);
+	mutex_lock(&hvc_structs_mutex);
 
 	list_for_each_entry(hp, &hvc_structs, next) {
 		spin_lock_irqsave(&hp->lock, flags);
 		if (hp->index == index) {
 			tty_port_get(&hp->port);
 			spin_unlock_irqrestore(&hp->lock, flags);
-			spin_unlock(&hvc_structs_lock);
+			mutex_unlock(&hvc_structs_mutex);
 			return hp;
 		}
 		spin_unlock_irqrestore(&hp->lock, flags);
 	}
 	hp = NULL;
+	mutex_unlock(&hvc_structs_mutex);
 
-	spin_unlock(&hvc_structs_lock);
 	return hp;
 }
 
-
 /*
  * Initial console vtermnos for console API usage prior to full console
  * initialization.  Any vty adapter outside this range will not have usable

@@ -224,13 +223,13 @@ static void hvc_port_destruct(struct tty_port *port)
 	struct hvc_struct *hp = container_of(port, struct hvc_struct, port);
 	unsigned long flags;
 
-	spin_lock(&hvc_structs_lock);
+	mutex_lock(&hvc_structs_mutex);
 
 	spin_lock_irqsave(&hp->lock, flags);
 	list_del(&(hp->next));
 	spin_unlock_irqrestore(&hp->lock, flags);
 
-	spin_unlock(&hvc_structs_lock);
+	mutex_unlock(&hvc_structs_mutex);
 
 	kfree(hp);
 }

@@ -733,11 +732,11 @@ static int khvcd(void *unused)
 		try_to_freeze();
 		wmb();
 		if (!cpus_are_in_xmon()) {
-			spin_lock(&hvc_structs_lock);
+			mutex_lock(&hvc_structs_mutex);
 			list_for_each_entry(hp, &hvc_structs, next) {
 				poll_mask |= hvc_poll(hp);
 			}
-			spin_unlock(&hvc_structs_lock);
+			mutex_unlock(&hvc_structs_mutex);
 		} else
 			poll_mask |= HVC_POLL_READ;
 		if (hvc_kicked)

@@ -871,7 +870,7 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 
 	INIT_WORK(&hp->tty_resize, hvc_set_winsz);
 	spin_lock_init(&hp->lock);
-	spin_lock(&hvc_structs_lock);
+	mutex_lock(&hvc_structs_mutex);
 
 	/*
 	 * find index to use:

@@ -891,7 +890,7 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 	vtermnos[i] = vtermno;
 
 	list_add_tail(&(hp->next), &hvc_structs);
-	spin_unlock(&hvc_structs_lock);
+	mutex_unlock(&hvc_structs_mutex);
 
 	/* check if we need to re-register the kernel console */
 	hvc_check_console(i);

index fddb63322c67..745ac220fce8 100644
@@ -592,7 +592,7 @@ static u32 timeout = MIN_TIMEOUT;
 int hvc_poll(struct hvc_struct *hp)
 {
 	struct tty_struct *tty;
-	int i, n, poll_mask = 0;
+	int i, n, count, poll_mask = 0;
 	char buf[N_INBUF] __ALIGNED__;
 	unsigned long flags;
 	int read_total = 0;

@@ -618,7 +618,7 @@ int hvc_poll(struct hvc_struct *hp)
 
 	/* Now check if we can get data (are we throttled ?) */
 	if (tty_throttled(tty))
-		goto throttled;
+		goto out;
 
 	/* If we aren't notifier driven and aren't throttled, we always
 	 * request a reschedule

@@ -627,56 +627,58 @@ int hvc_poll(struct hvc_struct *hp)
 		poll_mask |= HVC_POLL_READ;
 
 	/* Read data if any */
-	for (;;) {
-		int count = tty_buffer_request_room(&hp->port, N_INBUF);
 
-		/* If flip is full, just reschedule a later read */
-		if (count == 0) {
+	count = tty_buffer_request_room(&hp->port, N_INBUF);
+
+	/* If flip is full, just reschedule a later read */
+	if (count == 0) {
+		poll_mask |= HVC_POLL_READ;
+		goto out;
+	}
+
+	n = hp->ops->get_chars(hp->vtermno, buf, count);
+	if (n <= 0) {
+		/* Hangup the tty when disconnected from host */
+		if (n == -EPIPE) {
+			spin_unlock_irqrestore(&hp->lock, flags);
+			tty_hangup(tty);
+			spin_lock_irqsave(&hp->lock, flags);
+		} else if ( n == -EAGAIN ) {
+			/*
+			 * Some back-ends can only ensure a certain min
+			 * num of bytes read, which may be > 'count'.
+			 * Let the tty clear the flip buff to make room.
+			 */
 			poll_mask |= HVC_POLL_READ;
-			break;
 		}
+		goto out;
+	}
 
-		n = hp->ops->get_chars(hp->vtermno, buf, count);
-		if (n <= 0) {
-			/* Hangup the tty when disconnected from host */
-			if (n == -EPIPE) {
-				spin_unlock_irqrestore(&hp->lock, flags);
-				tty_hangup(tty);
-				spin_lock_irqsave(&hp->lock, flags);
-			} else if ( n == -EAGAIN ) {
-				/*
-				 * Some back-ends can only ensure a certain min
-				 * num of bytes read, which may be > 'count'.
-				 * Let the tty clear the flip buff to make room.
-				 */
-				poll_mask |= HVC_POLL_READ;
-			}
-			break;
-		}
-		for (i = 0; i < n; ++i) {
+	for (i = 0; i < n; ++i) {
 #ifdef CONFIG_MAGIC_SYSRQ
-			if (hp->index == hvc_console.index) {
-				/* Handle the SysRq Hack */
-				/* XXX should support a sequence */
-				if (buf[i] == '\x0f') {	/* ^O */
-					/* if ^O is pressed again, reset
-					 * sysrq_pressed and flip ^O char */
-					sysrq_pressed = !sysrq_pressed;
-					if (sysrq_pressed)
-						continue;
-				} else if (sysrq_pressed) {
-					handle_sysrq(buf[i]);
-					sysrq_pressed = 0;
+		if (hp->index == hvc_console.index) {
+			/* Handle the SysRq Hack */
+			/* XXX should support a sequence */
+			if (buf[i] == '\x0f') {	/* ^O */
+				/* if ^O is pressed again, reset
+				 * sysrq_pressed and flip ^O char */
+				sysrq_pressed = !sysrq_pressed;
+				if (sysrq_pressed)
 					continue;
-				}
+			} else if (sysrq_pressed) {
+				handle_sysrq(buf[i]);
+				sysrq_pressed = 0;
+				continue;
 			}
-#endif /* CONFIG_MAGIC_SYSRQ */
-			tty_insert_flip_char(&hp->port, buf[i], 0);
 		}
-
-		read_total += n;
+#endif /* CONFIG_MAGIC_SYSRQ */
+		tty_insert_flip_char(&hp->port, buf[i], 0);
 	}
- throttled:
+	if (n == count)
+		poll_mask |= HVC_POLL_READ;
+	read_total = n;
+
+ out:
 	/* Wakeup write queue if necessary */
 	if (hp->do_wakeup) {
 		hp->do_wakeup = 0;

index 745ac220fce8..2abfc0b15fbb 100644
@@ -589,7 +589,7 @@ static u32 timeout = MIN_TIMEOUT;
 #define HVC_POLL_READ	0x00000001
 #define HVC_POLL_WRITE	0x00000002
 
-int hvc_poll(struct hvc_struct *hp)
+static int __hvc_poll(struct hvc_struct *hp, bool may_sleep)
 {
 	struct tty_struct *tty;
 	int i, n, count, poll_mask = 0;

@@ -611,6 +611,12 @@ int hvc_poll(struct hvc_struct *hp)
 		timeout = (written_total) ? 0 : MIN_TIMEOUT;
 	}
 
+	if (may_sleep) {
+		spin_unlock_irqrestore(&hp->lock, flags);
+		cond_resched();
+		spin_lock_irqsave(&hp->lock, flags);
+	}
+
 	/* No tty attached, just skip */
 	tty = tty_port_tty_get(&hp->port);
 	if (tty == NULL)

@@ -698,6 +704,11 @@ int hvc_poll(struct hvc_struct *hp)
 
 	return poll_mask;
 }
+
+int hvc_poll(struct hvc_struct *hp)
+{
+	return __hvc_poll(hp, false);
+}
 EXPORT_SYMBOL_GPL(hvc_poll);
 
 /**

@@ -736,7 +747,8 @@ static int khvcd(void *unused)
 		if (!cpus_are_in_xmon()) {
 			mutex_lock(&hvc_structs_mutex);
 			list_for_each_entry(hp, &hvc_structs, next) {
-				poll_mask |= hvc_poll(hp);
+				poll_mask |= __hvc_poll(hp, true);
+				cond_resched();
 			}
 			mutex_unlock(&hvc_structs_mutex);
 		} else

index 2abfc0b15fbb..6131d5084c42 100644
@@ -493,23 +493,29 @@ static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count
 	if (hp->port.count <= 0)
 		return -EIO;
 
-	spin_lock_irqsave(&hp->lock, flags);
+	while (count > 0) {
+		spin_lock_irqsave(&hp->lock, flags);
 
-	/* Push pending writes */
-	if (hp->n_outbuf > 0)
-		hvc_push(hp);
-
-	while (count > 0 && (rsize = hp->outbuf_size - hp->n_outbuf) > 0) {
-		if (rsize > count)
-			rsize = count;
-		memcpy(hp->outbuf + hp->n_outbuf, buf, rsize);
-		count -= rsize;
-		buf += rsize;
-		hp->n_outbuf += rsize;
-		written += rsize;
-		hvc_push(hp);
+		rsize = hp->outbuf_size - hp->n_outbuf;
+
+		if (rsize) {
+			if (rsize > count)
+				rsize = count;
+			memcpy(hp->outbuf + hp->n_outbuf, buf, rsize);
+			count -= rsize;
+			buf += rsize;
+			hp->n_outbuf += rsize;
+			written += rsize;
+		}
+
+		if (hp->n_outbuf > 0)
+			hvc_push(hp);
+
+		spin_unlock_irqrestore(&hp->lock, flags);
+
+		if (count)
+			cond_resched();
 	}
-	spin_unlock_irqrestore(&hp->lock, flags);
 
 	/*
 	 * Racy, but harmless, kick thread if there is still pending data.

index 6131d5084c42..5414c4a87bea 100644
@@ -110,6 +110,29 @@ static struct hvc_struct *hvc_get_by_index(int index)
 	return hp;
 }
 
+static int __hvc_flush(const struct hv_ops *ops, uint32_t vtermno, bool wait)
+{
+	if (wait)
+		might_sleep();
+
+	if (ops->flush)
+		return ops->flush(vtermno, wait);
+	return 0;
+}
+
+static int hvc_console_flush(const struct hv_ops *ops, uint32_t vtermno)
+{
+	return __hvc_flush(ops, vtermno, false);
+}
+
+/*
+ * Wait for the console to flush before writing more to it. This sleeps.
+ */
+static int hvc_flush(struct hvc_struct *hp)
+{
+	return __hvc_flush(hp->ops, hp->vtermno, true);
+}
+
 /*
  * Initial console vtermnos for console API usage prior to full console
  * initialization.  Any vty adapter outside this range will not have usable

@@ -155,8 +178,12 @@ static void hvc_console_print(struct console *co, const char *b,
 			if (r <= 0) {
 				/* throw away characters on error
 				 * but spin in case of -EAGAIN */
-				if (r != -EAGAIN)
+				if (r != -EAGAIN) {
 					i = 0;
+				} else {
+					hvc_console_flush(cons_ops[index],
+						      vtermnos[index]);
+				}
 			} else if (r > 0) {
 				i -= r;
 				if (i > 0)

@@ -164,6 +191,7 @@ static void hvc_console_print(struct console *co, const char *b,
 			}
 		}
 	}
+	hvc_console_flush(cons_ops[index], vtermnos[index]);
 }
 
 static struct tty_driver *hvc_console_device(struct console *c, int *index)

@@ -513,8 +541,11 @@ static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count
 
 		spin_unlock_irqrestore(&hp->lock, flags);
 
-		if (count)
+		if (count) {
+			if (hp->n_outbuf > 0)
+				hvc_flush(hp);
 			cond_resched();
+		}
 	}
 
 	/*

index ea63090e013f..e9319954c832 100644
@@ -54,6 +54,7 @@ struct hvc_struct {
 struct hv_ops {
 	int (*get_chars)(uint32_t vtermno, char *buf, int count);
 	int (*put_chars)(uint32_t vtermno, const char *buf, int count);
+	int (*flush)(uint32_t vtermno, bool wait);
 
 	/* Callbacks for notification. Called in open, close and hangup */
 	int (*notifier_add)(struct hvc_struct *hp, int irq);

index 5d7072411561..a426d2caaf9f 100644
@@ -304,6 +304,7 @@ extern void opal_configure_cores(void);
 extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
 extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
 extern int opal_put_chars_atomic(uint32_t vtermno, const char *buf, int total_len);
+extern int opal_flush_chars(uint32_t vtermno, bool wait);
 extern int opal_flush_console(uint32_t vtermno);
 
 extern void hvc_opal_init_early(void);

119 lines not on this page · raw message

index 786e76a1e06d..fd306033f8d4 100644
@@ -52,6 +52,7 @@ static u32 hvc_opal_boot_termno;
 static const struct hv_ops hvc_opal_raw_ops = {
 	.get_chars = opal_get_chars,
 	.put_chars = opal_put_chars,
+	.flush = opal_flush_chars,
 	.notifier_add = notifier_add_irq,
 	.notifier_del = notifier_del_irq,
 	.notifier_hangup = notifier_hangup_irq,

@@ -141,6 +142,7 @@ static int hvc_opal_hvsi_tiocmset(struct hvc_struct *hp, unsigned int set,
 static const struct hv_ops hvc_opal_hvsi_ops = {
 	.get_chars = hvc_opal_hvsi_get_chars,
 	.put_chars = hvc_opal_hvsi_put_chars,
+	.flush = opal_flush_chars,
 	.notifier_add = hvc_opal_hvsi_open,
 	.notifier_del = hvc_opal_hvsi_close,
 	.notifier_hangup = hvc_opal_hvsi_hangup,

index fd2bbf4fd6dc..c610ef3541aa 100644
@@ -53,12 +53,12 @@ static void force_opal_console_flush(struct kmsg_dumper *dumper,
 	} else {
 		__be64 evt;
 
-		WARN_ONCE(1, "opal: OPAL_CONSOLE_FLUSH missing.\n");
 		/*
 		 * If OPAL_CONSOLE_FLUSH is not implemented in the firmware,
 		 * the console can still be flushed by calling the polling
 		 * function while it has OPAL_EVENT_CONSOLE_OUTPUT events.
 		 */
+		printk_once(KERN_NOTICE "opal: OPAL_CONSOLE_FLUSH missing.\n");
 		do {
 			opal_poll_events(&evt);
 		} while (be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT);