[patch 00/13] Cell kernel updates

[patch 00/13] Cell kernel updates

[Arnd Bergmann]

Sorry for having delayed these patches so long. This should
bring the mainline kernel up-to-date with the experimental
stuff that is hosted on bsc.es. It should apply on today's
git tree and with trivial modifications also works on 2.6.16,
for those that are interested.

Apart from a number of bug fixes, the important parts in here
are:

- the hvc console driver for rtas
- spufs support for doing syscalls from an spu
- host-initiated DMA though spufs
- option to map SPU control registers into user space

Paulus, please apply and forward as appropriate.

        Arnd <><

--

[patch 01/13] powerpc: hvc_console updates

[Arnd Bergmann]

These are some updates from both Ryan and Arnd for the hvc_console
driver:

The main point is to enable the inclusion of a console driver
for rtas, which is currrently needed for the cell platform.

Also shuffle around some data-type declarations and moves some
functions out of include/asm-ppc64/hvconsole.h and into a new
drivers/char/hvc_console.h file.

From: "Ryan S. Arnold" <rsa@us.ibm.com>
Signed-off-by: "Ryan S. Arnold" <rsa@us.ibm.com>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

Index: linux-2.6.16-rc/drivers/char/hvc_console.c
===================================================================
--- linux-2.6.16-rc.orig/drivers/char/hvc_console.c
+++ linux-2.6.16-rc/drivers/char/hvc_console.c
@@ -39,8 +39,10 @@
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/delay.h>
+
 #include <asm/uaccess.h>
-#include <asm/hvconsole.h>
+
+#include "hvc_console.h"
 
 #define HVC_MAJOR	229
 #define HVC_MINOR	0
@@ -54,17 +56,14 @@
 #define HVC_CLOSE_WAIT (HZ/100) /* 1/10 of a second */
 
 /*
- * The Linux TTY code does not support dynamic addition of tty derived devices
- * so we need to know how many tty devices we might need when space is allocated
- * for the tty device.  Since this driver supports hotplug of vty adapters we
- * need to make sure we have enough allocated.
+ * 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 HVC_ALLOC_TTY_ADAPTERS	8
-
 #define N_OUTBUF	16
 #define N_INBUF		16
 
-#define __ALIGNED__	__attribute__((__aligned__(8)))
+#define __ALIGNED__ __attribute__((__aligned__(sizeof(long))))
 
 static struct tty_driver *hvc_driver;
 static struct task_struct *hvc_task;
@@ -154,7 +153,7 @@ static uint32_t vtermnos[MAX_NR_HVC_CONS
 
 void hvc_console_print(struct console *co, const char *b, unsigned count)
 {
-	char c[16] __ALIGNED__;
+	char c[N_OUTBUF] __ALIGNED__;
 	unsigned i = 0, n = 0;
 	int r, donecr = 0, index = co->index;
 
@@ -473,8 +472,10 @@ static void hvc_push(struct hvc_struct *
 
 	n = hp->ops->put_chars(hp->vtermno, hp->outbuf, hp->n_outbuf);
 	if (n <= 0) {
-		if (n == 0)
+		if (n == 0) {
+			hp->do_wakeup = 1;
 			return;
+		}
 		/* throw away output on error; this happens when
 		   there is no session connected to the vterm. */
 		hp->n_outbuf = 0;
@@ -486,12 +487,19 @@ static void hvc_push(struct hvc_struct *
 		hp->do_wakeup = 1;
 }
 
-static inline int __hvc_write_kernel(struct hvc_struct *hp,
-				   const unsigned char *buf, int count)
+static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count)
 {
+	struct hvc_struct *hp = tty->driver_data;
 	unsigned long flags;
 	int rsize, written = 0;
 
+	/* This write was probably executed during a tty close. */
+	if (!hp)
+		return -EPIPE;
+
+	if (hp->count <= 0)
+		return -EIO;
+
 	spin_lock_irqsave(&hp->lock, flags);
 
 	/* Push pending writes */
@@ -510,26 +518,8 @@ static inline int __hvc_write_kernel(str
 	}
 	spin_unlock_irqrestore(&hp->lock, flags);
 
-	return written;
-}
-static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count)
-{
-	struct hvc_struct *hp = tty->driver_data;
-	int written;
-
-	/* This write was probably executed during a tty close. */
-	if (!hp)
-		return -EPIPE;
-
-	if (hp->count <= 0)
-		return -EIO;
-
-	written = __hvc_write_kernel(hp, buf, count);
-
 	/*
 	 * Racy, but harmless, kick thread if there is still pending data.
-	 * There really is nothing wrong with kicking the thread, even if there
-	 * is no buffered data.
 	 */
 	if (hp->n_outbuf)
 		hvc_kick();
@@ -614,6 +604,13 @@ static int hvc_poll(struct hvc_struct *h
 				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;
 		}
@@ -635,16 +632,7 @@ static int hvc_poll(struct hvc_struct *h
 			tty_insert_flip_char(tty, buf[i], 0);
 		}
 
-		/*
-		 * Account for the total amount read in one loop, and if above
-		 * 64 bytes, we do a quick schedule loop to let the tty grok
-		 * the data and eventually throttle us.
-		 */
 		read_total += n;
-		if (read_total >= 64) {
-			poll_mask |= HVC_POLL_QUICK;
-			break;
-		}
 	}
  throttled:
 	/* Wakeup write queue if necessary */
@@ -767,7 +755,8 @@ struct hvc_struct __devinit *hvc_alloc(u
 	 * see if this vterm id matches one registered for console.
 	 */
 	for (i=0; i < MAX_NR_HVC_CONSOLES; i++)
-		if (vtermnos[i] == hp->vtermno)
+		if (vtermnos[i] == hp->vtermno &&
+		    cons_ops[i] == hp->ops)
 			break;
 
 	/* no matching slot, just use a counter */
Index: linux-2.6.16-rc/drivers/char/hvc_console.h
===================================================================
--- /dev/null
+++ linux-2.6.16-rc/drivers/char/hvc_console.h
@@ -0,0 +1,63 @@
+/*
+ * hvc_console.h
+ * Copyright (C) 2005 IBM Corporation
+ *
+ * Author(s):
+ * 	Ryan S. Arnold <rsa@us.ibm.com>
+ *
+ * hvc_console header information:
+ *      moved here from include/asm-powerpc/hvconsole.h
+ *      and drivers/char/hvc_console.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#ifndef HVC_CONSOLE_H
+#define HVC_CONSOLE_H
+
+/*
+ * This is the max number of console adapters that can/will be found as
+ * console devices on first stage console init.  Any number beyond this range
+ * can't be used as a console device but is still a valid tty device.
+ */
+#define MAX_NR_HVC_CONSOLES	16
+
+/*
+ * The Linux TTY code does not support dynamic addition of tty derived devices
+ * so we need to know how many tty devices we might need when space is allocated
+ * for the tty device.  Since this driver supports hotplug of vty adapters we
+ * need to make sure we have enough allocated.
+ */
+#define HVC_ALLOC_TTY_ADAPTERS	8
+
+
+/* implemented by a low level driver */
+struct hv_ops {
+	int (*get_chars)(uint32_t vtermno, char *buf, int count);
+	int (*put_chars)(uint32_t vtermno, const char *buf, int count);
+};
+
+struct hvc_struct;
+
+/* Register a vterm and a slot index for use as a console (console_init) */
+extern int hvc_instantiate(uint32_t vtermno, int index, struct hv_ops *ops);
+
+/* register a vterm for hvc tty operation (module_init or hotplug add) */
+extern struct hvc_struct * __devinit hvc_alloc(uint32_t vtermno, int irq,
+						 struct hv_ops *ops);
+/* remove a vterm from hvc tty operation (modele_exit or hotplug remove) */
+extern int __devexit hvc_remove(struct hvc_struct *hp);
+
+#endif // HVC_CONSOLE_H
Index: linux-2.6.16-rc/include/asm-powerpc/hvconsole.h
===================================================================
--- linux-2.6.16-rc.orig/include/asm-powerpc/hvconsole.h
+++ linux-2.6.16-rc/include/asm-powerpc/hvconsole.h
@@ -24,17 +24,16 @@
 #ifdef __KERNEL__
 
 /*
- * This is the max number of console adapters that can/will be found as
- * console devices on first stage console init.  Any number beyond this range
- * can't be used as a console device but is still a valid tty device.
+ * PSeries firmware will only send/recv up to 16 bytes of character data per
+ * hcall.
  */
-#define MAX_NR_HVC_CONSOLES	16
+#define MAX_VIO_PUT_CHARS	16
+#define SIZE_VIO_GET_CHARS	16
 
-/* implemented by a low level driver */
-struct hv_ops {
-	int (*get_chars)(uint32_t vtermno, char *buf, int count);
-	int (*put_chars)(uint32_t vtermno, const char *buf, int count);
-};
+/*
+ * Vio firmware always attempts to fetch MAX_VIO_GET_CHARS chars.  The 'count'
+ * parm is included to conform to put_chars() function pointer template
+ */
 extern int hvc_get_chars(uint32_t vtermno, char *buf, int count);
 extern int hvc_put_chars(uint32_t vtermno, const char *buf, int count);
 
Index: linux-2.6.16-rc/drivers/char/Kconfig
===================================================================
--- linux-2.6.16-rc.orig/drivers/char/Kconfig
+++ linux-2.6.16-rc/drivers/char/Kconfig
@@ -560,9 +560,19 @@ config TIPAR
 
 	  If unsure, say N.
 
+config HVC_DRIVER
+	bool
+	help
+	  Users of pSeries machines that want to utilize the hvc console front-end
+	  module for their backend console driver should select this option.
+	  It will automatically be selected if one of the back-end console drivers
+	  is selected.
+
+
 config HVC_CONSOLE
 	bool "pSeries Hypervisor Virtual Console support"
 	depends on PPC_PSERIES
+	select HVC_DRIVER
 	help
 	  pSeries machines when partitioned support a hypervisor virtual
 	  console. This driver allows each pSeries partition to have a console
Index: linux-2.6.16-rc/drivers/char/Makefile
===================================================================
--- linux-2.6.16-rc.orig/drivers/char/Makefile
+++ linux-2.6.16-rc/drivers/char/Makefile
@@ -41,11 +41,12 @@ obj-$(CONFIG_N_HDLC)		+= n_hdlc.o
 obj-$(CONFIG_AMIGA_BUILTIN_SERIAL) += amiserial.o
 obj-$(CONFIG_SX)		+= sx.o generic_serial.o
 obj-$(CONFIG_RIO)		+= rio/ generic_serial.o
-obj-$(CONFIG_HVC_CONSOLE)	+= hvc_console.o hvc_vio.o hvsi.o
+obj-$(CONFIG_HVC_DRIVER)	+= hvc_console.o
+obj-$(CONFIG_HVC_CONSOLE)	+= hvc_vio.o hvsi.o
 obj-$(CONFIG_RAW_DRIVER)	+= raw.o
 obj-$(CONFIG_SGI_SNSC)		+= snsc.o snsc_event.o
 obj-$(CONFIG_MMTIMER)		+= mmtimer.o
-obj-$(CONFIG_VIOCONS) += viocons.o
+obj-$(CONFIG_VIOCONS)		+= viocons.o
 obj-$(CONFIG_VIOTAPE)		+= viotape.o
 obj-$(CONFIG_HVCS)		+= hvcs.o
 obj-$(CONFIG_SGI_MBCS)		+= mbcs.o
Index: linux-2.6.16-rc/drivers/char/hvc_vio.c
===================================================================
--- linux-2.6.16-rc.orig/drivers/char/hvc_vio.c
+++ linux-2.6.16-rc/drivers/char/hvc_vio.c
@@ -31,10 +31,13 @@
 
 #include <linux/types.h>
 #include <linux/init.h>
+
 #include <asm/hvconsole.h>
 #include <asm/vio.h>
 #include <asm/prom.h>
 
+#include "hvc_console.h"
+
 char hvc_driver_name[] = "hvc_console";
 
 static struct vio_device_id hvc_driver_table[] __devinitdata = {
@@ -48,6 +51,14 @@ static int filtered_get_chars(uint32_t v
 	unsigned long got;
 	int i;
 
+	/*
+	 * Vio firmware will read up to SIZE_VIO_GET_CHARS at its own discretion
+	 * so we play safe and avoid the situation where got > count which could
+	 * overload the flip buffer.
+	 */
+	if (count < SIZE_VIO_GET_CHARS)
+		return -EAGAIN;
+
 	got = hvc_get_chars(vtermno, buf, count);
 
 	/*
Index: linux-2.6.16-rc/arch/powerpc/platforms/pseries/hvconsole.c
===================================================================
--- linux-2.6.16-rc.orig/arch/powerpc/platforms/pseries/hvconsole.c
+++ linux-2.6.16-rc/arch/powerpc/platforms/pseries/hvconsole.c
@@ -62,6 +62,11 @@ int hvc_put_chars(uint32_t vtermno, cons
 	unsigned long *lbuf = (unsigned long *) buf;
 	long ret;
 
+
+	/* hcall will ret H_PARAMETER if 'count' exceeds firmware max.*/
+	if (count > MAX_VIO_PUT_CHARS)
+		count = MAX_VIO_PUT_CHARS;
+
 	ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count, lbuf[0],
 				 lbuf[1]);
 	if (ret == H_Success)

--

Re: [patch 01/13] powerpc: hvc_console updates

[Paul Mackerras]

Arnd Bergmann writes:

> Also shuffle around some data-type declarations and moves some
> functions out of include/asm-ppc64/hvconsole.h and into a new
> drivers/char/hvc_console.h file.

Unfortunately this causes compile failures because the declarations of
hvc_instantiate and hvc_alloc in include/asm-powerpc/hvconsole.h now
don't have the definition of struct hv_ops available to them.  I'll
ignore your 1/13 and 2/13 patches for now - please send fixed
versions.

Paul.

[updated patch 1/2] powerpc: hvc_console updates

[Arnd Bergmann]

These are some updates from both Ryan and Arnd for the hvc_console
driver:

The main point is to enable the inclusion of a console driver
for rtas, which is currrently needed for the cell platform.

Also shuffle around some data-type declarations and moves some
functions out of include/asm-ppc64/hvconsole.h and into a new
drivers/char/hvc_console.h file.

From: "Ryan S. Arnold" <rsa@us.ibm.com>
Signed-off-by: "Ryan S. Arnold" <rsa@us.ibm.com>
Signed-off-by: Arnd Bergmann <abergman@de.ibm.com>

Index: linus-2.6/drivers/char/hvc_console.c
===================================================================
--- linus-2.6.orig/drivers/char/hvc_console.c
+++ linus-2.6/drivers/char/hvc_console.c
@@ -39,8 +39,10 @@
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/delay.h>
+
 #include <asm/uaccess.h>
-#include <asm/hvconsole.h>
+
+#include "hvc_console.h"
 
 #define HVC_MAJOR	229
 #define HVC_MINOR	0
@@ -54,17 +56,14 @@
 #define HVC_CLOSE_WAIT (HZ/100) /* 1/10 of a second */
 
 /*
- * The Linux TTY code does not support dynamic addition of tty derived devices
- * so we need to know how many tty devices we might need when space is allocated
- * for the tty device.  Since this driver supports hotplug of vty adapters we
- * need to make sure we have enough allocated.
+ * 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 HVC_ALLOC_TTY_ADAPTERS	8
-
 #define N_OUTBUF	16
 #define N_INBUF		16
 
-#define __ALIGNED__	__attribute__((__aligned__(8)))
+#define __ALIGNED__ __attribute__((__aligned__(sizeof(long))))
 
 static struct tty_driver *hvc_driver;
 static struct task_struct *hvc_task;
@@ -154,7 +153,7 @@ static uint32_t vtermnos[MAX_NR_HVC_CONS
 
 void hvc_console_print(struct console *co, const char *b, unsigned count)
 {
-	char c[16] __ALIGNED__;
+	char c[N_OUTBUF] __ALIGNED__;
 	unsigned i = 0, n = 0;
 	int r, donecr = 0, index = co->index;
 
@@ -473,8 +472,10 @@ static void hvc_push(struct hvc_struct *
 
 	n = hp->ops->put_chars(hp->vtermno, hp->outbuf, hp->n_outbuf);
 	if (n <= 0) {
-		if (n == 0)
+		if (n == 0) {
+			hp->do_wakeup = 1;
 			return;
+		}
 		/* throw away output on error; this happens when
 		   there is no session connected to the vterm. */
 		hp->n_outbuf = 0;
@@ -486,12 +487,19 @@ static void hvc_push(struct hvc_struct *
 		hp->do_wakeup = 1;
 }
 
-static inline int __hvc_write_kernel(struct hvc_struct *hp,
-				   const unsigned char *buf, int count)
+static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count)
 {
+	struct hvc_struct *hp = tty->driver_data;
 	unsigned long flags;
 	int rsize, written = 0;
 
+	/* This write was probably executed during a tty close. */
+	if (!hp)
+		return -EPIPE;
+
+	if (hp->count <= 0)
+		return -EIO;
+
 	spin_lock_irqsave(&hp->lock, flags);
 
 	/* Push pending writes */
@@ -510,26 +518,8 @@ static inline int __hvc_write_kernel(str
 	}
 	spin_unlock_irqrestore(&hp->lock, flags);
 
-	return written;
-}
-static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count)
-{
-	struct hvc_struct *hp = tty->driver_data;
-	int written;
-
-	/* This write was probably executed during a tty close. */
-	if (!hp)
-		return -EPIPE;
-
-	if (hp->count <= 0)
-		return -EIO;
-
-	written = __hvc_write_kernel(hp, buf, count);
-
 	/*
 	 * Racy, but harmless, kick thread if there is still pending data.
-	 * There really is nothing wrong with kicking the thread, even if there
-	 * is no buffered data.
 	 */
 	if (hp->n_outbuf)
 		hvc_kick();
@@ -614,6 +604,13 @@ static int hvc_poll(struct hvc_struct *h
 				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;
 		}
@@ -635,16 +632,7 @@ static int hvc_poll(struct hvc_struct *h
 			tty_insert_flip_char(tty, buf[i], 0);
 		}
 
-		/*
-		 * Account for the total amount read in one loop, and if above
-		 * 64 bytes, we do a quick schedule loop to let the tty grok
-		 * the data and eventually throttle us.
-		 */
 		read_total += n;
-		if (read_total >= 64) {
-			poll_mask |= HVC_POLL_QUICK;
-			break;
-		}
 	}
  throttled:
 	/* Wakeup write queue if necessary */
@@ -767,7 +755,8 @@ struct hvc_struct __devinit *hvc_alloc(u
 	 * see if this vterm id matches one registered for console.
 	 */
 	for (i=0; i < MAX_NR_HVC_CONSOLES; i++)
-		if (vtermnos[i] == hp->vtermno)
+		if (vtermnos[i] == hp->vtermno &&
+		    cons_ops[i] == hp->ops)
 			break;
 
 	/* no matching slot, just use a counter */
Index: linus-2.6/drivers/char/hvc_console.h
===================================================================
--- /dev/null
+++ linus-2.6/drivers/char/hvc_console.h
@@ -0,0 +1,63 @@
+/*
+ * hvc_console.h
+ * Copyright (C) 2005 IBM Corporation
+ *
+ * Author(s):
+ * 	Ryan S. Arnold <rsa@us.ibm.com>
+ *
+ * hvc_console header information:
+ *      moved here from include/asm-powerpc/hvconsole.h
+ *      and drivers/char/hvc_console.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#ifndef HVC_CONSOLE_H
+#define HVC_CONSOLE_H
+
+/*
+ * This is the max number of console adapters that can/will be found as
+ * console devices on first stage console init.  Any number beyond this range
+ * can't be used as a console device but is still a valid tty device.
+ */
+#define MAX_NR_HVC_CONSOLES	16
+
+/*
+ * The Linux TTY code does not support dynamic addition of tty derived devices
+ * so we need to know how many tty devices we might need when space is allocated
+ * for the tty device.  Since this driver supports hotplug of vty adapters we
+ * need to make sure we have enough allocated.
+ */
+#define HVC_ALLOC_TTY_ADAPTERS	8
+
+
+/* implemented by a low level driver */
+struct hv_ops {
+	int (*get_chars)(uint32_t vtermno, char *buf, int count);
+	int (*put_chars)(uint32_t vtermno, const char *buf, int count);
+};
+
+struct hvc_struct;
+
+/* Register a vterm and a slot index for use as a console (console_init) */
+extern int hvc_instantiate(uint32_t vtermno, int index, struct hv_ops *ops);
+
+/* register a vterm for hvc tty operation (module_init or hotplug add) */
+extern struct hvc_struct * __devinit hvc_alloc(uint32_t vtermno, int irq,
+						 struct hv_ops *ops);
+/* remove a vterm from hvc tty operation (modele_exit or hotplug remove) */
+extern int __devexit hvc_remove(struct hvc_struct *hp);
+
+#endif // HVC_CONSOLE_H
Index: linus-2.6/include/asm-powerpc/hvconsole.h
===================================================================
--- linus-2.6.orig/include/asm-powerpc/hvconsole.h
+++ linus-2.6/include/asm-powerpc/hvconsole.h
@@ -24,28 +24,18 @@
 #ifdef __KERNEL__
 
 /*
- * This is the max number of console adapters that can/will be found as
- * console devices on first stage console init.  Any number beyond this range
- * can't be used as a console device but is still a valid tty device.
+ * PSeries firmware will only send/recv up to 16 bytes of character data per
+ * hcall.
  */
-#define MAX_NR_HVC_CONSOLES	16
+#define MAX_VIO_PUT_CHARS	16
+#define SIZE_VIO_GET_CHARS	16
 
-/* implemented by a low level driver */
-struct hv_ops {
-	int (*get_chars)(uint32_t vtermno, char *buf, int count);
-	int (*put_chars)(uint32_t vtermno, const char *buf, int count);
-};
+/*
+ * Vio firmware always attempts to fetch MAX_VIO_GET_CHARS chars.  The 'count'
+ * parm is included to conform to put_chars() function pointer template
+ */
 extern int hvc_get_chars(uint32_t vtermno, char *buf, int count);
 extern int hvc_put_chars(uint32_t vtermno, const char *buf, int count);
 
-struct hvc_struct;
-
-/* Register a vterm and a slot index for use as a console (console_init) */
-extern int hvc_instantiate(uint32_t vtermno, int index, struct hv_ops *ops);
-/* register a vterm for hvc tty operation (module_init or hotplug add) */
-extern struct hvc_struct * __devinit hvc_alloc(uint32_t vtermno, int irq,
-						 struct hv_ops *ops);
-/* remove a vterm from hvc tty operation (modele_exit or hotplug remove) */
-extern int __devexit hvc_remove(struct hvc_struct *hp);
 #endif /* __KERNEL__ */
 #endif /* _PPC64_HVCONSOLE_H */
Index: linus-2.6/drivers/char/Kconfig
===================================================================
--- linus-2.6.orig/drivers/char/Kconfig
+++ linus-2.6/drivers/char/Kconfig
@@ -561,9 +561,19 @@ config TIPAR
 
 	  If unsure, say N.
 
+config HVC_DRIVER
+	bool
+	help
+	  Users of pSeries machines that want to utilize the hvc console front-end
+	  module for their backend console driver should select this option.
+	  It will automatically be selected if one of the back-end console drivers
+	  is selected.
+
+
 config HVC_CONSOLE
 	bool "pSeries Hypervisor Virtual Console support"
 	depends on PPC_PSERIES
+	select HVC_DRIVER
 	help
 	  pSeries machines when partitioned support a hypervisor virtual
 	  console. This driver allows each pSeries partition to have a console
Index: linus-2.6/drivers/char/Makefile
===================================================================
--- linus-2.6.orig/drivers/char/Makefile
+++ linus-2.6/drivers/char/Makefile
@@ -41,7 +41,8 @@ obj-$(CONFIG_N_HDLC)		+= n_hdlc.o
 obj-$(CONFIG_AMIGA_BUILTIN_SERIAL) += amiserial.o
 obj-$(CONFIG_SX)		+= sx.o generic_serial.o
 obj-$(CONFIG_RIO)		+= rio/ generic_serial.o
-obj-$(CONFIG_HVC_CONSOLE)	+= hvc_console.o hvc_vio.o hvsi.o
+obj-$(CONFIG_HVC_DRIVER)	+= hvc_console.o
+obj-$(CONFIG_HVC_CONSOLE)	+= hvc_vio.o hvsi.o
 obj-$(CONFIG_RAW_DRIVER)	+= raw.o
 obj-$(CONFIG_SGI_SNSC)		+= snsc.o snsc_event.o
 obj-$(CONFIG_MMTIMER)		+= mmtimer.o
Index: linus-2.6/drivers/char/hvc_vio.c
===================================================================
--- linus-2.6.orig/drivers/char/hvc_vio.c
+++ linus-2.6/drivers/char/hvc_vio.c
@@ -31,10 +31,13 @@
 
 #include <linux/types.h>
 #include <linux/init.h>
+
 #include <asm/hvconsole.h>
 #include <asm/vio.h>
 #include <asm/prom.h>
 
+#include "hvc_console.h"
+
 char hvc_driver_name[] = "hvc_console";
 
 static struct vio_device_id hvc_driver_table[] __devinitdata = {
@@ -48,6 +51,14 @@ static int filtered_get_chars(uint32_t v
 	unsigned long got;
 	int i;
 
+	/*
+	 * Vio firmware will read up to SIZE_VIO_GET_CHARS at its own discretion
+	 * so we play safe and avoid the situation where got > count which could
+	 * overload the flip buffer.
+	 */
+	if (count < SIZE_VIO_GET_CHARS)
+		return -EAGAIN;
+
 	got = hvc_get_chars(vtermno, buf, count);
 
 	/*
Index: linus-2.6/arch/powerpc/platforms/pseries/hvconsole.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/pseries/hvconsole.c
+++ linus-2.6/arch/powerpc/platforms/pseries/hvconsole.c
@@ -62,6 +62,11 @@ int hvc_put_chars(uint32_t vtermno, cons
 	unsigned long *lbuf = (unsigned long *) buf;
 	long ret;
 
+
+	/* hcall will ret H_PARAMETER if 'count' exceeds firmware max.*/
+	if (count > MAX_VIO_PUT_CHARS)
+		count = MAX_VIO_PUT_CHARS;
+
 	ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count, lbuf[0],
 				 lbuf[1]);
 	if (ret == H_Success)

Re: [updated patch 1/2] powerpc: hvc_console updates

[Paul Mackerras]

Arnd Bergmann writes:

> These are some updates from both Ryan and Arnd for the hvc_console
> driver:

...

> From: "Ryan S. Arnold" <rsa@us.ibm.com>
> Signed-off-by: "Ryan S. Arnold" <rsa@us.ibm.com>
> Signed-off-by: Arnd Bergmann <abergman@de.ibm.com>

Arnd, please put the From: line as the first non-blank line in the
email body.  That way the git tools will handle it automatically and I
won't have to edit things by hand.

Thanks,
Paul.

[updated patch 2/2] powerpc: add hvc backend for rtas

[Arnd Bergmann]

Current Cell hardware is using the console through a set
of rtas calls. This driver is needed to get console
output on those boards.

Signed-off-by: Arnd Bergmann <abergman@de.ibm.com>

Index: linus-2.6/drivers/char/hvc_rtas.c
===================================================================
--- /dev/null
+++ linus-2.6/drivers/char/hvc_rtas.c
@@ -0,0 +1,138 @@
+/*
+ * IBM RTAS driver interface to hvc_console.c
+ *
+ * (C) Copyright IBM Corporation 2001-2005
+ * (C) Copyright Red Hat, Inc. 2005
+ *
+ * Author(s): Maximino Augilar <IBM STI Design Center>
+ *	    : Ryan S. Arnold <rsa@us.ibm.com>
+ *	    : Utz Bacher <utz.bacher@de.ibm.com>
+ *	    : David Woodhouse <dwmw2@infradead.org>
+ *
+ *    inspired by drivers/char/hvc_console.c
+ *    written by Anton Blanchard and Paul Mackerras
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/moduleparam.h>
+#include <linux/types.h>
+
+#include <asm/irq.h>
+#include <asm/rtas.h>
+#include "hvc_console.h"
+
+#define hvc_rtas_cookie 0x67781e15
+struct hvc_struct *hvc_rtas_dev;
+
+#define RTASCONS_PUT_ATTEMPTS  16
+
+static int rtascons_put_char_token = RTAS_UNKNOWN_SERVICE;
+static int rtascons_get_char_token = RTAS_UNKNOWN_SERVICE;
+static int rtascons_put_delay = 100;
+module_param_named(put_delay, rtascons_put_delay, int, 0644);
+
+static inline int hvc_rtas_write_console(uint32_t vtermno, const char *buf, int count)
+{
+	int done;
+
+	/* if there is more than one character to be displayed, wait a bit */
+	for (done = 0; done < count; done++) {
+		int result;
+		result = rtas_call(rtascons_put_char_token, 1, 1, NULL, buf[done]);
+		if (result)
+			break;
+	}
+	/* the calling routine expects to receive the number of bytes sent */
+	return done;
+}
+
+static int hvc_rtas_read_console(uint32_t vtermno, char *buf, int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		int c, err;
+
+		err = rtas_call(rtascons_get_char_token, 0, 2, &c);
+		if (err)
+			break;
+
+		buf[i] = c;
+	}
+
+	return i;
+}
+
+static struct hv_ops hvc_rtas_get_put_ops = {
+	.get_chars = hvc_rtas_read_console,
+	.put_chars = hvc_rtas_write_console,
+};
+
+static int hvc_rtas_init(void)
+{
+	struct hvc_struct *hp;
+
+	if (rtascons_put_char_token == RTAS_UNKNOWN_SERVICE)
+		rtascons_put_char_token = rtas_token("put-term-char");
+	if (rtascons_put_char_token == RTAS_UNKNOWN_SERVICE)
+		return -EIO;
+
+	if (rtascons_get_char_token == RTAS_UNKNOWN_SERVICE)
+		rtascons_get_char_token = rtas_token("get-term-char");
+	if (rtascons_get_char_token == RTAS_UNKNOWN_SERVICE)
+		return -EIO;
+
+	BUG_ON(hvc_rtas_dev);
+
+	/* Allocate an hvc_struct for the console device we instantiated
+	 * earlier.  Save off hp so that we can return it on exit */
+	hp = hvc_alloc(hvc_rtas_cookie, NO_IRQ, &hvc_rtas_get_put_ops);
+	if (IS_ERR(hp))
+		return PTR_ERR(hp);
+	hvc_rtas_dev = hp;
+	return 0;
+}
+module_init(hvc_rtas_init);
+
+/* This will tear down the tty portion of the driver */
+static void __exit hvc_rtas_exit(void)
+{
+	/* Really the fun isn't over until the worker thread breaks down and the
+	 * tty cleans up */
+	if (hvc_rtas_dev)
+		hvc_remove(hvc_rtas_dev);
+}
+module_exit(hvc_rtas_exit);
+
+/* This will happen prior to module init.  There is no tty at this time? */
+static int hvc_rtas_console_init(void)
+{
+	rtascons_put_char_token = rtas_token("put-term-char");
+	if (rtascons_put_char_token == RTAS_UNKNOWN_SERVICE)
+		return -EIO;
+	rtascons_get_char_token = rtas_token("get-term-char");
+	if (rtascons_get_char_token == RTAS_UNKNOWN_SERVICE)
+		return -EIO;
+
+	hvc_instantiate(hvc_rtas_cookie, 0, &hvc_rtas_get_put_ops );
+	add_preferred_console("hvc", 0, NULL);
+	return 0;
+}
+console_initcall(hvc_rtas_console_init);
Index: linus-2.6/drivers/char/Makefile
===================================================================
--- linus-2.6.orig/drivers/char/Makefile
+++ linus-2.6/drivers/char/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_SX)		+= sx.o generic_serial
 obj-$(CONFIG_RIO)		+= rio/ generic_serial.o
 obj-$(CONFIG_HVC_DRIVER)	+= hvc_console.o
 obj-$(CONFIG_HVC_CONSOLE)	+= hvc_vio.o hvsi.o
+obj-$(CONFIG_HVC_RTAS)		+= hvc_rtas.o
 obj-$(CONFIG_RAW_DRIVER)	+= raw.o
 obj-$(CONFIG_SGI_SNSC)		+= snsc.o snsc_event.o
 obj-$(CONFIG_MMTIMER)		+= mmtimer.o
Index: linus-2.6/drivers/char/Kconfig
===================================================================
--- linus-2.6.orig/drivers/char/Kconfig
+++ linus-2.6/drivers/char/Kconfig
@@ -579,6 +579,13 @@ config HVC_CONSOLE
 	  console. This driver allows each pSeries partition to have a console
 	  which is accessed via the HMC.
 
+config HVC_RTAS
+	bool "IBM RTAS Console support"
+	depends on PPC_RTAS
+	select HVC_DRIVER
+	help
+	  IBM Console device driver which makes use of RTAS
+
 config HVCS
 	tristate "IBM Hypervisor Virtual Console Server support"
 	depends on PPC_PSERIES

[patch 02/13] powerpc: add hvc backend for rtas

[Arnd Bergmann]

Current Cell hardware is using the console through a set
of rtas calls. This driver is needed to get console
output on those boards.

Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

Index: linus-2.6/drivers/char/hvc_rtas.c
===================================================================
--- /dev/null
+++ linus-2.6/drivers/char/hvc_rtas.c
@@ -0,0 +1,138 @@
+/*
+ * IBM RTAS driver interface to hvc_console.c
+ *
+ * (C) Copyright IBM Corporation 2001-2005
+ * (C) Copyright Red Hat, Inc. 2005
+ *
+ * Author(s): Maximino Augilar <IBM STI Design Center>
+ *	    : Ryan S. Arnold <rsa@us.ibm.com>
+ *	    : Utz Bacher <utz.bacher@de.ibm.com>
+ *	    : David Woodhouse <dwmw2@infradead.org>
+ *
+ *    inspired by drivers/char/hvc_console.c
+ *    written by Anton Blanchard and Paul Mackerras
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/moduleparam.h>
+#include <linux/types.h>
+
+#include <asm/irq.h>
+#include <asm/rtas.h>
+#include "hvc_console.h"
+
+#define hvc_rtas_cookie 0x67781e15
+struct hvc_struct *hvc_rtas_dev;
+
+#define RTASCONS_PUT_ATTEMPTS  16
+
+static int rtascons_put_char_token = RTAS_UNKNOWN_SERVICE;
+static int rtascons_get_char_token = RTAS_UNKNOWN_SERVICE;
+static int rtascons_put_delay = 100;
+module_param_named(put_delay, rtascons_put_delay, int, 0644);
+
+static inline int hvc_rtas_write_console(uint32_t vtermno, const char *buf, int count)
+{
+	int done;
+
+	/* if there is more than one character to be displayed, wait a bit */
+	for (done = 0; done < count; done++) {
+		int result;
+		result = rtas_call(rtascons_put_char_token, 1, 1, NULL, buf[done]);
+		if (result)
+			break;
+	}
+	/* the calling routine expects to receive the number of bytes sent */
+	return done;
+}
+
+static int hvc_rtas_read_console(uint32_t vtermno, char *buf, int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		int c, err;
+
+		err = rtas_call(rtascons_get_char_token, 0, 2, &c);
+		if (err)
+			break;
+
+		buf[i] = c;
+	}
+
+	return i;
+}
+
+static struct hv_ops hvc_rtas_get_put_ops = {
+	.get_chars = hvc_rtas_read_console,
+	.put_chars = hvc_rtas_write_console,
+};
+
+static int hvc_rtas_init(void)
+{
+	struct hvc_struct *hp;
+
+	if (rtascons_put_char_token == RTAS_UNKNOWN_SERVICE)
+		rtascons_put_char_token = rtas_token("put-term-char");
+	if (rtascons_put_char_token == RTAS_UNKNOWN_SERVICE)
+		return -EIO;
+
+	if (rtascons_get_char_token == RTAS_UNKNOWN_SERVICE)
+		rtascons_get_char_token = rtas_token("get-term-char");
+	if (rtascons_get_char_token == RTAS_UNKNOWN_SERVICE)
+		return -EIO;
+
+	BUG_ON(hvc_rtas_dev);
+
+	/* Allocate an hvc_struct for the console device we instantiated
+	 * earlier.  Save off hp so that we can return it on exit */
+	hp = hvc_alloc(hvc_rtas_cookie, NO_IRQ, &hvc_rtas_get_put_ops);
+	if (IS_ERR(hp))
+		return PTR_ERR(hp);
+	hvc_rtas_dev = hp;
+	return 0;
+}
+module_init(hvc_rtas_init);
+
+/* This will tear down the tty portion of the driver */
+static void __exit hvc_rtas_exit(void)
+{
+	/* Really the fun isn't over until the worker thread breaks down and the
+	 * tty cleans up */
+	if (hvc_rtas_dev)
+		hvc_remove(hvc_rtas_dev);
+}
+module_exit(hvc_rtas_exit); /* before drivers/char/hvc_console.c */
+
+/* This will happen prior to module init.  There is no tty at this time? */
+static int hvc_rtas_console_init(void)
+{
+	rtascons_put_char_token = rtas_token("put-term-char");
+	if (rtascons_put_char_token == RTAS_UNKNOWN_SERVICE)
+		return -EIO;
+	rtascons_get_char_token = rtas_token("get-term-char");
+	if (rtascons_get_char_token == RTAS_UNKNOWN_SERVICE)
+		return -EIO;
+
+	hvc_instantiate(hvc_rtas_cookie, 0, &hvc_rtas_get_put_ops );
+	add_preferred_console("hvc", 0, NULL);
+	return 0;
+}
+console_initcall(hvc_rtas_console_init);
Index: linus-2.6/drivers/char/Makefile
===================================================================
--- linus-2.6.orig/drivers/char/Makefile
+++ linus-2.6/drivers/char/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_SX)		+= sx.o generic_serial
 obj-$(CONFIG_RIO)		+= rio/ generic_serial.o
 obj-$(CONFIG_HVC_DRIVER)	+= hvc_console.o
 obj-$(CONFIG_HVC_CONSOLE)	+= hvc_vio.o hvsi.o
+obj-$(CONFIG_HVC_RTAS)		+= hvc_rtas.o
 obj-$(CONFIG_RAW_DRIVER)	+= raw.o
 obj-$(CONFIG_SGI_SNSC)		+= snsc.o snsc_event.o
 obj-$(CONFIG_MMTIMER)		+= mmtimer.o
Index: linus-2.6/drivers/char/Kconfig
===================================================================
--- linus-2.6.orig/drivers/char/Kconfig
+++ linus-2.6/drivers/char/Kconfig
@@ -578,6 +578,13 @@ config HVC_CONSOLE
 	  console. This driver allows each pSeries partition to have a console
 	  which is accessed via the HMC.
 
+config HVC_RTAS
+	bool "IBM RTAS Console support"
+	depends on PPC_RTAS
+	select HVC_DRIVER
+	help
+	  IBM Console device driver which makes use of RTAS
+
 config HVCS
 	tristate "IBM Hypervisor Virtual Console Server support"
 	depends on PPC_PSERIES

--

Re: [patch 02/13] powerpc: add hvc backend for rtas

[Olof Johansson]

Hi,

I have a couple of nitpicks below, nothing major.

Since it's such a simple driver, it's easy to use as a base for similar
ones, and as such it'd be nice to have it as clean as possible to avoid
others to inherit strangeness.


-Olof

On Thu, Mar 23, 2006 at 12:00:02AM +0100, Arnd Bergmann wrote:

> +static inline int hvc_rtas_write_console(uint32_t vtermno, const char *buf, int count)
> +{
> +	int done;
> +
> +	/* if there is more than one character to be displayed, wait a bit */
> +	for (done = 0; done < count; done++) {
> +		int result;
> +		result = rtas_call(rtascons_put_char_token, 1, 1, NULL, buf[done]);
> +		if (result)
> +			break;

Why introduce a scope-local variable just to check it?
		if(rtas_call(...))   would be cleaner.

> +	}
> +	/* the calling routine expects to receive the number of bytes sent */
> +	return done;
> +}
> +
> +static int hvc_rtas_read_console(uint32_t vtermno, char *buf, int count)
> +{
> +	int i;
> +
> +	for (i = 0; i < count; i++) {
> +		int c, err;
> +
> +		err = rtas_call(rtascons_get_char_token, 0, 2, &c);
> +		if (err)
> +			break;

Same here

> +
> +		buf[i] = c;
> +	}
> +
> +	return i;
> +}
> +
> +static struct hv_ops hvc_rtas_get_put_ops = {
> +	.get_chars = hvc_rtas_read_console,
> +	.put_chars = hvc_rtas_write_console,
> +};
> +
> +static int hvc_rtas_init(void)
> +{
> +	struct hvc_struct *hp;
> +
> +	if (rtascons_put_char_token == RTAS_UNKNOWN_SERVICE)
> +		rtascons_put_char_token = rtas_token("put-term-char");
> +	if (rtascons_put_char_token == RTAS_UNKNOWN_SERVICE)
> +		return -EIO;
> +
> +	if (rtascons_get_char_token == RTAS_UNKNOWN_SERVICE)
> +		rtascons_get_char_token = rtas_token("get-term-char");
> +	if (rtascons_get_char_token == RTAS_UNKNOWN_SERVICE)
> +		return -EIO;
> +
> +	BUG_ON(hvc_rtas_dev);
> +
> +	/* Allocate an hvc_struct for the console device we instantiated
> +	 * earlier.  Save off hp so that we can return it on exit */
> +	hp = hvc_alloc(hvc_rtas_cookie, NO_IRQ, &hvc_rtas_get_put_ops);
> +	if (IS_ERR(hp))
> +		return PTR_ERR(hp);
> +	hvc_rtas_dev = hp;
> +	return 0;
> +}
> +module_init(hvc_rtas_init);
> +
> +/* This will tear down the tty portion of the driver */
> +static void __exit hvc_rtas_exit(void)
> +{
> +	/* Really the fun isn't over until the worker thread breaks down and the
> +	 * tty cleans up */
> +	if (hvc_rtas_dev)
> +		hvc_remove(hvc_rtas_dev);
> +}
> +module_exit(hvc_rtas_exit); /* before drivers/char/hvc_console.c */

Cryptic comment? 

> +/* This will happen prior to module init.  There is no tty at this time? */
> +static int hvc_rtas_console_init(void)
> +{
> +	rtascons_put_char_token = rtas_token("put-term-char");
> +	if (rtascons_put_char_token == RTAS_UNKNOWN_SERVICE)
> +		return -EIO;
> +	rtascons_get_char_token = rtas_token("get-term-char");
> +	if (rtascons_get_char_token == RTAS_UNKNOWN_SERVICE)
> +		return -EIO;
> +
> +	hvc_instantiate(hvc_rtas_cookie, 0, &hvc_rtas_get_put_ops );
> +	add_preferred_console("hvc", 0, NULL);
> +	return 0;
> +}
> +console_initcall(hvc_rtas_console_init);
> Index: linus-2.6/drivers/char/Makefile
> ===================================================================
> --- linus-2.6.orig/drivers/char/Makefile
> +++ linus-2.6/drivers/char/Makefile
> @@ -43,6 +43,7 @@ obj-$(CONFIG_SX)		+= sx.o generic_serial
>  obj-$(CONFIG_RIO)		+= rio/ generic_serial.o
>  obj-$(CONFIG_HVC_DRIVER)	+= hvc_console.o
>  obj-$(CONFIG_HVC_CONSOLE)	+= hvc_vio.o hvsi.o
> +obj-$(CONFIG_HVC_RTAS)		+= hvc_rtas.o
>  obj-$(CONFIG_RAW_DRIVER)	+= raw.o
>  obj-$(CONFIG_SGI_SNSC)		+= snsc.o snsc_event.o
>  obj-$(CONFIG_MMTIMER)		+= mmtimer.o
> Index: linus-2.6/drivers/char/Kconfig
> ===================================================================
> --- linus-2.6.orig/drivers/char/Kconfig
> +++ linus-2.6/drivers/char/Kconfig
> @@ -578,6 +578,13 @@ config HVC_CONSOLE
>  	  console. This driver allows each pSeries partition to have a console
>  	  which is accessed via the HMC.
>  
> +config HVC_RTAS
> +	bool "IBM RTAS Console support"
> +	depends on PPC_RTAS
> +	select HVC_DRIVER
> +	help
> +	  IBM Console device driver which makes use of RTAS
> +
>  config HVCS
>  	tristate "IBM Hypervisor Virtual Console Server support"
>  	depends on PPC_PSERIES
> 
> --
> 
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/

Re: [Cbe-oss-dev] [patch 02/13] powerpc: add hvc backend for rtas

[Arnd Bergmann]

Am Thursday 23 March 2006 22:32 schrieb Olof Johansson:
> > +static inline int hvc_rtas_write_console(uint32_t vtermno, const char
> > *buf, int count) +{
> > +=A0=A0=A0=A0=A0int done;
> > +
> > +=A0=A0=A0=A0=A0/* if there is more than one character to be displayed,=
 wait a bit */
> > +=A0=A0=A0=A0=A0for (done =3D 0; done < count; done++) {=20
> > +=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0int result;
> > +=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0result =3D rtas_call(rtascons_p=
ut_char_token, 1, 1, NULL, buf[done]);
> > +=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0if (result)=20
> > +=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0break;
>
> Why introduce a scope-local variable just to check it?
> =A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0if(rtas_call(...)) =A0 wo=
uld be cleaner.

I don't like doing the important stuff inside of another expression,
and I prefer conditions not to have side-effects.
If nobody else has a strong opinion on it, I'd prefer to leave it.

BTW, who is the current maintainer of hvc_console? Ryan is working on
glibc nowadays, right?

> > +=A0=A0=A0=A0=A0/* Really the fun isn't over until the worker thread br=
eaks down
> > and the +=A0=A0=A0=A0=A0 * tty cleans up */
> > +=A0=A0=A0=A0=A0if (hvc_rtas_dev)
> > +=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0hvc_remove(hvc_rtas_dev);
> > +}
> > +module_exit(hvc_rtas_exit); /* before drivers/char/hvc_console.c */
>
> Cryptic comment?

No idea how what it was about, I'll remove it.

	Arnd <><

Re: [Cbe-oss-dev] [patch 02/13] powerpc: add hvc backend for rtas

[Olof Johansson]

On Thu, Mar 23, 2006 at 11:36:19PM +0100, Arnd Bergmann wrote:
> Am Thursday 23 March 2006 22:32 schrieb Olof Johansson:
> > > +static inline int hvc_rtas_write_console(uint32_t vtermno, const char
> > > *buf, int count) +{
> > > +     int done;
> > > +
> > > +     /* if there is more than one character to be displayed, wait a bit */
> > > +     for (done = 0; done < count; done++) { 
> > > +             int result;
> > > +             result = rtas_call(rtascons_put_char_token, 1, 1, NULL, buf[done]);
> > > +             if (result) 
> > > +                     break;
> >
> > Why introduce a scope-local variable just to check it?
> >                 if(rtas_call(...))   would be cleaner.
> 
> I don't like doing the important stuff inside of another expression,
> and I prefer conditions not to have side-effects.
> If nobody else has a strong opinion on it, I'd prefer to leave it.

Ok. It just looked silly to have the declaration/assignment/test and no
use of result outside of those three lines.

> BTW, who is the current maintainer of hvc_console? Ryan is working on
> glibc nowadays, right?

That's what I think IBM pays him to do, that's never stopped people from
maintaining other code in the past though. :-)


-Olof

powerpc: fix hvc-rtas comments

[Arnd Bergmann]

As notice by Olof Johansson, the comment about module_exit
in hvc_rtas is rather confusing, so remove it.

Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

---
Index: linus-2.6/drivers/char/hvc_rtas.c
===================================================================
--- linus-2.6.orig/drivers/char/hvc_rtas.c
+++ linus-2.6/drivers/char/hvc_rtas.c
@@ -119,7 +119,7 @@ static void __exit hvc_rtas_exit(void)
 	if (hvc_rtas_dev)
 		hvc_remove(hvc_rtas_dev);
 }
-module_exit(hvc_rtas_exit); /* before drivers/char/hvc_console.c */
+module_exit(hvc_rtas_exit);
 
 /* This will happen prior to module init.  There is no tty at this time? */
 static int hvc_rtas_console_init(void)

[patch 03/13] powerpc: update cell platform detection

[Arnd Bergmann]

All future firmware should have 'CBEA' in the compatible
property in order to tell us that we are running on the
cell platform, so check for that as well as the now
deprecated value we have been using so far.

Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index d34fe53..fc1f169 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1503,7 +1503,8 @@ static int __init prom_find_machine_type
 #ifdef CONFIG_PPC64
 			if (strstr(p, RELOC("Momentum,Maple")))
 				return PLATFORM_MAPLE;
-			if (strstr(p, RELOC("IBM,CPB")))
+			if (strstr(p, RELOC("IBM,CPB"))||
+			    strstr(p, RELOC("CBEA")))
 				return PLATFORM_CELL;
 #endif
 			i += sl + 1;

--

[patch 04/13] powerpc: fix cell iommu setup

[Arnd Bergmann]

A small bug crept in the iommu driver when we made it more
generic. This patch is needed for boards that have a dma
window that does not start at bus address zero.

Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

Index: linux-2.6.15-rc5/arch/powerpc/platforms/cell/iommu.c
===================================================================
--- linux-2.6.15-rc5.orig/arch/powerpc/platforms/cell/iommu.c
+++ linux-2.6.15-rc5/arch/powerpc/platforms/cell/iommu.c
@@ -289,7 +289,7 @@ static void cell_do_map_iommu(struct cel
 	ioc_base = iommu->mapped_base;
 	ioc_mmio_base = iommu->mapped_mmio_base;
 
-	for (real_address = 0, io_address = 0;
+	for (real_address = 0, io_address = map_start;
 	     io_address <= map_start + map_size;
 	     real_address += io_page_size, io_address += io_page_size) {
 		ioste = get_iost_entry(fake_iopt, io_address, io_page_size);
@@ -302,7 +302,7 @@ static void cell_do_map_iommu(struct cel
 		set_iopt_cache(ioc_mmio_base,
 			get_ioc_hash_1way(ioste, io_address),
 			get_ioc_tag(ioste, io_address),
-			get_iopt_entry(real_address-map_start, ioid, IOPT_PROT_RW));
+			get_iopt_entry(real_address, ioid, IOPT_PROT_RW));
 	}
 }
 

--

[patch 05/13] powerpc: update cell defconfig

[Arnd Bergmann]

The default configuration in mainline got a little out of
sync with what we use internally.

Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

Index: linus-2.6/arch/powerpc/configs/cell_defconfig
===================================================================
--- linus-2.6.orig/arch/powerpc/configs/cell_defconfig
+++ linus-2.6/arch/powerpc/configs/cell_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.16-rc6
-# Wed Mar 15 16:19:48 2006
+# Linux kernel version: 2.6.16
+# Thu Mar 23 20:48:09 2006
 #
 CONFIG_PPC64=y
 CONFIG_64BIT=y
@@ -30,6 +30,7 @@ CONFIG_POWER4=y
 CONFIG_PPC_FPU=y
 CONFIG_ALTIVEC=y
 CONFIG_PPC_STD_MMU=y
+CONFIG_VIRT_CPU_ACCOUNTING=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=4
 
@@ -51,7 +52,8 @@ CONFIG_SYSVIPC=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 CONFIG_SYSCTL=y
 # CONFIG_AUDIT is not set
-# CONFIG_IKCONFIG is not set
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
 # CONFIG_CPUSETS is not set
 CONFIG_INITRAMFS_SOURCE=""
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
@@ -85,7 +87,7 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_OBSOLETE_MODPARM=y
 # CONFIG_MODVERSIONS is not set
 # CONFIG_MODULE_SRCVERSION_ALL is not set
-# CONFIG_KMOD is not set
+CONFIG_KMOD=y
 CONFIG_STOP_MACHINE=y
 
 #
@@ -130,7 +132,8 @@ CONFIG_CELL_IIC=y
 #
 # Cell Broadband Engine options
 #
-CONFIG_SPU_FS=y
+CONFIG_SPU_FS=m
+CONFIG_SPUFS_MMAP=y
 
 #
 # Kernel options
@@ -144,7 +147,7 @@ CONFIG_PREEMPT_NONE=y
 # CONFIG_PREEMPT is not set
 CONFIG_PREEMPT_BKL=y
 CONFIG_BINFMT_ELF=y
-# CONFIG_BINFMT_MISC is not set
+CONFIG_BINFMT_MISC=m
 CONFIG_FORCE_MAX_ZONEORDER=13
 # CONFIG_IOMMU_VMERGE is not set
 CONFIG_KEXEC=y
@@ -155,13 +158,16 @@ CONFIG_ARCH_SELECT_MEMORY_MODEL=y
 CONFIG_ARCH_FLATMEM_ENABLE=y
 CONFIG_ARCH_SPARSEMEM_ENABLE=y
 CONFIG_SELECT_MEMORY_MODEL=y
-CONFIG_FLATMEM_MANUAL=y
+# CONFIG_FLATMEM_MANUAL is not set
 # CONFIG_DISCONTIGMEM_MANUAL is not set
-# CONFIG_SPARSEMEM_MANUAL is not set
-CONFIG_FLATMEM=y
-CONFIG_FLAT_NODE_MEM_MAP=y
+CONFIG_SPARSEMEM_MANUAL=y
+CONFIG_SPARSEMEM=y
+CONFIG_HAVE_MEMORY_PRESENT=y
 # CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPARSEMEM_EXTREME=y
+# CONFIG_MEMORY_HOTPLUG is not set
 CONFIG_SPLIT_PTLOCK_CPUS=4
+CONFIG_MIGRATION=y
 # CONFIG_PPC_64K_PAGES is not set
 CONFIG_SCHED_SMT=y
 CONFIG_PROC_DEVICETREE=y
@@ -232,6 +238,7 @@ CONFIG_TCP_CONG_BIC=y
 # CONFIG_IP_VS is not set
 CONFIG_IPV6=y
 # CONFIG_IPV6_PRIVACY is not set
+# CONFIG_IPV6_ROUTER_PREF is not set
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
@@ -244,25 +251,7 @@ CONFIG_NETFILTER=y
 # Core Netfilter Configuration
 #
 # CONFIG_NETFILTER_NETLINK is not set
-CONFIG_NETFILTER_XTABLES=m
-CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
-CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
-CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-# CONFIG_NETFILTER_XT_MATCH_DCCP is not set
-CONFIG_NETFILTER_XT_MATCH_HELPER=m
-CONFIG_NETFILTER_XT_MATCH_LENGTH=m
-CONFIG_NETFILTER_XT_MATCH_LIMIT=m
-CONFIG_NETFILTER_XT_MATCH_MAC=m
-CONFIG_NETFILTER_XT_MATCH_MARK=m
-CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
-CONFIG_NETFILTER_XT_MATCH_REALM=m
-CONFIG_NETFILTER_XT_MATCH_SCTP=m
-CONFIG_NETFILTER_XT_MATCH_STATE=m
-CONFIG_NETFILTER_XT_MATCH_STRING=m
-CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
+# CONFIG_NETFILTER_XTABLES is not set
 
 #
 # IP: Netfilter Configuration
@@ -278,51 +267,13 @@ CONFIG_IP_NF_IRC=m
 CONFIG_IP_NF_TFTP=m
 CONFIG_IP_NF_AMANDA=m
 # CONFIG_IP_NF_PPTP is not set
+# CONFIG_IP_NF_H323 is not set
 CONFIG_IP_NF_QUEUE=m
-CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_IPRANGE=m
-CONFIG_IP_NF_MATCH_MULTIPORT=m
-CONFIG_IP_NF_MATCH_TOS=m
-CONFIG_IP_NF_MATCH_RECENT=m
-CONFIG_IP_NF_MATCH_ECN=m
-CONFIG_IP_NF_MATCH_DSCP=m
-CONFIG_IP_NF_MATCH_AH_ESP=m
-CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_MATCH_OWNER=m
-CONFIG_IP_NF_MATCH_ADDRTYPE=m
-CONFIG_IP_NF_MATCH_HASHLIMIT=m
-CONFIG_IP_NF_MATCH_POLICY=m
-CONFIG_IP_NF_FILTER=m
-CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_TARGET_LOG=m
-CONFIG_IP_NF_TARGET_ULOG=m
-CONFIG_IP_NF_TARGET_TCPMSS=m
-CONFIG_IP_NF_NAT=m
-CONFIG_IP_NF_NAT_NEEDED=y
-CONFIG_IP_NF_TARGET_MASQUERADE=m
-CONFIG_IP_NF_TARGET_REDIRECT=m
-CONFIG_IP_NF_TARGET_NETMAP=m
-CONFIG_IP_NF_TARGET_SAME=m
-CONFIG_IP_NF_NAT_SNMP_BASIC=m
-CONFIG_IP_NF_NAT_IRC=m
-CONFIG_IP_NF_NAT_FTP=m
-CONFIG_IP_NF_NAT_TFTP=m
-CONFIG_IP_NF_NAT_AMANDA=m
-CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_TOS=m
-CONFIG_IP_NF_TARGET_ECN=m
-CONFIG_IP_NF_TARGET_DSCP=m
-CONFIG_IP_NF_TARGET_TTL=m
-CONFIG_IP_NF_RAW=m
-CONFIG_IP_NF_ARPTABLES=m
-CONFIG_IP_NF_ARPFILTER=m
-CONFIG_IP_NF_ARP_MANGLE=m
 
 #
 # IPv6: Netfilter Configuration (EXPERIMENTAL)
 #
 # CONFIG_IP6_NF_QUEUE is not set
-# CONFIG_IP6_NF_IPTABLES is not set
 
 #
 # DCCP Configuration (EXPERIMENTAL)
@@ -355,7 +306,6 @@ CONFIG_IP_NF_ARP_MANGLE=m
 # QoS and/or fair queueing
 #
 # CONFIG_NET_SCHED is not set
-CONFIG_NET_CLS_ROUTE=y
 
 #
 # Network testing
@@ -408,7 +358,7 @@ CONFIG_FW_LOADER=y
 # CONFIG_BLK_DEV_COW_COMMON is not set
 CONFIG_BLK_DEV_LOOP=y
 # CONFIG_BLK_DEV_CRYPTOLOOP is not set
-CONFIG_BLK_DEV_NBD=y
+# CONFIG_BLK_DEV_NBD is not set
 # CONFIG_BLK_DEV_SX8 is not set
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_COUNT=16
@@ -484,7 +434,23 @@ CONFIG_IDEDMA_AUTO=y
 #
 # Multi-device support (RAID and LVM)
 #
-# CONFIG_MD is not set
+CONFIG_MD=y
+CONFIG_BLK_DEV_MD=m
+CONFIG_MD_LINEAR=m
+CONFIG_MD_RAID0=m
+CONFIG_MD_RAID1=m
+# CONFIG_MD_RAID10 is not set
+# CONFIG_MD_RAID5 is not set
+# CONFIG_MD_RAID6 is not set
+# CONFIG_MD_MULTIPATH is not set
+# CONFIG_MD_FAULTY is not set
+CONFIG_BLK_DEV_DM=m
+CONFIG_DM_CRYPT=m
+CONFIG_DM_SNAPSHOT=m
+CONFIG_DM_MIRROR=m
+CONFIG_DM_ZERO=m
+CONFIG_DM_MULTIPATH=m
+# CONFIG_DM_MULTIPATH_EMC is not set
 
 #
 # Fusion MPT device support
@@ -548,7 +514,7 @@ CONFIG_MII=y
 # CONFIG_ACENIC is not set
 # CONFIG_DL2K is not set
 CONFIG_E1000=m
-# CONFIG_E1000_NAPI is not set
+CONFIG_E1000_NAPI=y
 # CONFIG_E1000_DISABLE_PACKET_SPLIT is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
@@ -560,7 +526,7 @@ CONFIG_SKGE=m
 # CONFIG_SK98LIN is not set
 # CONFIG_TIGON3 is not set
 # CONFIG_BNX2 is not set
-CONFIG_SPIDER_NET=y
+CONFIG_SPIDER_NET=m
 # CONFIG_MV643XX_ETH is not set
 
 #
@@ -678,6 +644,8 @@ CONFIG_SERIAL_CORE_CONSOLE=y
 # CONFIG_SERIAL_JSM is not set
 CONFIG_UNIX98_PTYS=y
 # CONFIG_LEGACY_PTYS is not set
+CONFIG_HVC_DRIVER=y
+CONFIG_HVC_RTAS=y
 
 #
 # IPMI
@@ -694,14 +662,13 @@ CONFIG_WATCHDOG=y
 # Watchdog Device Drivers
 #
 # CONFIG_SOFT_WATCHDOG is not set
-# CONFIG_WATCHDOG_RTAS is not set
+CONFIG_WATCHDOG_RTAS=y
 
 #
 # PCI-based Watchdog Cards
 #
 # CONFIG_PCIPCWATCHDOG is not set
 # CONFIG_WDTPCI is not set
-# CONFIG_RTC is not set
 CONFIG_GEN_RTC=y
 # CONFIG_GEN_RTC_X is not set
 # CONFIG_DTLK is not set
@@ -833,6 +800,7 @@ CONFIG_DUMMY_CONSOLE=y
 #
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
+CONFIG_USB_ARCH_HAS_EHCI=y
 # CONFIG_USB is not set
 
 #
@@ -852,7 +820,14 @@ CONFIG_USB_ARCH_HAS_OHCI=y
 #
 # InfiniBand support
 #
-# CONFIG_INFINIBAND is not set
+CONFIG_INFINIBAND=y
+CONFIG_INFINIBAND_USER_MAD=m
+CONFIG_INFINIBAND_USER_ACCESS=m
+CONFIG_INFINIBAND_MTHCA=m
+CONFIG_INFINIBAND_MTHCA_DEBUG=y
+CONFIG_INFINIBAND_IPOIB=m
+CONFIG_INFINIBAND_IPOIB_DEBUG=y
+CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y
 
 #
 # EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
@@ -1037,10 +1012,6 @@ CONFIG_CRC32=y
 # CONFIG_LIBCRC32C is not set
 CONFIG_ZLIB_INFLATE=m
 CONFIG_ZLIB_DEFLATE=m
-CONFIG_TEXTSEARCH=y
-CONFIG_TEXTSEARCH_KMP=m
-CONFIG_TEXTSEARCH_BM=m
-CONFIG_TEXTSEARCH_FSM=m
 
 #
 # Instrumentation Support
@@ -1058,7 +1029,7 @@ CONFIG_LOG_BUF_SHIFT=15
 CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_DEBUG_SLAB is not set
-# CONFIG_DEBUG_MUTEXES is not set
+CONFIG_DEBUG_MUTEXES=y
 # CONFIG_DEBUG_SPINLOCK is not set
 CONFIG_DEBUG_SPINLOCK_SLEEP=y
 # CONFIG_DEBUG_KOBJECT is not set

--

[patch 06/13] powerpc: cell interrupt controller updates

[Arnd Bergmann]

The current interrupt controller setup on Cell is done
in a rather ad-hoc way with device tree properties
that are not standardized at all.

In an attempt to do something that follows the OF standard
(or at least the IBM extensions to it) more closely,
we have now come up with this patch. It still provides
a fallback to the old behaviour when we find older firmware,
that hack can not be removed until the existing customer
installations have upgraded.

Cc: hpenner@de.ibm.com
Cc: stk@de.ibm.com
Cc: Segher Boessenkool <segher@kernel.crashing.org>
Cc: Milton Miller <miltonm@bga.com>
Cc: benh@kernel.crashing.org
From: Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

Index: linus-2.6/arch/powerpc/platforms/cell/spider-pic.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/spider-pic.c
+++ linus-2.6/arch/powerpc/platforms/cell/spider-pic.c
@@ -84,10 +84,11 @@ static void __iomem *spider_get_irq_conf
 
 static void spider_enable_irq(unsigned int irq)
 {
+	int nodeid = (irq / IIC_NODE_STRIDE) * 0x10;
 	void __iomem *cfg = spider_get_irq_config(irq);
 	irq = spider_get_nr(irq);
 
-	out_be32(cfg, in_be32(cfg) | 0x3107000eu);
+	out_be32(cfg, in_be32(cfg) | 0x3107000eu | nodeid);
 	out_be32(cfg + 4, in_be32(cfg + 4) | 0x00020000u | irq);
 }
 
@@ -131,61 +132,108 @@ static struct hw_interrupt_type spider_p
 	.end = spider_end_irq,
 };
 
-
-int spider_get_irq(unsigned long int_pending)
+int spider_get_irq(int node)
 {
-	void __iomem *regs = spider_get_pic(int_pending);
 	unsigned long cs;
-	int irq;
-
-	cs = in_be32(regs + TIR_CS);
+	void __iomem *regs = spider_pics[node];
 
-	irq = cs >> 24;
-	if (irq != 63)
-		return irq;
+	cs = in_be32(regs + TIR_CS) >> 24;
 
-	return -1;
+	if (cs == 63)
+		return -1;
+	else
+		return cs;
 }
- 
-void spider_init_IRQ(void)
+
+/* hardcoded part to be compatible with older firmware */
+
+void spider_init_IRQ_hardcoded(void)
 {
 	int node;
-	struct device_node *dn;
-	unsigned int *property;
 	long spiderpic;
+	long pics[] = { 0x24000008000, 0x34000008000 };
 	int n;
 
-/* FIXME: detect multiple PICs as soon as the device tree has them */
-	for (node = 0; node < 1; node++) {
-		dn = of_find_node_by_path("/");
-		n = prom_n_addr_cells(dn);
-		property = (unsigned int *) get_property(dn,
-				"platform-spider-pic", NULL);
+	pr_debug("%s(%d): Using hardcoded defaults\n", __FUNCTION__, __LINE__);
 
-		if (!property)
-			continue;
-		for (spiderpic = 0; n > 0; --n)
-			spiderpic = (spiderpic << 32) + *property++;
+	for (node = 0; node < num_present_cpus()/2; node++) {
+		spiderpic = pics[node];
 		printk(KERN_DEBUG "SPIDER addr: %lx\n", spiderpic);
 		spider_pics[node] = __ioremap(spiderpic, 0x800, _PAGE_NO_CACHE);
 		for (n = 0; n < IIC_NUM_EXT; n++) {
 			int irq = n + IIC_EXT_OFFSET + node * IIC_NODE_STRIDE;
 			get_irq_desc(irq)->handler = &spider_pic;
+		}
 
  		/* do not mask any interrupts because of level */
  		out_be32(spider_pics[node] + TIR_MSK, 0x0);
- 		
+
  		/* disable edge detection clear */
  		/* out_be32(spider_pics[node] + TIR_EDC, 0x0); */
- 		
+
  		/* enable interrupt packets to be output */
  		out_be32(spider_pics[node] + TIR_PIEN,
 			in_be32(spider_pics[node] + TIR_PIEN) | 0x1);
- 		
+
  		/* Enable the interrupt detection enable bit. Do this last! */
  		out_be32(spider_pics[node] + TIR_DEN,
-			in_be32(spider_pics[node] +TIR_DEN) | 0x1);
+			in_be32(spider_pics[node] + TIR_DEN) | 0x1);
+	}
+}
+
+void spider_init_IRQ(void)
+{
+	long spider_reg;
+	struct device_node *dn;
+	char *compatible;
+	int n, node = 0;
+
+	for (dn = NULL; (dn = of_find_node_by_name(dn, "interrupt-controller"));) {
+		compatible = (char *)get_property(dn, "compatible", NULL);
 
+		if (!compatible)
+			continue;
+
+		if (strstr(compatible, "CBEA,platform-spider-pic"))
+			spider_reg = *(long *)get_property(dn,"reg", NULL);
+		else if (strstr(compatible, "sti,platform-spider-pic")) {
+			spider_init_IRQ_hardcoded();
+			return;
+		} else
+			continue;
+
+		if (!spider_reg)
+			printk("interrupt controller does not have reg property !\n");
+
+		n = prom_n_addr_cells(dn);
+
+		if ( n != 2)
+			printk("reg property with invalid number of elements \n");
+
+		spider_pics[node] = __ioremap(spider_reg, 0x800, _PAGE_NO_CACHE);
+
+		printk("SPIDER addr: %lx with %i addr_cells mapped to %p\n",
+		       spider_reg, n, spider_pics[node]);
+
+		for (n = 0; n < IIC_NUM_EXT; n++) {
+			int irq = n + IIC_EXT_OFFSET + node * IIC_NODE_STRIDE;
+			get_irq_desc(irq)->handler = &spider_pic;
 		}
+
+		/* do not mask any interrupts because of level */
+		out_be32(spider_pics[node] + TIR_MSK, 0x0);
+
+		/* disable edge detection clear */
+		/* out_be32(spider_pics[node] + TIR_EDC, 0x0); */
+
+		/* enable interrupt packets to be output */
+		out_be32(spider_pics[node] + TIR_PIEN,
+			in_be32(spider_pics[node] + TIR_PIEN) | 0x1);
+
+		/* Enable the interrupt detection enable bit. Do this last! */
+		out_be32(spider_pics[node] + TIR_DEN,
+			in_be32(spider_pics[node] + TIR_DEN) | 0x1);
+
+		node++;
 	}
 }
Index: linus-2.6/arch/powerpc/platforms/cell/interrupt.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/interrupt.c
+++ linus-2.6/arch/powerpc/platforms/cell/interrupt.c
@@ -123,7 +123,7 @@ static int iic_external_get_irq(struct i
 		    pending.class != 2)
 			break;
 		irq = IIC_EXT_OFFSET
-			+ spider_get_irq(pending.prio + node * IIC_NODE_STRIDE)
+			+ spider_get_irq(node)
 			+ node * IIC_NODE_STRIDE;
 		break;
 	case 0x01 ... 0x04:
@@ -174,40 +174,104 @@ int iic_get_irq(struct pt_regs *regs)
 	return irq;
 }
 
-static int setup_iic(int cpu, struct iic *iic)
+/* hardcoded part to be compatible with older firmware */
+
+static int setup_iic_hardcoded(void)
 {
 	struct device_node *np;
-	int nodeid = cpu / 2;
+	int nodeid, cpu;
 	unsigned long regs;
+	struct iic *iic;
 
-	for (np = of_find_node_by_type(NULL, "cpu");
-	     np;
-	     np = of_find_node_by_type(np, "cpu")) {
-		if (nodeid == *(int *)get_property(np, "node-id", NULL))
-			break;
-	}
+	for_each_cpu(cpu) {
+		iic = &per_cpu(iic, cpu);
+		nodeid = cpu/2;
 
-	if (!np) {
-		printk(KERN_WARNING "IIC: CPU %d not found\n", cpu);
-		iic->regs = NULL;
-		iic->target_id = 0xff;
-		return -ENODEV;
-	}
+		for (np = of_find_node_by_type(NULL, "cpu");
+		     np;
+		     np = of_find_node_by_type(np, "cpu")) {
+			if (nodeid == *(int *)get_property(np, "node-id", NULL))
+				break;
+			}
+
+		if (!np) {
+			printk(KERN_WARNING "IIC: CPU %d not found\n", cpu);
+			iic->regs = NULL;
+			iic->target_id = 0xff;
+			return -ENODEV;
+			}
+
+		regs = *(long *)get_property(np, "iic", NULL);
+
+		/* hack until we have decided on the devtree info */
+		regs += 0x400;
+		if (cpu & 1)
+			regs += 0x20;
+
+		printk(KERN_INFO "IIC for CPU %d at %lx\n", cpu, regs);
+		iic->regs = __ioremap(regs, sizeof(struct iic_regs),
+				      _PAGE_NO_CACHE);
 
-	regs = *(long *)get_property(np, "iic", NULL);
+		iic->target_id = (nodeid << 4) + ((cpu & 1) ? 0xf : 0xe);
+	}
 
-	/* hack until we have decided on the devtree info */
-	regs += 0x400;
-	if (cpu & 1)
-		regs += 0x20;
-
-	printk(KERN_DEBUG "IIC for CPU %d at %lx\n", cpu, regs);
-	iic->regs = __ioremap(regs, sizeof(struct iic_regs),
-					 _PAGE_NO_CACHE);
-	iic->target_id = (nodeid << 4) + ((cpu & 1) ? 0xf : 0xe);
 	return 0;
 }
 
+static int setup_iic(void)
+{
+	struct device_node *dn;
+	unsigned long *regs;
+	char *compatible;
+ 	unsigned *np, found = 0;
+	struct iic *iic = NULL;
+
+	for (dn = NULL; (dn = of_find_node_by_name(dn, "interrupt-controller"));) {
+		compatible = (char *)get_property(dn, "compatible", NULL);
+
+		if (!compatible) {
+			printk(KERN_WARNING "no compatible property found !\n");
+			continue;
+		}
+
+ 		if (strstr(compatible, "IBM,CBEA-Internal-Interrupt-Controller"))
+ 			regs = (unsigned long *)get_property(dn,"reg", NULL);
+ 		else
+			continue;
+
+ 		if (!regs)
+ 			printk(KERN_WARNING "IIC: no reg property\n");
+
+ 		np = (unsigned int *)get_property(dn, "ibm,interrupt-server-ranges", NULL);
+
+ 		if (!np) {
+			printk(KERN_WARNING "IIC: CPU association not found\n");
+			iic->regs = NULL;
+			iic->target_id = 0xff;
+			return -ENODEV;
+		}
+
+ 		iic = &per_cpu(iic, np[0]);
+ 		iic->regs = __ioremap(regs[0], sizeof(struct iic_regs),
+ 				      _PAGE_NO_CACHE);
+		iic->target_id = ((np[0] & 2) << 3) + ((np[0] & 1) ? 0xf : 0xe);
+ 		printk("IIC for CPU %d at %lx mapped to %p\n", np[0], regs[0], iic->regs);
+
+ 		iic = &per_cpu(iic, np[1]);
+ 		iic->regs = __ioremap(regs[2], sizeof(struct iic_regs),
+ 				      _PAGE_NO_CACHE);
+		iic->target_id = ((np[1] & 2) << 3) + ((np[1] & 1) ? 0xf : 0xe);
+ 		printk("IIC for CPU %d at %lx mapped to %p\n", np[1], regs[2], iic->regs);
+
+		found++;
+  	}
+
+	if (found)
+		return 0;
+	else
+		return -ENODEV;
+}
+
 #ifdef CONFIG_SMP
 
 /* Use the highest interrupt priorities for IPI */
@@ -283,10 +347,12 @@ void iic_init_IRQ(void)
 	int cpu, irq_offset;
 	struct iic *iic;
 
+	if (setup_iic() < 0)
+		setup_iic_hardcoded();
+
 	irq_offset = 0;
 	for_each_cpu(cpu) {
 		iic = &per_cpu(iic, cpu);
-		setup_iic(cpu, iic);
 		if (iic->regs)
 			out_be64(&iic->regs->prio, 0xff);
 	}
Index: linus-2.6/arch/powerpc/platforms/cell/interrupt.h
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/interrupt.h
+++ linus-2.6/arch/powerpc/platforms/cell/interrupt.h
@@ -57,7 +57,7 @@ extern void iic_local_disable(void);
 extern u8 iic_get_target_id(int cpu);
 
 extern void spider_init_IRQ(void);
-extern int spider_get_irq(unsigned long int_pending);
+extern int spider_get_irq(int node);
 
 #endif
 #endif /* ASM_CELL_PIC_H */

--

Re: [patch 06/13] powerpc: cell interrupt controller updates

[Benjamin Herrenschmidt]

On Thu, 2006-03-23 at 00:00 +0100, Arnd Bergmann wrote:
> plain text document attachment (cell-pic-updates-3.diff)
> The current interrupt controller setup on Cell is done
> in a rather ad-hoc way with device tree properties
> that are not standardized at all.
> 
> In an attempt to do something that follows the OF standard
> (or at least the IBM extensions to it) more closely,
> we have now come up with this patch. It still provides
> a fallback to the old behaviour when we find older firmware,
> that hack can not be removed until the existing customer
> installations have upgraded.

BTW... You still use __ioremap(...,PAGE_NO_CACHE); which I think won't
give you guarded... I wouldn'd do that if I were you... The accessors
should have barriers but still...

Ben.

[PATCH] powerpc: use guarded ioremap for on-chip mappings

[Arnd Bergmann]

Subject: powerpc: use guarded ioremap for cell on-chip mappings

I'm not sure where the information came from, but I assumed
that doing cache-inhibited mappings for mmio regions was
sufficient.

It seems we also need the guarded bit set, like everyone
else, which is the default for ioremap.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>

---
Index: linus-2.6/arch/powerpc/platforms/cell/interrupt.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/interrupt.c
+++ linus-2.6/arch/powerpc/platforms/cell/interrupt.c
@@ -226,9 +226,7 @@ static int setup_iic_hardcoded(void)
 			regs += 0x20;
 
 		printk(KERN_INFO "IIC for CPU %d at %lx\n", cpu, regs);
-		iic->regs = __ioremap(regs, sizeof(struct iic_regs),
-				      _PAGE_NO_CACHE);
-
+		iic->regs = ioremap(regs, sizeof(struct iic_regs));
 		iic->target_id = (nodeid << 4) + ((cpu & 1) ? 0xf : 0xe);
 	}
 
@@ -269,14 +267,12 @@ static int setup_iic(void)
 		}
 
  		iic = &per_cpu(iic, np[0]);
- 		iic->regs = __ioremap(regs[0], sizeof(struct iic_regs),
- 				      _PAGE_NO_CACHE);
+ 		iic->regs = ioremap(regs[0], sizeof(struct iic_regs));
 		iic->target_id = ((np[0] & 2) << 3) + ((np[0] & 1) ? 0xf : 0xe);
  		printk("IIC for CPU %d at %lx mapped to %p\n", np[0], regs[0], iic->regs);
 
  		iic = &per_cpu(iic, np[1]);
- 		iic->regs = __ioremap(regs[2], sizeof(struct iic_regs),
- 				      _PAGE_NO_CACHE);
+ 		iic->regs = ioremap(regs[2], sizeof(struct iic_regs));
 		iic->target_id = ((np[1] & 2) << 3) + ((np[1] & 1) ? 0xf : 0xe);
  		printk("IIC for CPU %d at %lx mapped to %p\n", np[1], regs[2], iic->regs);
 
Index: linus-2.6/arch/powerpc/platforms/cell/iommu.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/iommu.c
+++ linus-2.6/arch/powerpc/platforms/cell/iommu.c
@@ -344,8 +344,8 @@ static int cell_map_iommu_hardcoded(int 
 
 	/* node 0 */
 	iommu = &cell_iommus[0];
-	iommu->mapped_base = __ioremap(0x20000511000, 0x1000, _PAGE_NO_CACHE);
-	iommu->mapped_mmio_base = __ioremap(0x20000510000, 0x1000, _PAGE_NO_CACHE);
+	iommu->mapped_base = ioremap(0x20000511000, 0x1000);
+	iommu->mapped_mmio_base = ioremap(0x20000510000, 0x1000);
 
 	enable_mapping(iommu->mapped_base, iommu->mapped_mmio_base);
 
@@ -357,8 +357,8 @@ static int cell_map_iommu_hardcoded(int 
 
 	/* node 1 */
 	iommu = &cell_iommus[1];
-	iommu->mapped_base = __ioremap(0x30000511000, 0x1000, _PAGE_NO_CACHE);
-	iommu->mapped_mmio_base = __ioremap(0x30000510000, 0x1000, _PAGE_NO_CACHE);
+	iommu->mapped_base = ioremap(0x30000511000, 0x1000);
+	iommu->mapped_mmio_base = ioremap(0x30000510000, 0x1000);
 
 	enable_mapping(iommu->mapped_base, iommu->mapped_mmio_base);
 
@@ -407,8 +407,8 @@ static int cell_map_iommu(void)
 		iommu->base = *base;
 		iommu->mmio_base = *mmio_base;
 
-		iommu->mapped_base = __ioremap(*base, 0x1000, _PAGE_NO_CACHE);
-		iommu->mapped_mmio_base = __ioremap(*mmio_base, 0x1000, _PAGE_NO_CACHE);
+		iommu->mapped_base = ioremap(*base, 0x1000);
+		iommu->mapped_mmio_base = ioremap(*mmio_base, 0x1000);
 
 		enable_mapping(iommu->mapped_base,
 			       iommu->mapped_mmio_base);
Index: linus-2.6/arch/powerpc/platforms/cell/pervasive.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/pervasive.c
+++ linus-2.6/arch/powerpc/platforms/cell/pervasive.c
@@ -203,7 +203,7 @@ found:
 
 	pr_debug("pervasive area for CPU %d at %lx, size %x\n",
 			cpu, real_address, size);
-	p->regs = __ioremap(real_address, size, _PAGE_NO_CACHE);
+	p->regs = ioremap(real_address, size);
 	p->thread = thread;
 	return 0;
 }
Index: linus-2.6/arch/powerpc/platforms/cell/spider-pic.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/spider-pic.c
+++ linus-2.6/arch/powerpc/platforms/cell/spider-pic.c
@@ -159,7 +159,7 @@ void spider_init_IRQ_hardcoded(void)
 	for (node = 0; node < num_present_cpus()/2; node++) {
 		spiderpic = pics[node];
 		printk(KERN_DEBUG "SPIDER addr: %lx\n", spiderpic);
-		spider_pics[node] = __ioremap(spiderpic, 0x800, _PAGE_NO_CACHE);
+		spider_pics[node] = ioremap(spiderpic, 0x800);
 		for (n = 0; n < IIC_NUM_EXT; n++) {
 			int irq = n + IIC_EXT_OFFSET + node * IIC_NODE_STRIDE;
 			get_irq_desc(irq)->handler = &spider_pic;
@@ -210,7 +210,7 @@ void spider_init_IRQ(void)
 		if ( n != 2)
 			printk("reg property with invalid number of elements \n");
 
-		spider_pics[node] = __ioremap(spider_reg, 0x800, _PAGE_NO_CACHE);
+		spider_pics[node] = ioremap(spider_reg, 0x800);
 
 		printk("SPIDER addr: %lx with %i addr_cells mapped to %p\n",
 		       spider_reg, n, spider_pics[node]);

Re: [patch 06/13] powerpc: cell interrupt controller updates

[Milton Miller]

On Mar 22, 2006, at 5:00 PM, Arnd Bergmann wrote:
>  static void spider_enable_irq(unsigned int irq)
>  {
> +	int nodeid = (irq / IIC_NODE_STRIDE) * 0x10;
>  	void __iomem *cfg = spider_get_irq_config(irq);
>  	irq = spider_get_nr(irq);
>
> -	out_be32(cfg, in_be32(cfg) | 0x3107000eu);
> +	out_be32(cfg, in_be32(cfg) | 0x3107000eu | nodeid);
>  	out_be32(cfg + 4, in_be32(cfg + 4) | 0x00020000u | irq);
>  }
>

I just did a quick read of the code, but my first thought is what if 
some other node id was previously set?  Perhaps you should mask off 
some bits before or'ing in the node id?

milton

Re: [patch 06/13] powerpc: cell interrupt controller updates

[Arnd Bergmann]

On Friday 24 March 2006 18:43, Milton Miller wrote:
> On Mar 22, 2006, at 5:00 PM, Arnd Bergmann wrote:
> >  static void spider_enable_irq(unsigned int irq)
> >  {
> > +     int nodeid = (irq / IIC_NODE_STRIDE) * 0x10;
> >       void __iomem *cfg = spider_get_irq_config(irq);
> >       irq = spider_get_nr(irq);
> >
> > -     out_be32(cfg, in_be32(cfg) | 0x3107000eu);
> > +     out_be32(cfg, in_be32(cfg) | 0x3107000eu | nodeid);
> >       out_be32(cfg + 4, in_be32(cfg + 4) | 0x00020000u | irq);
> >  }
> >
> 
> I just did a quick read of the code, but my first thought is what if 
> some other node id was previously set?  Perhaps you should mask off 
> some bits before or'ing in the node id?

Good point. The firmware always sets nodeid zero (or the same one that
we set), but I can't see any reason why we should take that for granted.

Thanks,

	Arnd <><

[PATCH] powerpc: fix spider-pic affinity setting

[Arnd Bergmann]

As noticed by Milton Miller, setting the initial affinity in
spider-pic can go wrong if the target node field was not orinally
empty.

Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

--- linus-2.6.orig/arch/powerpc/platforms/cell/spider-pic.c
+++ linus-2.6/arch/powerpc/platforms/cell/spider-pic.c
@@ -88,7 +88,7 @@ static void spider_enable_irq(unsigned i
 	void __iomem *cfg = spider_get_irq_config(irq);
 	irq = spider_get_nr(irq);
 
-	out_be32(cfg, in_be32(cfg) | 0x3107000eu | nodeid);
+	out_be32(cfg, (in_be32(cfg) & ~0xf0)| 0x3107000eu | nodeid);
 	out_be32(cfg + 4, in_be32(cfg + 4) | 0x00020000u | irq);
 }
 

[patch 07/13] powerpc: work around a cell interrupt HW bug

[Arnd Bergmann]

Apparently we have found a bug in the CPU that causes
external interrupts to sometimes get disabled indefinitely.
This adds a workaround for the problem.

Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

Index: linux-2.6.15.4/arch/powerpc/platforms/cell/interrupt.c
===================================================================
--- linux-2.6.15.4.orig/arch/powerpc/platforms/cell/interrupt.c
+++ linux-2.6.15.4/arch/powerpc/platforms/cell/interrupt.c
@@ -63,7 +63,24 @@ static DEFINE_PER_CPU(struct iic, iic);
 
 void iic_local_enable(void)
 {
-	out_be64(&__get_cpu_var(iic).regs->prio, 0xff);
+	struct iic *iic = &__get_cpu_var(iic);
+	u64 tmp;
+
+	/*
+	 * There seems to be a bug that is present in DD2.x CPUs
+	 * and still only partially fixed in DD3.1.
+	 * This bug causes a value written to the priority register
+	 * not to make it there, resulting in a system hang unless we
+	 * write it again.
+	 * Masking with 0xf0 is done because the Cell BE does not
+	 * implement the lower four bits of the interrupt priority,
+	 * they always read back as zeroes, although future CPUs
+	 * might implement different bits.
+	 */
+	do {
+		out_be64(&iic->regs->prio, 0xff);
+		tmp = in_be64(&iic->regs->prio);
+	} while ((tmp & 0xf0) != 0xf0);
 }
 
 void iic_local_disable(void)

--

[patch 08/13] powerpc: declare arch syscalls in <asm/syscalls.h>

[Arnd Bergmann]

powerpc currently declares some of its own system calls
in <asm/unistd.h>, but not all of them. That place also
contains remainders of the now almost unused kernel syscall
hack.

 - Add a new <asm/syscalls.h> with clean declarations
 - Include that file from every source that implements one
   of these
 - Get rid of old declarations in <asm/unistd.h>

This patch is required as a base for implementing system
calls from an SPU, but also makes sense as a general
cleanup.

Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

Index: linus-2.6/include/asm-powerpc/syscalls.h
===================================================================
--- /dev/null
+++ linus-2.6/include/asm-powerpc/syscalls.h
@@ -0,0 +1,58 @@
+#ifndef __ASM_POWERPC_SYSCALLS_H
+#define __ASM_POWERPC_SYSCALLS_H
+#ifdef __KERNEL__
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <asm/signal.h>
+
+struct new_utsname;
+struct pt_regs;
+struct rtas_args;
+struct sigaction;
+
+asmlinkage unsigned long sys_mmap(unsigned long addr, size_t len,
+		unsigned long prot, unsigned long flags,
+		unsigned long fd, off_t offset);
+asmlinkage unsigned long sys_mmap2(unsigned long addr, size_t len,
+		unsigned long prot, unsigned long flags,
+		unsigned long fd, unsigned long pgoff);
+asmlinkage int sys_execve(unsigned long a0, unsigned long a1,
+		unsigned long a2, unsigned long a3, unsigned long a4,
+		unsigned long a5, struct pt_regs *regs);
+asmlinkage int sys_clone(unsigned long clone_flags, unsigned long usp,
+		int __user *parent_tidp, void __user *child_threadptr,
+		int __user *child_tidp, int p6, struct pt_regs *regs);
+asmlinkage int sys_fork(unsigned long p1, unsigned long p2,
+		unsigned long p3, unsigned long p4, unsigned long p5,
+		unsigned long p6, struct pt_regs *regs);
+asmlinkage int sys_vfork(unsigned long p1, unsigned long p2,
+		unsigned long p3, unsigned long p4, unsigned long p5,
+		unsigned long p6, struct pt_regs *regs);
+asmlinkage int sys_pipe(int __user *fildes);
+asmlinkage long sys_rt_sigaction(int sig,
+		const struct sigaction __user *act,
+		struct sigaction __user *oact, size_t sigsetsize);
+asmlinkage int sys_ipc(uint call, int first, unsigned long second,
+		long third, void __user *ptr, long fifth);
+asmlinkage long ppc64_personality(unsigned long personality);
+asmlinkage int ppc_rtas(struct rtas_args __user *uargs);
+asmlinkage time_t sys64_time(time_t __user * tloc);
+asmlinkage long ppc_newuname(struct new_utsname __user * name);
+
+asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset,
+		size_t sigsetsize);
+
+#ifndef __powerpc64__
+asmlinkage long sys_sigaltstack(const stack_t __user *uss,
+		stack_t __user *uoss, int r5, int r6, int r7, int r8,
+		struct pt_regs *regs);
+#else /* __powerpc64__ */
+asmlinkage long sys_sigaltstack(const stack_t __user *uss,
+		stack_t __user *uoss, unsigned long r5, unsigned long r6,
+		unsigned long r7, unsigned long r8, struct pt_regs *regs);
+#endif /* __powerpc64__ */
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_POWERPC_SYSCALLS_H */
Index: linus-2.6/include/asm-powerpc/unistd.h
===================================================================
--- linus-2.6.orig/include/asm-powerpc/unistd.h
+++ linus-2.6/include/asm-powerpc/unistd.h
@@ -425,6 +425,7 @@ type name(type1 arg1, type2 arg2, type3 
 #include <linux/types.h>
 #include <linux/compiler.h>
 #include <linux/linkage.h>
+#include <asm/syscalls.h>
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
@@ -460,44 +461,10 @@ type name(type1 arg1, type2 arg2, type3 
  * System call prototypes.
  */
 #ifdef __KERNEL_SYSCALLS__
-extern pid_t setsid(void);
-extern int write(int fd, const char *buf, off_t count);
-extern int read(int fd, char *buf, off_t count);
-extern off_t lseek(int fd, off_t offset, int count);
-extern int dup(int fd);
 extern int execve(const char *file, char **argv, char **envp);
-extern int open(const char *file, int flag, int mode);
-extern int close(int fd);
-extern pid_t waitpid(pid_t pid, int *wait_stat, int options);
 #endif /* __KERNEL_SYSCALLS__ */
 
 /*
- * Functions that implement syscalls.
- */
-unsigned long sys_mmap(unsigned long addr, size_t len, unsigned long prot,
-		       unsigned long flags, unsigned long fd, off_t offset);
-unsigned long sys_mmap2(unsigned long addr, size_t len,
-			unsigned long prot, unsigned long flags,
-			unsigned long fd, unsigned long pgoff);
-struct pt_regs;
-int sys_execve(unsigned long a0, unsigned long a1, unsigned long a2,
-		unsigned long a3, unsigned long a4, unsigned long a5,
-		struct pt_regs *regs);
-int sys_clone(unsigned long clone_flags, unsigned long usp,
-		int __user *parent_tidp, void __user *child_threadptr,
-		int __user *child_tidp, int p6, struct pt_regs *regs);
-int sys_fork(unsigned long p1, unsigned long p2, unsigned long p3,
-		unsigned long p4, unsigned long p5, unsigned long p6,
-		struct pt_regs *regs);
-int sys_vfork(unsigned long p1, unsigned long p2, unsigned long p3,
-		unsigned long p4, unsigned long p5, unsigned long p6,
-		struct pt_regs *regs);
-int sys_pipe(int __user *fildes);
-struct sigaction;
-long sys_rt_sigaction(int sig, const struct sigaction __user *act,
-		      struct sigaction __user *oact, size_t sigsetsize);
-
-/*
  * "Conditional" syscalls
  *
  * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
Index: linus-2.6/arch/powerpc/kernel/process.c
===================================================================
--- linus-2.6.orig/arch/powerpc/kernel/process.c
+++ linus-2.6/arch/powerpc/kernel/process.c
@@ -46,6 +46,7 @@
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/time.h>
+#include <asm/syscalls.h>
 #ifdef CONFIG_PPC64
 #include <asm/firmware.h>
 #endif
Index: linus-2.6/arch/powerpc/kernel/rtas.c
===================================================================
--- linus-2.6.orig/arch/powerpc/kernel/rtas.c
+++ linus-2.6/arch/powerpc/kernel/rtas.c
@@ -32,6 +32,7 @@
 #include <asm/uaccess.h>
 #include <asm/lmb.h>
 #include <asm/udbg.h>
+#include <asm/syscalls.h>
 
 struct rtas_t rtas = {
 	.lock = SPIN_LOCK_UNLOCKED
Index: linus-2.6/arch/powerpc/kernel/signal_32.c
===================================================================
--- linus-2.6.orig/arch/powerpc/kernel/signal_32.c
+++ linus-2.6/arch/powerpc/kernel/signal_32.c
@@ -42,6 +42,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
+#include <asm/syscalls.h>
 #include <asm/sigcontext.h>
 #include <asm/vdso.h>
 #ifdef CONFIG_PPC64
Index: linus-2.6/arch/powerpc/kernel/signal_64.c
===================================================================
--- linus-2.6.orig/arch/powerpc/kernel/signal_64.c
+++ linus-2.6/arch/powerpc/kernel/signal_64.c
@@ -33,6 +33,7 @@
 #include <asm/pgtable.h>
 #include <asm/unistd.h>
 #include <asm/cacheflush.h>
+#include <asm/syscalls.h>
 #include <asm/vdso.h>
 
 #define DEBUG_SIG 0
Index: linus-2.6/arch/powerpc/kernel/syscalls.c
===================================================================
--- linus-2.6.orig/arch/powerpc/kernel/syscalls.c
+++ linus-2.6/arch/powerpc/kernel/syscalls.c
@@ -40,6 +40,7 @@
 #include <asm/uaccess.h>
 #include <asm/ipc.h>
 #include <asm/semaphore.h>
+#include <asm/syscalls.h>
 #include <asm/time.h>
 #include <asm/unistd.h>
 

--

[patch 09/13] spufs: allow SPU code to do syscalls

[Arnd Bergmann]

An SPU does not have a way to implement system calls
itself, but it can create intercepts to the kernel.

This patch uses the method defined by the JSRE interface
for C99 host library calls from an SPU to implement
Linux system calls. It uses the reserved SPU stop code
0x2104 for this, using the structure layout and syscall
numbers for ppc64-linux.

I'm still undecided wether it is better to have a list
of allowed syscalls or a list of forbidden syscalls,
since we can't allow an SPU to call all syscalls that
are defined for ppc64-linux.

This patch implements the easier choice of them, with a
blacklist that only prevents an SPU from calling anything
that interacts with its own execution, e.g fork, execve,
clone, vfork, exit, spu_run and spu_create and everything
that deals with signals.

Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

Index: linux-2.6.16-rc/arch/powerpc/platforms/cell/Makefile
===================================================================
--- linux-2.6.16-rc.orig/arch/powerpc/platforms/cell/Makefile
+++ linux-2.6.16-rc/arch/powerpc/platforms/cell/Makefile
@@ -6,5 +6,11 @@ obj-$(CONFIG_SPU_FS)	+= spu-base.o spufs
 
 spu-base-y		+= spu_base.o spu_priv1.o
 
-builtin-spufs-$(CONFIG_SPU_FS)	+= spu_syscalls.o
-obj-y			+= $(builtin-spufs-m)
+# needed only when building loadable spufs.ko
+spufs-modular-$(CONFIG_SPU_FS) += spu_syscalls.o
+obj-y			+= $(spufs-modular-m)
+
+# always needed in kernel
+spufs-builtin-$(CONFIG_SPU_FS) += spu_callbacks.o
+obj-y			+= $(spufs-builtin-y) $(spufs-builtin-m)
+
Index: linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/run.c
===================================================================
--- linux-2.6.16-rc.orig/arch/powerpc/platforms/cell/spufs/run.c
+++ linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/run.c
@@ -76,6 +76,90 @@ static inline int spu_reacquire_runnable
 	return 0;
 }
 
+/*
+ * SPU syscall restarting is tricky because we violate the basic
+ * assumption that the signal handler is running on the interrupted
+ * thread. Here instead, the handler runs on PowerPC user space code,
+ * while the syscall was called from the SPU.
+ * This means we can only do a very rough approximation of POSIX
+ * signal semantics.
+ */
+int spu_handle_restartsys(struct spu_context *ctx, long *spu_ret,
+			  unsigned int *npc)
+{
+	int ret;
+
+	switch (*spu_ret) {
+	case -ERESTARTSYS:
+	case -ERESTARTNOINTR:
+		/*
+		 * Enter the regular syscall restarting for
+		 * sys_spu_run, then restart the SPU syscall
+		 * callback.
+		 */
+		*npc -= 8;
+		ret = -ERESTARTSYS;
+		break;
+	case -ERESTARTNOHAND:
+	case -ERESTART_RESTARTBLOCK:
+		/*
+		 * Restart block is too hard for now, just return -EINTR
+		 * to the SPU.
+		 * ERESTARTNOHAND comes from sys_pause, we also return
+		 * -EINTR from there.
+		 * Assume that we need to be restarted ourselves though.
+		 */
+		*spu_ret = -EINTR;
+		ret = -ERESTARTSYS;
+		break;
+	default:
+		printk(KERN_WARNING "%s: unexpected return code %ld\n",
+			__FUNCTION__, *spu_ret);
+		ret = 0;
+	}
+	return ret;
+}
+
+int spu_process_callback(struct spu_context *ctx)
+{
+	struct spu_syscall_block s;
+	u32 ls_pointer, npc;
+	char *ls;
+	long spu_ret;
+	int ret;
+
+	/* get syscall block from local store */
+	npc = ctx->ops->npc_read(ctx);
+	ls = ctx->ops->get_ls(ctx);
+	ls_pointer = *(u32*)(ls + npc);
+	if (ls_pointer > (LS_SIZE - sizeof(s)))
+		return -EFAULT;
+	memcpy(&s, ls + ls_pointer, sizeof (s));
+
+	/* do actual syscall without pinning the spu */
+	ret = 0;
+	spu_ret = -ENOSYS;
+	npc += 4;
+
+	if (s.nr_ret < __NR_syscalls) {
+		spu_release(ctx);
+		/* do actual system call from here */
+		spu_ret = spu_sys_callback(&s);
+		if (spu_ret <= -ERESTARTSYS) {
+			ret = spu_handle_restartsys(ctx, &spu_ret, &npc);
+		}
+		spu_acquire(ctx);
+		if (ret == -ERESTARTSYS)
+			return ret;
+	}
+
+	/* write result, jump over indirect pointer */
+	memcpy(ls + ls_pointer, &spu_ret, sizeof (spu_ret));
+	ctx->ops->npc_write(ctx, npc);
+	ctx->ops->runcntl_write(ctx, SPU_RUNCNTL_RUNNABLE);
+	return ret;
+}
+
 static inline int spu_process_events(struct spu_context *ctx)
 {
 	struct spu *spu = ctx->spu;
@@ -107,6 +191,13 @@ long spufs_run_spu(struct file *file, st
 		ret = spufs_wait(ctx->stop_wq, spu_stopped(ctx, status));
 		if (unlikely(ret))
 			break;
+		if ((*status & SPU_STATUS_STOPPED_BY_STOP) &&
+		    (*status >> SPU_STOP_STATUS_SHIFT == 0x2104)) {
+			ret = spu_process_callback(ctx);
+			if (ret)
+				break;
+			*status &= ~SPU_STATUS_STOPPED_BY_STOP;
+		}
 		if (unlikely(ctx->state != SPU_STATE_RUNNABLE)) {
 			ret = spu_reacquire_runnable(ctx, npc, status);
 			if (ret)
Index: linux-2.6.16-rc/include/asm-powerpc/spu.h
===================================================================
--- linux-2.6.16-rc.orig/include/asm-powerpc/spu.h
+++ linux-2.6.16-rc/include/asm-powerpc/spu.h
@@ -149,6 +149,14 @@ int spu_irq_class_0_bottom(struct spu *s
 int spu_irq_class_1_bottom(struct spu *spu);
 void spu_irq_setaffinity(struct spu *spu, int cpu);
 
+/* system callbacks from the SPU */
+struct spu_syscall_block {
+	u64 nr_ret;
+	u64 parm[6];
+};
+extern long spu_sys_callback(struct spu_syscall_block *s);
+
+/* syscalls implemented in spufs */
 extern struct spufs_calls {
 	asmlinkage long (*create_thread)(const char __user *name,
 					unsigned int flags, mode_t mode);
@@ -399,7 +407,6 @@ struct spu_priv1 {
 #define SPU_GET_REVISION_BITS(vr)	(vr & SPU_REVISION_BITS)
 	u8  pad_0x28_0x100[0x100 - 0x28];			/* 0x28 */
 
-
 	/* Interrupt Area */
 	u64 int_mask_RW[3];					/* 0x100 */
 #define CLASS0_ENABLE_DMA_ALIGNMENT_INTR		0x1L
Index: linux-2.6.16-rc/arch/powerpc/platforms/cell/spu_callbacks.c
===================================================================
--- /dev/null
+++ linux-2.6.16-rc/arch/powerpc/platforms/cell/spu_callbacks.c
@@ -0,0 +1,345 @@
+/*
+ * System call callback functions for SPUs
+ */
+
+#define DEBUG
+
+#include <linux/kallsyms.h>
+#include <linux/module.h>
+#include <linux/syscalls.h>
+
+#include <asm/spu.h>
+#include <asm/syscalls.h>
+#include <asm/unistd.h>
+
+/*
+ * This table defines the system calls that an SPU can call.
+ * It is currently a subset of the 64 bit powerpc system calls,
+ * with the exact semantics.
+ *
+ * The reasons for disabling some of the system calls are:
+ * 1. They interact with the way SPU syscalls are handled
+ *    and we can't let them execute ever:
+ *	restart_syscall, exit, for, execve, ptrace, ...
+ * 2. They are deprecated and replaced by other means:
+ *	uselib, pciconfig_*, sysfs, ...
+ * 3. They are somewhat interacting with the system in a way
+ *    we don't want an SPU to:
+ *	reboot, init_module, mount, kexec_load
+ * 4. They are optional and we can't rely on them being
+ *    linked into the kernel. Unfortunately, the cond_syscall
+ *    helper does not work here as it does not add the necessary
+ *    opd symbols:
+ *	mbind, mq_open, ipc, ...
+ */
+
+void *spu_syscall_table[] = {
+	[__NR_restart_syscall]		sys_ni_syscall, /* sys_restart_syscall */
+	[__NR_exit]			sys_ni_syscall, /* sys_exit */
+	[__NR_fork]			sys_ni_syscall, /* ppc_fork */
+	[__NR_read]			sys_read,
+	[__NR_write]			sys_write,
+	[__NR_open]			sys_open,
+	[__NR_close]			sys_close,
+	[__NR_waitpid]			sys_waitpid,
+	[__NR_creat]			sys_creat,
+	[__NR_link]			sys_link,
+	[__NR_unlink]			sys_unlink,
+	[__NR_execve]			sys_ni_syscall, /* sys_execve */
+	[__NR_chdir]			sys_chdir,
+	[__NR_time]			sys_time,
+	[__NR_mknod]			sys_mknod,
+	[__NR_chmod]			sys_chmod,
+	[__NR_lchown]			sys_lchown,
+	[__NR_break]			sys_ni_syscall,
+	[__NR_oldstat]			sys_ni_syscall,
+	[__NR_lseek]			sys_lseek,
+	[__NR_getpid]			sys_getpid,
+	[__NR_mount]			sys_ni_syscall, /* sys_mount */
+	[__NR_umount]			sys_ni_syscall,
+	[__NR_setuid]			sys_setuid,
+	[__NR_getuid]			sys_getuid,
+	[__NR_stime]			sys_stime,
+	[__NR_ptrace]			sys_ni_syscall, /* sys_ptrace */
+	[__NR_alarm]			sys_alarm,
+	[__NR_oldfstat]			sys_ni_syscall,
+	[__NR_pause]			sys_ni_syscall, /* sys_pause */
+	[__NR_utime]			sys_ni_syscall, /* sys_utime */
+	[__NR_stty]			sys_ni_syscall,
+	[__NR_gtty]			sys_ni_syscall,
+	[__NR_access]			sys_access,
+	[__NR_nice]			sys_nice,
+	[__NR_ftime]			sys_ni_syscall,
+	[__NR_sync]			sys_sync,
+	[__NR_kill]			sys_kill,
+	[__NR_rename]			sys_rename,
+	[__NR_mkdir]			sys_mkdir,
+	[__NR_rmdir]			sys_rmdir,
+	[__NR_dup]			sys_dup,
+	[__NR_pipe]			sys_pipe,
+	[__NR_times]			sys_times,
+	[__NR_prof]			sys_ni_syscall,
+	[__NR_brk]			sys_brk,
+	[__NR_setgid]			sys_setgid,
+	[__NR_getgid]			sys_getgid,
+	[__NR_signal]			sys_ni_syscall, /* sys_signal */
+	[__NR_geteuid]			sys_geteuid,
+	[__NR_getegid]			sys_getegid,
+	[__NR_acct]			sys_ni_syscall, /* sys_acct */
+	[__NR_umount2]			sys_ni_syscall, /* sys_umount */
+	[__NR_lock]			sys_ni_syscall,
+	[__NR_ioctl]			sys_ioctl,
+	[__NR_fcntl]			sys_fcntl,
+	[__NR_mpx]			sys_ni_syscall,
+	[__NR_setpgid]			sys_setpgid,
+	[__NR_ulimit]			sys_ni_syscall,
+	[__NR_oldolduname]		sys_ni_syscall,
+	[__NR_umask]			sys_umask,
+	[__NR_chroot]			sys_chroot,
+	[__NR_ustat]			sys_ni_syscall, /* sys_ustat */
+	[__NR_dup2]			sys_dup2,
+	[__NR_getppid]			sys_getppid,
+	[__NR_getpgrp]			sys_getpgrp,
+	[__NR_setsid]			sys_setsid,
+	[__NR_sigaction]		sys_ni_syscall,
+	[__NR_sgetmask]			sys_sgetmask,
+	[__NR_ssetmask]			sys_ssetmask,
+	[__NR_setreuid]			sys_setreuid,
+	[__NR_setregid]			sys_setregid,
+	[__NR_sigsuspend]		sys_ni_syscall,
+	[__NR_sigpending]		sys_ni_syscall,
+	[__NR_sethostname]		sys_sethostname,
+	[__NR_setrlimit]		sys_setrlimit,
+	[__NR_getrlimit]		sys_ni_syscall,
+	[__NR_getrusage]		sys_getrusage,
+	[__NR_gettimeofday]		sys_gettimeofday,
+	[__NR_settimeofday]		sys_settimeofday,
+	[__NR_getgroups]		sys_getgroups,
+	[__NR_setgroups]		sys_setgroups,
+	[__NR_select]			sys_ni_syscall,
+	[__NR_symlink]			sys_symlink,
+	[__NR_oldlstat]			sys_ni_syscall,
+	[__NR_readlink]			sys_readlink,
+	[__NR_uselib]			sys_ni_syscall, /* sys_uselib */
+	[__NR_swapon]			sys_ni_syscall, /* sys_swapon */
+	[__NR_reboot]			sys_ni_syscall, /* sys_reboot */
+	[__NR_readdir]			sys_ni_syscall,
+	[__NR_mmap]			sys_mmap,
+	[__NR_munmap]			sys_munmap,
+	[__NR_truncate]			sys_truncate,
+	[__NR_ftruncate]		sys_ftruncate,
+	[__NR_fchmod]			sys_fchmod,
+	[__NR_fchown]			sys_fchown,
+	[__NR_getpriority]		sys_getpriority,
+	[__NR_setpriority]		sys_setpriority,
+	[__NR_profil]			sys_ni_syscall,
+	[__NR_statfs]			sys_ni_syscall, /* sys_statfs */
+	[__NR_fstatfs]			sys_ni_syscall, /* sys_fstatfs */
+	[__NR_ioperm]			sys_ni_syscall,
+	[__NR_socketcall]		sys_socketcall,
+	[__NR_syslog]			sys_syslog,
+	[__NR_setitimer]		sys_setitimer,
+	[__NR_getitimer]		sys_getitimer,
+	[__NR_stat]			sys_newstat,
+	[__NR_lstat]			sys_newlstat,
+	[__NR_fstat]			sys_newfstat,
+	[__NR_olduname]			sys_ni_syscall,
+	[__NR_iopl]			sys_ni_syscall,
+	[__NR_vhangup]			sys_vhangup,
+	[__NR_idle]			sys_ni_syscall,
+	[__NR_vm86]			sys_ni_syscall,
+	[__NR_wait4]			sys_wait4,
+	[__NR_swapoff]			sys_ni_syscall, /* sys_swapoff */
+	[__NR_sysinfo]			sys_sysinfo,
+	[__NR_ipc]			sys_ni_syscall, /* sys_ipc */
+	[__NR_fsync]			sys_fsync,
+	[__NR_sigreturn]		sys_ni_syscall,
+	[__NR_clone]			sys_ni_syscall, /* ppc_clone */
+	[__NR_setdomainname]		sys_setdomainname,
+	[__NR_uname]			ppc_newuname,
+	[__NR_modify_ldt]		sys_ni_syscall,
+	[__NR_adjtimex]			sys_adjtimex,
+	[__NR_mprotect]			sys_mprotect,
+	[__NR_sigprocmask]		sys_ni_syscall,
+	[__NR_create_module]		sys_ni_syscall,
+	[__NR_init_module]		sys_ni_syscall, /* sys_init_module */
+	[__NR_delete_module]		sys_ni_syscall, /* sys_delete_module */
+	[__NR_get_kernel_syms]		sys_ni_syscall,
+	[__NR_quotactl]			sys_ni_syscall, /* sys_quotactl */
+	[__NR_getpgid]			sys_getpgid,
+	[__NR_fchdir]			sys_fchdir,
+	[__NR_bdflush]			sys_bdflush,
+	[__NR_sysfs]			sys_ni_syscall, /* sys_sysfs */
+	[__NR_personality]		ppc64_personality,
+	[__NR_afs_syscall]		sys_ni_syscall,
+	[__NR_setfsuid]			sys_setfsuid,
+	[__NR_setfsgid]			sys_setfsgid,
+	[__NR__llseek]			sys_llseek,
+	[__NR_getdents]			sys_getdents,
+	[__NR__newselect]		sys_select,
+	[__NR_flock]			sys_flock,
+	[__NR_msync]			sys_msync,
+	[__NR_readv]			sys_readv,
+	[__NR_writev]			sys_writev,
+	[__NR_getsid]			sys_getsid,
+	[__NR_fdatasync]		sys_fdatasync,
+	[__NR__sysctl]			sys_ni_syscall, /* sys_sysctl */
+	[__NR_mlock]			sys_mlock,
+	[__NR_munlock]			sys_munlock,
+	[__NR_mlockall]			sys_mlockall,
+	[__NR_munlockall]		sys_munlockall,
+	[__NR_sched_setparam]		sys_sched_setparam,
+	[__NR_sched_getparam]		sys_sched_getparam,
+	[__NR_sched_setscheduler]	sys_sched_setscheduler,
+	[__NR_sched_getscheduler]	sys_sched_getscheduler,
+	[__NR_sched_yield]		sys_sched_yield,
+	[__NR_sched_get_priority_max]	sys_sched_get_priority_max,
+	[__NR_sched_get_priority_min]	sys_sched_get_priority_min,
+	[__NR_sched_rr_get_interval]	sys_sched_rr_get_interval,
+	[__NR_nanosleep]		sys_nanosleep,
+	[__NR_mremap]			sys_mremap,
+	[__NR_setresuid]		sys_setresuid,
+	[__NR_getresuid]		sys_getresuid,
+	[__NR_query_module]		sys_ni_syscall,
+	[__NR_poll]			sys_poll,
+	[__NR_nfsservctl]		sys_ni_syscall, /* sys_nfsservctl */
+	[__NR_setresgid]		sys_setresgid,
+	[__NR_getresgid]		sys_getresgid,
+	[__NR_prctl]			sys_prctl,
+	[__NR_rt_sigreturn]		sys_ni_syscall, /* ppc64_rt_sigreturn */
+	[__NR_rt_sigaction]		sys_ni_syscall, /* sys_rt_sigaction */
+	[__NR_rt_sigprocmask]		sys_ni_syscall, /* sys_rt_sigprocmask */
+	[__NR_rt_sigpending]		sys_ni_syscall, /* sys_rt_sigpending */
+	[__NR_rt_sigtimedwait]		sys_ni_syscall, /* sys_rt_sigtimedwait */
+	[__NR_rt_sigqueueinfo]		sys_ni_syscall, /* sys_rt_sigqueueinfo */
+	[__NR_rt_sigsuspend]		sys_ni_syscall, /* sys_rt_sigsuspend */
+	[__NR_pread64]			sys_pread64,
+	[__NR_pwrite64]			sys_pwrite64,
+	[__NR_chown]			sys_chown,
+	[__NR_getcwd]			sys_getcwd,
+	[__NR_capget]			sys_capget,
+	[__NR_capset]			sys_capset,
+	[__NR_sigaltstack]		sys_ni_syscall, /* sys_sigaltstack */
+	[__NR_sendfile]			sys_sendfile64,
+	[__NR_getpmsg]			sys_ni_syscall,
+	[__NR_putpmsg]			sys_ni_syscall,
+	[__NR_vfork]			sys_ni_syscall, /* ppc_vfork */
+	[__NR_ugetrlimit]		sys_getrlimit,
+	[__NR_readahead]		sys_readahead,
+	[192]				sys_ni_syscall,
+	[193]				sys_ni_syscall,
+	[194]				sys_ni_syscall,
+	[195]				sys_ni_syscall,
+	[196]				sys_ni_syscall,
+	[197]				sys_ni_syscall,
+	[__NR_pciconfig_read]		sys_ni_syscall, /* sys_pciconfig_read */
+	[__NR_pciconfig_write]		sys_ni_syscall, /* sys_pciconfig_write */
+	[__NR_pciconfig_iobase]		sys_ni_syscall, /* sys_pciconfig_iobase */
+	[__NR_multiplexer]		sys_ni_syscall,
+	[__NR_getdents64]		sys_getdents64,
+	[__NR_pivot_root]		sys_pivot_root,
+	[204]				sys_ni_syscall,
+	[__NR_madvise]			sys_madvise,
+	[__NR_mincore]			sys_mincore,
+	[__NR_gettid]			sys_gettid,
+	[__NR_tkill]			sys_tkill,
+	[__NR_setxattr]			sys_setxattr,
+	[__NR_lsetxattr]		sys_lsetxattr,
+	[__NR_fsetxattr]		sys_fsetxattr,
+	[__NR_getxattr]			sys_getxattr,
+	[__NR_lgetxattr]		sys_lgetxattr,
+	[__NR_fgetxattr]		sys_fgetxattr,
+	[__NR_listxattr]		sys_listxattr,
+	[__NR_llistxattr]		sys_llistxattr,
+	[__NR_flistxattr]		sys_flistxattr,
+	[__NR_removexattr]		sys_removexattr,
+	[__NR_lremovexattr]		sys_lremovexattr,
+	[__NR_fremovexattr]		sys_fremovexattr,
+	[__NR_futex]			sys_futex,
+	[__NR_sched_setaffinity]	sys_sched_setaffinity,
+	[__NR_sched_getaffinity]	sys_sched_getaffinity,
+	[__NR_tuxcall]			sys_ni_syscall,
+	[226]				sys_ni_syscall,
+	[__NR_io_setup]			sys_io_setup,
+	[__NR_io_destroy]		sys_io_destroy,
+	[__NR_io_getevents]		sys_io_getevents,
+	[__NR_io_submit]		sys_io_submit,
+	[__NR_io_cancel]		sys_io_cancel,
+	[__NR_set_tid_address]		sys_ni_syscall, /* sys_set_tid_address */
+	[__NR_fadvise64]		sys_fadvise64,
+	[__NR_exit_group]		sys_ni_syscall, /* sys_exit_group */
+	[__NR_lookup_dcookie]		sys_ni_syscall, /* sys_lookup_dcookie */
+	[__NR_epoll_create]		sys_epoll_create,
+	[__NR_epoll_ctl]		sys_epoll_ctl,
+	[__NR_epoll_wait]		sys_epoll_wait,
+	[__NR_remap_file_pages]		sys_remap_file_pages,
+	[__NR_timer_create]		sys_timer_create,
+	[__NR_timer_settime]		sys_timer_settime,
+	[__NR_timer_gettime]		sys_timer_gettime,
+	[__NR_timer_getoverrun]		sys_timer_getoverrun,
+	[__NR_timer_delete]		sys_timer_delete,
+	[__NR_clock_settime]		sys_clock_settime,
+	[__NR_clock_gettime]		sys_clock_gettime,
+	[__NR_clock_getres]		sys_clock_getres,
+	[__NR_clock_nanosleep]		sys_clock_nanosleep,
+	[__NR_swapcontext]		sys_ni_syscall, /* ppc64_swapcontext */
+	[__NR_tgkill]			sys_tgkill,
+	[__NR_utimes]			sys_utimes,
+	[__NR_statfs64]			sys_statfs64,
+	[__NR_fstatfs64]		sys_fstatfs64,
+	[254]				sys_ni_syscall,
+	[__NR_rtas]			ppc_rtas,
+	[256]				sys_ni_syscall,
+	[257]				sys_ni_syscall,
+	[258]				sys_ni_syscall,
+	[__NR_mbind]			sys_ni_syscall, /* sys_mbind */
+	[__NR_get_mempolicy]		sys_ni_syscall, /* sys_get_mempolicy */
+	[__NR_set_mempolicy]		sys_ni_syscall, /* sys_set_mempolicy */
+	[__NR_mq_open]			sys_ni_syscall, /* sys_mq_open */
+	[__NR_mq_unlink]		sys_ni_syscall, /* sys_mq_unlink */
+	[__NR_mq_timedsend]		sys_ni_syscall, /* sys_mq_timedsend */
+	[__NR_mq_timedreceive]		sys_ni_syscall, /* sys_mq_timedreceive */
+	[__NR_mq_notify]		sys_ni_syscall, /* sys_mq_notify */
+	[__NR_mq_getsetattr]		sys_ni_syscall, /* sys_mq_getsetattr */
+	[__NR_kexec_load]		sys_ni_syscall, /* sys_kexec_load */
+	[__NR_add_key]			sys_ni_syscall, /* sys_add_key */
+	[__NR_request_key]		sys_ni_syscall, /* sys_request_key */
+	[__NR_keyctl]			sys_ni_syscall, /* sys_keyctl */
+	[__NR_waitid]			sys_ni_syscall, /* sys_waitid */
+	[__NR_ioprio_set]		sys_ni_syscall, /* sys_ioprio_set */
+	[__NR_ioprio_get]		sys_ni_syscall, /* sys_ioprio_get */
+	[__NR_inotify_init]		sys_ni_syscall, /* sys_inotify_init */
+	[__NR_inotify_add_watch]	sys_ni_syscall, /* sys_inotify_add_watch */
+	[__NR_inotify_rm_watch]		sys_ni_syscall, /* sys_inotify_rm_watch */
+	[__NR_spu_run]			sys_ni_syscall, /* sys_spu_run */
+	[__NR_spu_create]		sys_ni_syscall, /* sys_spu_create */
+	[__NR_pselect6]			sys_ni_syscall, /* sys_pselect */
+	[__NR_ppoll]			sys_ni_syscall, /* sys_ppoll */
+	[__NR_unshare]			sys_unshare,
+};
+
+long spu_sys_callback(struct spu_syscall_block *s)
+{
+	long (*syscall)(u64 a1, u64 a2, u64 a3, u64 a4, u64 a5, u64 a6);
+
+	BUILD_BUG_ON(ARRAY_SIZE(spu_syscall_table) != __NR_syscalls);
+
+	syscall = spu_syscall_table[s->nr_ret];
+
+	if (s->nr_ret >= __NR_syscalls) {
+		pr_debug("%s: invalid syscall #%ld", __FUNCTION__, s->nr_ret);
+		return -ENOSYS;
+	}
+
+#ifdef DEBUG
+	print_symbol(KERN_DEBUG "SPU-syscall %s:", (unsigned long)syscall);
+	printk("syscall%ld(%lx, %lx, %lx, %lx, %lx, %lx)\n",
+			s->nr_ret,
+			s->parm[0], s->parm[1], s->parm[2],
+			s->parm[3], s->parm[4], s->parm[5]);
+#endif
+
+	return syscall(s->parm[0], s->parm[1], s->parm[2],
+		       s->parm[3], s->parm[4], s->parm[5]);
+}
+EXPORT_SYMBOL_GPL(spu_sys_callback);

--

[patch 10/13] add sys_unshare to syscalls.h

[Arnd Bergmann]

All architecture independent system calls should be declared
in syscalls.h, add the one that is missing.

To: Andrew Morton <akpm@osdl.org>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

---

This patch is not powerpc-specific in principle, the reason
for including it in my cell updates is that my next patch
depends on it.

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index d73501b..72de104 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -568,5 +568,6 @@ asmlinkage long compat_sys_newfstatat(un
 				      int flag);
 asmlinkage long compat_sys_openat(unsigned int dfd, const char __user *filename,
 				   int flags, int mode);
+asmlinkage long sys_unshare(unsigned long unshare_flags);
 
 #endif

--

[patch 11/13] spufs: implement mfc access for PPE-side DMA

[Arnd Bergmann]

This patch adds a new file called 'mfc' to each spufs directory.
The file accepts DMA commands that are a subset of what would
be legal DMA commands for problem state register access. Upon
reading the file, a bitmask is returned with the completed
tag groups set.

The file is meant to be used from an abstraction in libspe
that is added by a different patch.

>From the kernel perspective, this means a process can now
offload a memory copy from or into an SPE local store
without having to run code on the SPE itself.

The transfer will only be performed while the SPE is owned
by one thread that is waiting in the spu_run system call
and the data will be transferred into that thread's
address space, independent of which thread started the
transfer.

Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

Index: linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/file.c
===================================================================
--- linux-2.6.16-rc.orig/arch/powerpc/platforms/cell/spufs/file.c
+++ linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/file.c
@@ -20,6 +20,8 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#undef DEBUG
+
 #include <linux/fs.h>
 #include <linux/ioctl.h>
 #include <linux/module.h>
@@ -641,6 +643,297 @@ static u64 spufs_signal2_type_get(void *
 DEFINE_SIMPLE_ATTRIBUTE(spufs_signal2_type, spufs_signal2_type_get,
 					spufs_signal2_type_set, "%llu");
 
+
+static int spufs_mfc_open(struct inode *inode, struct file *file)
+{
+	struct spufs_inode_info *i = SPUFS_I(inode);
+	struct spu_context *ctx = i->i_ctx;
+
+	/* we don't want to deal with DMA into other processes */
+	if (ctx->owner != current->mm)
+		return -EINVAL;
+
+	if (atomic_read(&inode->i_count) != 1)
+		return -EBUSY;
+
+	file->private_data = ctx;
+	return nonseekable_open(inode, file);
+}
+
+/* interrupt-level mfc callback function. */
+void spufs_mfc_callback(struct spu *spu)
+{
+	struct spu_context *ctx = spu->ctx;
+
+	wake_up_all(&ctx->mfc_wq);
+
+	pr_debug("%s %s\n", __FUNCTION__, spu->name);
+	if (ctx->mfc_fasync) {
+		u32 free_elements, tagstatus;
+		unsigned int mask;
+
+		/* no need for spu_acquire in interrupt context */
+		free_elements = ctx->ops->get_mfc_free_elements(ctx);
+		tagstatus = ctx->ops->read_mfc_tagstatus(ctx);
+
+		mask = 0;
+		if (free_elements & 0xffff)
+			mask |= POLLOUT;
+		if (tagstatus & ctx->tagwait)
+			mask |= POLLIN;
+
+		kill_fasync(&ctx->mfc_fasync, SIGIO, mask);
+	}
+}
+
+static int spufs_read_mfc_tagstatus(struct spu_context *ctx, u32 *status)
+{
+	/* See if there is one tag group is complete */
+	/* FIXME we need locking around tagwait */
+	*status = ctx->ops->read_mfc_tagstatus(ctx) & ctx->tagwait;
+	ctx->tagwait &= ~*status;
+	if (*status)
+		return 1;
+
+	/* enable interrupt waiting for any tag group,
+	   may silently fail if interrupts are already enabled */
+	ctx->ops->set_mfc_query(ctx, ctx->tagwait, 1);
+	return 0;
+}
+
+static ssize_t spufs_mfc_read(struct file *file, char __user *buffer,
+			size_t size, loff_t *pos)
+{
+	struct spu_context *ctx = file->private_data;
+	int ret = -EINVAL;
+	u32 status;
+
+	if (size != 4)
+		goto out;
+
+	spu_acquire(ctx);
+	if (file->f_flags & O_NONBLOCK) {
+		status = ctx->ops->read_mfc_tagstatus(ctx);
+		if (!(status & ctx->tagwait))
+			ret = -EAGAIN;
+		else
+			ctx->tagwait &= ~status;
+	} else {
+		ret = spufs_wait(ctx->mfc_wq,
+			   spufs_read_mfc_tagstatus(ctx, &status));
+	}
+	spu_release(ctx);
+
+	if (ret)
+		goto out;
+
+	ret = 4;
+	if (copy_to_user(buffer, &status, 4))
+		ret = -EFAULT;
+
+out:
+	return ret;
+}
+
+static int spufs_check_valid_dma(struct mfc_dma_command *cmd)
+{
+	pr_debug("queueing DMA %x %lx %x %x %x\n", cmd->lsa,
+		 cmd->ea, cmd->size, cmd->tag, cmd->cmd);
+
+	switch (cmd->cmd) {
+	case MFC_PUT_CMD:
+	case MFC_PUTF_CMD:
+	case MFC_PUTB_CMD:
+	case MFC_GET_CMD:
+	case MFC_GETF_CMD:
+	case MFC_GETB_CMD:
+		break;
+	default:
+		pr_debug("invalid DMA opcode %x\n", cmd->cmd);
+		return -EIO;
+	}
+
+	if ((cmd->lsa & 0xf) != (cmd->ea &0xf)) {
+		pr_debug("invalid DMA alignment, ea %lx lsa %x\n",
+				cmd->ea, cmd->lsa);
+		return -EIO;
+	}
+
+	switch (cmd->size & 0xf) {
+	case 1:
+		break;
+	case 2:
+		if (cmd->lsa & 1)
+			goto error;
+		break;
+	case 4:
+		if (cmd->lsa & 3)
+			goto error;
+		break;
+	case 8:
+		if (cmd->lsa & 7)
+			goto error;
+		break;
+	case 0:
+		if (cmd->lsa & 15)
+			goto error;
+		break;
+	error:
+	default:
+		pr_debug("invalid DMA alignment %x for size %x\n",
+			cmd->lsa & 0xf, cmd->size);
+		return -EIO;
+	}
+
+	if (cmd->size > 16 * 1024) {
+		pr_debug("invalid DMA size %x\n", cmd->size);
+		return -EIO;
+	}
+
+	if (cmd->tag & 0xfff0) {
+		/* we reserve the higher tag numbers for kernel use */
+		pr_debug("invalid DMA tag\n");
+		return -EIO;
+	}
+
+	if (cmd->class) {
+		/* not supported in this version */
+		pr_debug("invalid DMA class\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int spu_send_mfc_command(struct spu_context *ctx,
+				struct mfc_dma_command cmd,
+				int *error)
+{
+	*error = ctx->ops->send_mfc_command(ctx, &cmd);
+	if (*error == -EAGAIN) {
+		/* wait for any tag group to complete
+		   so we have space for the new command */
+		ctx->ops->set_mfc_query(ctx, ctx->tagwait, 1);
+		/* try again, because the queue might be
+		   empty again */
+		*error = ctx->ops->send_mfc_command(ctx, &cmd);
+		if (*error == -EAGAIN)
+			return 0;
+	}
+	return 1;
+}
+
+static ssize_t spufs_mfc_write(struct file *file, const char __user *buffer,
+			size_t size, loff_t *pos)
+{
+	struct spu_context *ctx = file->private_data;
+	struct mfc_dma_command cmd;
+	int ret = -EINVAL;
+
+	if (size != sizeof cmd)
+		goto out;
+
+	ret = -EFAULT;
+	if (copy_from_user(&cmd, buffer, sizeof cmd))
+		goto out;
+
+	ret = spufs_check_valid_dma(&cmd);
+	if (ret)
+		goto out;
+
+	spu_acquire_runnable(ctx);
+	if (file->f_flags & O_NONBLOCK) {
+		ret = ctx->ops->send_mfc_command(ctx, &cmd);
+	} else {
+		int status;
+		ret = spufs_wait(ctx->mfc_wq,
+				 spu_send_mfc_command(ctx, cmd, &status));
+		if (status)
+			ret = status;
+	}
+	spu_release(ctx);
+
+	if (ret)
+		goto out;
+
+	ctx->tagwait |= 1 << cmd.tag;
+
+out:
+	return ret;
+}
+
+static unsigned int spufs_mfc_poll(struct file *file,poll_table *wait)
+{
+	struct spu_context *ctx = file->private_data;
+	u32 free_elements, tagstatus;
+	unsigned int mask;
+
+	spu_acquire(ctx);
+	ctx->ops->set_mfc_query(ctx, ctx->tagwait, 2);
+	free_elements = ctx->ops->get_mfc_free_elements(ctx);
+	tagstatus = ctx->ops->read_mfc_tagstatus(ctx);
+	spu_release(ctx);
+
+	poll_wait(file, &ctx->mfc_wq, wait);
+
+	mask = 0;
+	if (free_elements & 0xffff)
+		mask |= POLLOUT | POLLWRNORM;
+	if (tagstatus & ctx->tagwait)
+		mask |= POLLIN | POLLRDNORM;
+
+	pr_debug("%s: free %d tagstatus %d tagwait %d\n", __FUNCTION__,
+		free_elements, tagstatus, ctx->tagwait);
+
+	return mask;
+}
+
+static int spufs_mfc_flush(struct file *file)
+{
+	struct spu_context *ctx = file->private_data;
+	int ret;
+
+	spu_acquire(ctx);
+#if 0
+/* this currently hangs */
+	ret = spufs_wait(ctx->mfc_wq,
+			 ctx->ops->set_mfc_query(ctx, ctx->tagwait, 2));
+	if (ret)
+		goto out;
+	ret = spufs_wait(ctx->mfc_wq,
+			 ctx->ops->read_mfc_tagstatus(ctx) == ctx->tagwait);
+out:
+#else
+	ret = 0;
+#endif
+	spu_release(ctx);
+
+	return ret;
+}
+
+static int spufs_mfc_fsync(struct file *file, struct dentry *dentry,
+			   int datasync)
+{
+	return spufs_mfc_flush(file);
+}
+
+static int spufs_mfc_fasync(int fd, struct file *file, int on)
+{
+	struct spu_context *ctx = file->private_data;
+
+	return fasync_helper(fd, file, on, &ctx->mfc_fasync);
+}
+
+static struct file_operations spufs_mfc_fops = {
+	.open	 = spufs_mfc_open,
+	.read	 = spufs_mfc_read,
+	.write	 = spufs_mfc_write,
+	.poll	 = spufs_mfc_poll,
+	.flush	 = spufs_mfc_flush,
+	.fsync	 = spufs_mfc_fsync,
+	.fasync	 = spufs_mfc_fasync,
+};
+
 static void spufs_npc_set(void *data, u64 val)
 {
 	struct spu_context *ctx = data;
@@ -783,6 +1076,7 @@ struct tree_descr spufs_dir_contents[] =
 	{ "signal2", &spufs_signal2_fops, 0666, },
 	{ "signal1_type", &spufs_signal1_type, 0666, },
 	{ "signal2_type", &spufs_signal2_type, 0666, },
+	{ "mfc", &spufs_mfc_fops, 0666, },
 	{ "npc", &spufs_npc_ops, 0666, },
 	{ "fpcr", &spufs_fpcr_fops, 0666, },
 	{ "decr", &spufs_decr_ops, 0666, },
Index: linux-2.6.16-rc/arch/powerpc/platforms/cell/spu_base.c
===================================================================
--- linux-2.6.16-rc.orig/arch/powerpc/platforms/cell/spu_base.c
+++ linux-2.6.16-rc/arch/powerpc/platforms/cell/spu_base.c
@@ -111,7 +111,7 @@ static int __spu_trap_data_seg(struct sp
 extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap); //XXX
 static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
 {
-	pr_debug("%s\n", __FUNCTION__);
+	pr_debug("%s, %lx, %lx\n", __FUNCTION__, dsisr, ea);
 
 	/* Handle kernel space hash faults immediately.
 	   User hash faults need to be deferred to process context. */
@@ -168,7 +168,7 @@ static int __spu_trap_halt(struct spu *s
 static int __spu_trap_tag_group(struct spu *spu)
 {
 	pr_debug("%s\n", __FUNCTION__);
-	/* wake_up(&spu->dma_wq); */
+	spu->mfc_callback(spu);
 	return 0;
 }
 
@@ -242,6 +242,8 @@ spu_irq_class_1(int irq, void *data, str
 		spu_mfc_dsisr_set(spu, 0ul);
 	spu_int_stat_clear(spu, 1, stat);
 	spin_unlock(&spu->register_lock);
+	pr_debug("%s: %lx %lx %lx %lx\n", __FUNCTION__, mask, stat,
+			dar, dsisr);
 
 	if (stat & 1) /* segment fault */
 		__spu_trap_data_seg(spu, dar);
@@ -632,6 +634,7 @@ static int __init create_spu(struct devi
 	spu->ibox_callback = NULL;
 	spu->wbox_callback = NULL;
 	spu->stop_callback = NULL;
+	spu->mfc_callback = NULL;
 
 	down(&spu_mutex);
 	spu->number = number++;
Index: linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/backing_ops.c
===================================================================
--- linux-2.6.16-rc.orig/arch/powerpc/platforms/cell/spufs/backing_ops.c
+++ linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/backing_ops.c
@@ -285,6 +285,49 @@ static void spu_backing_runcntl_stop(str
 	spu_backing_runcntl_write(ctx, SPU_RUNCNTL_STOP);
 }
 
+static int spu_backing_set_mfc_query(struct spu_context * ctx, u32 mask,
+					u32 mode)
+{
+	struct spu_problem_collapsed *prob = &ctx->csa.prob;
+	int ret;
+
+	spin_lock(&ctx->csa.register_lock);
+	ret = -EAGAIN;
+	if (prob->dma_querytype_RW)
+		goto out;
+	ret = 0;
+	/* FIXME: what are the side-effects of this? */
+	prob->dma_querymask_RW = mask;
+	prob->dma_querytype_RW = mode;
+out:
+	spin_unlock(&ctx->csa.register_lock);
+
+	return ret;
+}
+
+static u32 spu_backing_read_mfc_tagstatus(struct spu_context * ctx)
+{
+	return ctx->csa.prob.dma_tagstatus_R;
+}
+
+static u32 spu_backing_get_mfc_free_elements(struct spu_context *ctx)
+{
+	return ctx->csa.prob.dma_qstatus_R;
+}
+
+static int spu_backing_send_mfc_command(struct spu_context *ctx,
+					struct mfc_dma_command *cmd)
+{
+	int ret;
+
+	spin_lock(&ctx->csa.register_lock);
+	ret = -EAGAIN;
+	/* FIXME: set up priv2->puq */
+	spin_unlock(&ctx->csa.register_lock);
+
+	return ret;
+}
+
 struct spu_context_ops spu_backing_ops = {
 	.mbox_read = spu_backing_mbox_read,
 	.mbox_stat_read = spu_backing_mbox_stat_read,
@@ -305,4 +348,8 @@ struct spu_context_ops spu_backing_ops =
 	.get_ls = spu_backing_get_ls,
 	.runcntl_write = spu_backing_runcntl_write,
 	.runcntl_stop = spu_backing_runcntl_stop,
+	.set_mfc_query = spu_backing_set_mfc_query,
+	.read_mfc_tagstatus = spu_backing_read_mfc_tagstatus,
+	.get_mfc_free_elements = spu_backing_get_mfc_free_elements,
+	.send_mfc_command = spu_backing_send_mfc_command,
 };
Index: linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/hw_ops.c
===================================================================
--- linux-2.6.16-rc.orig/arch/powerpc/platforms/cell/spufs/hw_ops.c
+++ linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/hw_ops.c
@@ -232,6 +232,59 @@ static void spu_hw_runcntl_stop(struct s
 	spin_unlock_irq(&ctx->spu->register_lock);
 }
 
+static int spu_hw_set_mfc_query(struct spu_context * ctx, u32 mask, u32 mode)
+{
+	struct spu_problem *prob = ctx->spu->problem;
+	int ret;
+
+	spin_lock_irq(&ctx->spu->register_lock);
+	ret = -EAGAIN;
+	if (in_be32(&prob->dma_querytype_RW))
+		goto out;
+	ret = 0;
+	out_be32(&prob->dma_querymask_RW, mask);
+	out_be32(&prob->dma_querytype_RW, mode);
+out:
+	spin_unlock_irq(&ctx->spu->register_lock);
+	return ret;
+}
+
+static u32 spu_hw_read_mfc_tagstatus(struct spu_context * ctx)
+{
+	return in_be32(&ctx->spu->problem->dma_tagstatus_R);
+}
+
+static u32 spu_hw_get_mfc_free_elements(struct spu_context *ctx)
+{
+	return in_be32(&ctx->spu->problem->dma_qstatus_R);
+}
+
+static int spu_hw_send_mfc_command(struct spu_context *ctx,
+					struct mfc_dma_command *cmd)
+{
+	u32 status;
+	struct spu_problem *prob = ctx->spu->problem;
+
+	spin_lock_irq(&ctx->spu->register_lock);
+	out_be32(&prob->mfc_lsa_W, cmd->lsa);
+	out_be64(&prob->mfc_ea_W, cmd->ea);
+	out_be32(&prob->mfc_union_W.by32.mfc_size_tag32,
+				cmd->size << 16 | cmd->tag);
+	out_be32(&prob->mfc_union_W.by32.mfc_class_cmd32,
+				cmd->class << 16 | cmd->cmd);
+	status = in_be32(&prob->mfc_union_W.by32.mfc_class_cmd32);
+	spin_unlock_irq(&ctx->spu->register_lock);
+
+	switch (status & 0xffff) {
+	case 0:
+		return 0;
+	case 2:
+		return -EAGAIN;
+	default:
+		return -EINVAL;
+	}
+}
+
 struct spu_context_ops spu_hw_ops = {
 	.mbox_read = spu_hw_mbox_read,
 	.mbox_stat_read = spu_hw_mbox_stat_read,
@@ -252,4 +305,8 @@ struct spu_context_ops spu_hw_ops = {
 	.get_ls = spu_hw_get_ls,
 	.runcntl_write = spu_hw_runcntl_write,
 	.runcntl_stop = spu_hw_runcntl_stop,
+	.set_mfc_query = spu_hw_set_mfc_query,
+	.read_mfc_tagstatus = spu_hw_read_mfc_tagstatus,
+	.get_mfc_free_elements = spu_hw_get_mfc_free_elements,
+	.send_mfc_command = spu_hw_send_mfc_command,
 };
Index: linux-2.6.16-rc/include/asm-powerpc/spu.h
===================================================================
--- linux-2.6.16-rc.orig/include/asm-powerpc/spu.h
+++ linux-2.6.16-rc/include/asm-powerpc/spu.h
@@ -137,6 +137,7 @@ struct spu {
 	void (* wbox_callback)(struct spu *spu);
 	void (* ibox_callback)(struct spu *spu);
 	void (* stop_callback)(struct spu *spu);
+	void (* mfc_callback)(struct spu *spu);
 
 	char irq_c0[8];
 	char irq_c1[8];
Index: linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/context.c
===================================================================
--- linux-2.6.16-rc.orig/arch/powerpc/platforms/cell/spufs/context.c
+++ linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/context.c
@@ -47,8 +47,11 @@ struct spu_context *alloc_spu_context(st
 	init_waitqueue_head(&ctx->ibox_wq);
 	init_waitqueue_head(&ctx->wbox_wq);
 	init_waitqueue_head(&ctx->stop_wq);
+	init_waitqueue_head(&ctx->mfc_wq);
 	ctx->ibox_fasync = NULL;
 	ctx->wbox_fasync = NULL;
+	ctx->mfc_fasync = NULL;
+	ctx->tagwait = 0;
 	ctx->state = SPU_STATE_SAVED;
 	ctx->local_store = local_store;
 	ctx->spu = NULL;
@@ -68,8 +71,6 @@ void destroy_spu_context(struct kref *kr
 	ctx = container_of(kref, struct spu_context, kref);
 	down_write(&ctx->state_sema);
 	spu_deactivate(ctx);
-	ctx->ibox_fasync = NULL;
-	ctx->wbox_fasync = NULL;
 	up_write(&ctx->state_sema);
 	spu_fini_csa(&ctx->csa);
 	kfree(ctx);
Index: linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/sched.c
===================================================================
--- linux-2.6.16-rc.orig/arch/powerpc/platforms/cell/spufs/sched.c
+++ linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/sched.c
@@ -180,6 +180,7 @@ static inline void bind_context(struct s
 	spu->ibox_callback = spufs_ibox_callback;
 	spu->wbox_callback = spufs_wbox_callback;
 	spu->stop_callback = spufs_stop_callback;
+	spu->mfc_callback = spufs_mfc_callback;
 	mb();
 	spu_unmap_mappings(ctx);
 	spu_restore(&ctx->csa, spu);
@@ -197,6 +198,7 @@ static inline void unbind_context(struct
 	spu->ibox_callback = NULL;
 	spu->wbox_callback = NULL;
 	spu->stop_callback = NULL;
+	spu->mfc_callback = NULL;
 	spu->mm = NULL;
 	spu->pid = 0;
 	spu->prio = MAX_PRIO;
Index: linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/spufs.h
===================================================================
--- linux-2.6.16-rc.orig/arch/powerpc/platforms/cell/spufs/spufs.h
+++ linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -55,13 +55,27 @@ struct spu_context {
 	wait_queue_head_t ibox_wq;
 	wait_queue_head_t wbox_wq;
 	wait_queue_head_t stop_wq;
+	wait_queue_head_t mfc_wq;
 	struct fasync_struct *ibox_fasync;
 	struct fasync_struct *wbox_fasync;
+	struct fasync_struct *mfc_fasync;
+	u32 tagwait;
 	struct spu_context_ops *ops;
 	struct work_struct reap_work;
 	u64 flags;
 };
 
+struct mfc_dma_command {
+	int32_t pad;	/* reserved */
+	uint32_t lsa;	/* local storage address */
+	uint64_t ea;	/* effective address */
+	uint16_t size;	/* transfer size */
+	uint16_t tag;	/* command tag */
+	uint16_t class;	/* class ID */
+	uint16_t cmd;	/* command opcode */
+};
+
+
 /* SPU context query/set operations. */
 struct spu_context_ops {
 	int (*mbox_read) (struct spu_context * ctx, u32 * data);
@@ -84,6 +98,11 @@ struct spu_context_ops {
 	char*(*get_ls) (struct spu_context * ctx);
 	void (*runcntl_write) (struct spu_context * ctx, u32 data);
 	void (*runcntl_stop) (struct spu_context * ctx);
+	int (*set_mfc_query)(struct spu_context * ctx, u32 mask, u32 mode);
+	u32 (*read_mfc_tagstatus)(struct spu_context * ctx);
+	u32 (*get_mfc_free_elements)(struct spu_context *ctx);
+	int (*send_mfc_command)(struct spu_context *ctx,
+					struct mfc_dma_command *cmd);
 };
 
 extern struct spu_context_ops spu_hw_ops;
@@ -159,5 +178,6 @@ size_t spu_ibox_read(struct spu_context 
 void spufs_ibox_callback(struct spu *spu);
 void spufs_wbox_callback(struct spu *spu);
 void spufs_stop_callback(struct spu *spu);
+void spufs_mfc_callback(struct spu *spu);
 
 #endif
Index: linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/switch.c
===================================================================
--- linux-2.6.16-rc.orig/arch/powerpc/platforms/cell/spufs/switch.c
+++ linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/switch.c
@@ -2145,7 +2145,8 @@ static void init_priv1(struct spu_state 
 	csa->priv1.int_mask_class1_RW = CLASS1_ENABLE_SEGMENT_FAULT_INTR |
 	    CLASS1_ENABLE_STORAGE_FAULT_INTR;
 	csa->priv1.int_mask_class2_RW = CLASS2_ENABLE_SPU_STOP_INTR |
-	    CLASS2_ENABLE_SPU_HALT_INTR;
+	    CLASS2_ENABLE_SPU_HALT_INTR |
+	    CLASS2_ENABLE_SPU_DMA_TAG_GROUP_COMPLETE_INTR;
 }
 
 static void init_priv2(struct spu_state *csa)

--

[patch 12/13] spufs: enable SPE problem state MMIO access.

[Arnd Bergmann]

This patch is layered on top of CONFIG_SPARSEMEM
and is patterned after direct mapping of LS.

This patch allows mmap() of the following regions: 
"mfc", which represents the area from [0x3000 - 0x3fff]; 
"cntl", which represents the area from [0x4000 - 0x4fff]; 
"signal1" which begins at offset 0x14000; "signal2" which 
begins at offset 0x1c000.

The signal1 & signal2 files may be mmap()'d by regular user 
processes.  The cntl and mfc file, on the other hand, may
only be accessed if the owning process has CAP_SYS_RAWIO,
because they have the potential to confuse the kernel
with regard to parallel access to the same files with
regular file operations: the kernel always holds a spinlock
when accessing registers in these areas to serialize them,
which can not be guaranteed with user mmaps,

From: Mark Nutter <mnutter@us.ibm.com>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

Index: linus-2.6/arch/powerpc/platforms/cell/spu_base.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/spu_base.c
+++ linus-2.6/arch/powerpc/platforms/cell/spu_base.c
@@ -570,6 +570,11 @@ static int __init spu_map_device(struct 
 	if (!spu->local_store)
 		goto out;
 
+	prop = get_property(spe, "problem", NULL);
+	if (!prop)
+		goto out_unmap;
+	spu->problem_phys = *(unsigned long *)prop;
+
 	spu->problem= map_spe_prop(spe, "problem");
 	if (!spu->problem)
 		goto out_unmap;
Index: linus-2.6/arch/powerpc/platforms/cell/spufs/context.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/spufs/context.c
+++ linus-2.6/arch/powerpc/platforms/cell/spufs/context.c
@@ -27,7 +27,7 @@
 #include <asm/spu_csa.h>
 #include "spufs.h"
 
-struct spu_context *alloc_spu_context(struct address_space *local_store)
+struct spu_context *alloc_spu_context(void)
 {
 	struct spu_context *ctx;
 	ctx = kmalloc(sizeof *ctx, GFP_KERNEL);
@@ -53,7 +53,10 @@ struct spu_context *alloc_spu_context(st
 	ctx->mfc_fasync = NULL;
 	ctx->tagwait = 0;
 	ctx->state = SPU_STATE_SAVED;
-	ctx->local_store = local_store;
+	ctx->local_store = NULL;
+	ctx->cntl = NULL;
+	ctx->signal1 = NULL;
+	ctx->signal2 = NULL;
 	ctx->spu = NULL;
 	ctx->ops = &spu_backing_ops;
 	ctx->owner = get_task_mm(current);
@@ -110,7 +113,16 @@ void spu_release(struct spu_context *ctx
 
 void spu_unmap_mappings(struct spu_context *ctx)
 {
-	unmap_mapping_range(ctx->local_store, 0, LS_SIZE, 1);
+	if (ctx->local_store)
+		unmap_mapping_range(ctx->local_store, 0, LS_SIZE, 1);
+	if (ctx->mfc)
+		unmap_mapping_range(ctx->mfc, 0, 0x4000, 1);
+	if (ctx->cntl)
+		unmap_mapping_range(ctx->cntl, 0, 0x4000, 1);
+	if (ctx->signal1)
+		unmap_mapping_range(ctx->signal1, 0, 0x4000, 1);
+	if (ctx->signal2)
+		unmap_mapping_range(ctx->signal2, 0, 0x4000, 1);
 }
 
 int spu_acquire_runnable(struct spu_context *ctx)
Index: linus-2.6/arch/powerpc/platforms/cell/spufs/file.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/spufs/file.c
+++ linus-2.6/arch/powerpc/platforms/cell/spufs/file.c
@@ -41,8 +41,10 @@ static int
 spufs_mem_open(struct inode *inode, struct file *file)
 {
 	struct spufs_inode_info *i = SPUFS_I(inode);
-	file->private_data = i->i_ctx;
-	file->f_mapping = i->i_ctx->local_store;
+	struct spu_context *ctx = i->i_ctx;
+	file->private_data = ctx;
+	file->f_mapping = inode->i_mapping;
+	ctx->local_store = inode->i_mapping;
 	return 0;
 }
 
@@ -86,7 +88,7 @@ spufs_mem_write(struct file *file, const
 	return ret;
 }
 
-#ifdef CONFIG_SPARSEMEM
+#ifdef CONFIG_SPUFS_MMAP
 static struct page *
 spufs_mem_mmap_nopage(struct vm_area_struct *vma,
 		      unsigned long address, int *type)
@@ -138,11 +140,113 @@ static struct file_operations spufs_mem_
 	.read    = spufs_mem_read,
 	.write   = spufs_mem_write,
 	.llseek  = generic_file_llseek,
-#ifdef CONFIG_SPARSEMEM
+#ifdef CONFIG_SPUFS_MMAP
 	.mmap    = spufs_mem_mmap,
 #endif
 };
 
+#ifdef CONFIG_SPUFS_MMAP
+static struct page *spufs_ps_nopage(struct vm_area_struct *vma,
+				    unsigned long address,
+				    int *type, unsigned long ps_offs)
+{
+	struct page *page = NOPAGE_SIGBUS;
+	int fault_type = VM_FAULT_SIGBUS;
+	struct spu_context *ctx = vma->vm_file->private_data;
+	unsigned long offset = address - vma->vm_start;
+	unsigned long area;
+	int ret;
+
+	offset += vma->vm_pgoff << PAGE_SHIFT;
+	if (offset >= 0x4000)
+		goto out;
+
+	ret = spu_acquire_runnable(ctx);
+	if (ret)
+		goto out;
+
+	area = ctx->spu->problem_phys + ps_offs;
+	page = pfn_to_page((area + offset) >> PAGE_SHIFT);
+	fault_type = VM_FAULT_MINOR;
+	page_cache_get(page);
+
+	spu_release(ctx);
+
+      out:
+	if (type)
+		*type = fault_type;
+
+	return page;
+}
+
+static struct page *spufs_cntl_mmap_nopage(struct vm_area_struct *vma,
+					   unsigned long address, int *type)
+{
+	return spufs_ps_nopage(vma, address, type, 0x4000);
+}
+
+static struct vm_operations_struct spufs_cntl_mmap_vmops = {
+	.nopage = spufs_cntl_mmap_nopage,
+};
+
+/*
+ * mmap support for problem state control area [0x4000 - 0x4fff].
+ * Mapping this area requires that the application have CAP_SYS_RAWIO,
+ * as these registers require special care when read/writing.
+ */
+static int spufs_cntl_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	vma->vm_flags |= VM_RESERVED;
+	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
+				     | _PAGE_NO_CACHE);
+
+	vma->vm_ops = &spufs_cntl_mmap_vmops;
+	return 0;
+}
+#endif
+
+static int spufs_cntl_open(struct inode *inode, struct file *file)
+{
+	struct spufs_inode_info *i = SPUFS_I(inode);
+	struct spu_context *ctx = i->i_ctx;
+
+	file->private_data = ctx;
+	file->f_mapping = inode->i_mapping;
+	ctx->cntl = inode->i_mapping;
+	return 0;
+}
+
+static ssize_t
+spufs_cntl_read(struct file *file, char __user *buffer,
+		size_t size, loff_t *pos)
+{
+	/* FIXME: read from spu status */
+	return -EINVAL;
+}
+
+static ssize_t
+spufs_cntl_write(struct file *file, const char __user *buffer,
+		 size_t size, loff_t *pos)
+{
+	/* FIXME: write to runctl bit */
+	return -EINVAL;
+}
+
+static struct file_operations spufs_cntl_fops = {
+	.open = spufs_cntl_open,
+	.read = spufs_cntl_read,
+	.write = spufs_cntl_write,
+#ifdef CONFIG_SPUFS_MMAP
+	.mmap = spufs_cntl_mmap,
+#endif
+};
+
 static int
 spufs_regs_open(struct inode *inode, struct file *file)
 {
@@ -503,6 +607,16 @@ static struct file_operations spufs_wbox
 	.read	= spufs_wbox_stat_read,
 };
 
+static int spufs_signal1_open(struct inode *inode, struct file *file)
+{
+	struct spufs_inode_info *i = SPUFS_I(inode);
+	struct spu_context *ctx = i->i_ctx;
+	file->private_data = ctx;
+	file->f_mapping = inode->i_mapping;
+	ctx->signal1 = inode->i_mapping;
+	return nonseekable_open(inode, file);
+}
+
 static ssize_t spufs_signal1_read(struct file *file, char __user *buf,
 			size_t len, loff_t *pos)
 {
@@ -543,12 +657,50 @@ static ssize_t spufs_signal1_write(struc
 	return 4;
 }
 
+#ifdef CONFIG_SPUFS_MMAP
+static struct page *spufs_signal1_mmap_nopage(struct vm_area_struct *vma,
+					      unsigned long address, int *type)
+{
+	return spufs_ps_nopage(vma, address, type, 0x14000);
+}
+
+static struct vm_operations_struct spufs_signal1_mmap_vmops = {
+	.nopage = spufs_signal1_mmap_nopage,
+};
+
+static int spufs_signal1_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	vma->vm_flags |= VM_RESERVED;
+	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
+				     | _PAGE_NO_CACHE);
+
+	vma->vm_ops = &spufs_signal1_mmap_vmops;
+	return 0;
+}
+#endif
+
 static struct file_operations spufs_signal1_fops = {
-	.open = spufs_pipe_open,
+	.open = spufs_signal1_open,
 	.read = spufs_signal1_read,
 	.write = spufs_signal1_write,
+#ifdef CONFIG_SPUFS_MMAP
+	.mmap = spufs_signal1_mmap,
+#endif
 };
 
+static int spufs_signal2_open(struct inode *inode, struct file *file)
+{
+	struct spufs_inode_info *i = SPUFS_I(inode);
+	struct spu_context *ctx = i->i_ctx;
+	file->private_data = ctx;
+	file->f_mapping = inode->i_mapping;
+	ctx->signal2 = inode->i_mapping;
+	return nonseekable_open(inode, file);
+}
+
 static ssize_t spufs_signal2_read(struct file *file, char __user *buf,
 			size_t len, loff_t *pos)
 {
@@ -591,10 +743,39 @@ static ssize_t spufs_signal2_write(struc
 	return 4;
 }
 
+#ifdef CONFIG_SPUFS_MMAP
+static struct page *spufs_signal2_mmap_nopage(struct vm_area_struct *vma,
+					      unsigned long address, int *type)
+{
+	return spufs_ps_nopage(vma, address, type, 0x1c000);
+}
+
+static struct vm_operations_struct spufs_signal2_mmap_vmops = {
+	.nopage = spufs_signal2_mmap_nopage,
+};
+
+static int spufs_signal2_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	/* FIXME: */
+	vma->vm_flags |= VM_RESERVED;
+	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
+				     | _PAGE_NO_CACHE);
+
+	vma->vm_ops = &spufs_signal2_mmap_vmops;
+	return 0;
+}
+#endif
+
 static struct file_operations spufs_signal2_fops = {
-	.open = spufs_pipe_open,
+	.open = spufs_signal2_open,
 	.read = spufs_signal2_read,
 	.write = spufs_signal2_write,
+#ifdef CONFIG_SPUFS_MMAP
+	.mmap = spufs_signal2_mmap,
+#endif
 };
 
 static void spufs_signal1_type_set(void *data, u64 val)
@@ -643,6 +824,38 @@ static u64 spufs_signal2_type_get(void *
 DEFINE_SIMPLE_ATTRIBUTE(spufs_signal2_type, spufs_signal2_type_get,
 					spufs_signal2_type_set, "%llu");
 
+#ifdef CONFIG_SPUFS_MMAP
+static struct page *spufs_mfc_mmap_nopage(struct vm_area_struct *vma,
+					   unsigned long address, int *type)
+{
+	return spufs_ps_nopage(vma, address, type, 0x3000);
+}
+
+static struct vm_operations_struct spufs_mfc_mmap_vmops = {
+	.nopage = spufs_mfc_mmap_nopage,
+};
+
+/*
+ * mmap support for problem state MFC DMA area [0x0000 - 0x0fff].
+ * Mapping this area requires that the application have CAP_SYS_RAWIO,
+ * as these registers require special care when read/writing.
+ */
+static int spufs_mfc_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	vma->vm_flags |= VM_RESERVED;
+	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
+				     | _PAGE_NO_CACHE);
+
+	vma->vm_ops = &spufs_mfc_mmap_vmops;
+	return 0;
+}
+#endif
 
 static int spufs_mfc_open(struct inode *inode, struct file *file)
 {
@@ -932,6 +1145,9 @@ static struct file_operations spufs_mfc_
 	.flush	 = spufs_mfc_flush,
 	.fsync	 = spufs_mfc_fsync,
 	.fasync	 = spufs_mfc_fasync,
+#ifdef CONFIG_SPUFS_MMAP
+	.mmap	 = spufs_mfc_mmap,
+#endif
 };
 
 static void spufs_npc_set(void *data, u64 val)
@@ -1077,6 +1293,7 @@ struct tree_descr spufs_dir_contents[] =
 	{ "signal1_type", &spufs_signal1_type, 0666, },
 	{ "signal2_type", &spufs_signal2_type, 0666, },
 	{ "mfc", &spufs_mfc_fops, 0666, },
+	{ "cntl", &spufs_cntl_fops,  0666, },
 	{ "npc", &spufs_npc_ops, 0666, },
 	{ "fpcr", &spufs_fpcr_fops, 0666, },
 	{ "decr", &spufs_decr_ops, 0666, },
Index: linus-2.6/arch/powerpc/platforms/cell/spufs/inode.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/spufs/inode.c
+++ linus-2.6/arch/powerpc/platforms/cell/spufs/inode.c
@@ -241,7 +241,7 @@ spufs_mkdir(struct inode *dir, struct de
 		inode->i_gid = dir->i_gid;
 		inode->i_mode &= S_ISGID;
 	}
-	ctx = alloc_spu_context(inode->i_mapping);
+	ctx = alloc_spu_context();
 	SPUFS_I(inode)->i_ctx = ctx;
 	if (!ctx)
 		goto out_iput;
Index: linus-2.6/arch/powerpc/platforms/cell/spufs/spufs.h
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/spufs/spufs.h
+++ linus-2.6/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -43,7 +43,11 @@ struct spu_context {
 	struct spu *spu;		  /* pointer to a physical SPU */
 	struct spu_state csa;		  /* SPU context save area. */
 	spinlock_t mmio_lock;		  /* protects mmio access */
-	struct address_space *local_store;/* local store backing store */
+	struct address_space *local_store; /* local store mapping.  */
+	struct address_space *mfc;	   /* 'mfc' area mappings. */
+	struct address_space *cntl; 	   /* 'control' area mappings. */
+	struct address_space *signal1; 	   /* 'signal1' area mappings. */
+	struct address_space *signal2; 	   /* 'signal2' area mappings. */
 
 	enum { SPU_STATE_RUNNABLE, SPU_STATE_SAVED } state;
 	struct rw_semaphore state_sema;
@@ -125,7 +129,7 @@ long spufs_create_thread(struct nameidat
 extern struct file_operations spufs_context_fops;
 
 /* context management */
-struct spu_context * alloc_spu_context(struct address_space *local_store);
+struct spu_context * alloc_spu_context(void);
 void destroy_spu_context(struct kref *kref);
 struct spu_context * get_spu_context(struct spu_context *ctx);
 int put_spu_context(struct spu_context *ctx);
Index: linus-2.6/include/asm-powerpc/spu.h
===================================================================
--- linus-2.6.orig/include/asm-powerpc/spu.h
+++ linus-2.6/include/asm-powerpc/spu.h
@@ -110,6 +110,7 @@ struct spu {
 	char *name;
 	unsigned long local_store_phys;
 	u8 *local_store;
+	unsigned long problem_phys;
 	struct spu_problem __iomem *problem;
 	struct spu_priv1 __iomem *priv1;
 	struct spu_priv2 __iomem *priv2;
Index: linus-2.6/arch/powerpc/platforms/cell/Kconfig
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/Kconfig
+++ linus-2.6/arch/powerpc/platforms/cell/Kconfig
@@ -10,4 +10,9 @@ config SPU_FS
 	  Units on machines implementing the Broadband Processor
 	  Architecture.
 
+config SPUFS_MMAP
+	bool
+	depends on SPU_FS && SPARSEMEM && !PPC_64K_PAGES
+	default y
+
 endmenu

--

[patch 13/13] spufs: initialize context correctly

[Arnd Bergmann]

the mfc member of a new context was not initialized to zero,
which potentially leads to wild memory accesses.

From: Dirk Herrendoerfer <herrendo@de.ibm.com>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

Index: linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/context.c
===================================================================
--- linux-2.6.16-rc.orig/arch/powerpc/platforms/cell/spufs/context.c
+++ linux-2.6.16-rc/arch/powerpc/platforms/cell/spufs/context.c
@@ -51,6 +51,7 @@ struct spu_context *alloc_spu_context(vo
 	ctx->ibox_fasync = NULL;
 	ctx->wbox_fasync = NULL;
 	ctx->mfc_fasync = NULL;
+	ctx->mfc = NULL;
 	ctx->tagwait = 0;
 	ctx->state = SPU_STATE_SAVED;
 	ctx->local_store = NULL;

--

[PATCH] spufs: Fix endless protection fault on LS writes by SPE.

[Arnd Bergmann]

If an SPE attempts a DMA put to a local store after already doing
a get, the kernel must update the HW PTE to allow the write access.
This case was not being handled correctly.

From: Mike Kistler <mkistler@us.ibm.com>
Signed-off-by: Mike Kistler <mkistler@us.ibm.com>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>

---
diff -ur linux-2.6.15/arch/powerpc/platforms/cell/spu_base.c linux-2.6.15.fixed/arch/powerpc/platforms/cell/spu_base.c
--- linux-2.6.15/arch/powerpc/platforms/cell/spu_base.c	2006-03-22 12:30:07.000000000 -0600
+++ linux-2.6.15.fixed/arch/powerpc/platforms/cell/spu_base.c	2006-03-22 10:21:26.000000000 -0600
@@ -486,14 +486,13 @@
 
 	ea = spu->dar;
 	dsisr = spu->dsisr;
-	if (dsisr & MFC_DSISR_PTE_NOT_FOUND) {
+	if (dsisr & (MFC_DSISR_PTE_NOT_FOUND | MFC_DSISR_ACCESS_DENIED)) {
 		access = (_PAGE_PRESENT | _PAGE_USER);
 		access |= (dsisr & MFC_DSISR_ACCESS_PUT) ? _PAGE_RW : 0UL;
 		if (hash_page(ea, access, 0x300) != 0)
 			error |= CLASS1_ENABLE_STORAGE_FAULT_INTR;
 	}
-	if ((error & CLASS1_ENABLE_STORAGE_FAULT_INTR) ||
-	    (dsisr & MFC_DSISR_ACCESS_DENIED)) {
+	if (error & CLASS1_ENABLE_STORAGE_FAULT_INTR) {
 		if ((ret = spu_handle_mm_fault(spu)) != 0)
 			error |= CLASS1_ENABLE_STORAGE_FAULT_INTR;
 		else

[PATCH] fix __init/__exit annotations for spufs

[Arnd Bergmann]

spufs_init and spufs_exit should be marked correctly so
they can be removed when not needed.

Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
---
Index: linus-2.6/arch/powerpc/platforms/cell/spufs/inode.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/spufs/inode.c
+++ linus-2.6/arch/powerpc/platforms/cell/spufs/inode.c
@@ -442,7 +442,7 @@ static struct file_system_type spufs_typ
 	.kill_sb = kill_litter_super,
 };
 
-static int spufs_init(void)
+static int __init spufs_init(void)
 {
 	int ret;
 	ret = -ENOMEM;
@@ -472,7 +472,7 @@ out:
 }
 module_init(spufs_init);
 
-static void spufs_exit(void)
+static void __exit spufs_exit(void)
 {
 	spu_sched_exit();
 	unregister_spu_syscalls(&spufs_calls);