Merge branch 'linus' into sched/urgent

Documentation/cpusets.txt

@@ -542,7 +542,7 @@ otherwise initial value -1 that indicates the cpuset has no request.
    2  : search cores in a package.
    3  : search cpus in a node [= system wide on non-NUMA system]
  ( 4  : search nodes in a chunk of node [on NUMA system] )
- ( 5~ : search system wide [on NUMA system])
+ ( 5  : search system wide [on NUMA system] )
 
 This file is per-cpuset and affect the sched domain where the cpuset
 belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset

Documentation/hwmon/sysfs-interface

@@ -2,17 +2,12 @@ Naming and data format standards for sysfs files
 ------------------------------------------------
 
 The libsensors library offers an interface to the raw sensors data
-through the sysfs interface. See libsensors documentation and source for
-further information. As of writing this document, libsensors
-(from lm_sensors 2.8.3) is heavily chip-dependent. Adding or updating
-support for any given chip requires modifying the library's code.
-This is because libsensors was written for the procfs interface
-older kernel modules were using, which wasn't standardized enough.
-Recent versions of libsensors (from lm_sensors 2.8.2 and later) have
-support for the sysfs interface, though.
-
-The new sysfs interface was designed to be as chip-independent as
-possible.
+through the sysfs interface. Since lm-sensors 3.0.0, libsensors is
+completely chip-independent. It assumes that all the kernel drivers
+implement the standard sysfs interface described in this document.
+This makes adding or updating support for any given chip very easy, as
+libsensors, and applications using it, do not need to be modified.
+This is a major improvement compared to lm-sensors 2.
 
 Note that motherboards vary widely in the connections to sensor chips.
 There is no standard that ensures, for example, that the second
@@ -35,19 +30,17 @@ access this data in a simple and consistent way. That said, such programs
 will have to implement conversion, labeling and hiding of inputs. For
 this reason, it is still not recommended to bypass the library.
 
-If you are developing a userspace application please send us feedback on
-this standard.
-
-Note that this standard isn't completely established yet, so it is subject
-to changes. If you are writing a new hardware monitoring driver those
-features can't seem to fit in this interface, please contact us with your
-extension proposal. Keep in mind that backward compatibility must be
-preserved.
-
 Each chip gets its own directory in the sysfs /sys/devices tree.  To
 find all sensor chips, it is easier to follow the device symlinks from
 /sys/class/hwmon/hwmon*.
 
+Up to lm-sensors 3.0.0, libsensors looks for hardware monitoring attributes
+in the "physical" device directory. Since lm-sensors 3.0.1, attributes found
+in the hwmon "class" device directory are also supported. Complex drivers
+(e.g. drivers for multifunction chips) may want to use this possibility to
+avoid namespace pollution. The only drawback will be that older versions of
+libsensors won't support the driver in question.
+
 All sysfs values are fixed point numbers.
 
 There is only one value per file, unlike the older /proc specification.

MAINTAINERS

@@ -4431,10 +4431,10 @@ M:	johnpol@2ka.mipt.ru
 S:	Maintained
 
 W83791D HARDWARE MONITORING DRIVER
-P:	Charles Spirakis
-M:	bezaur@gmail.com
+P:	Marc Hulsman
+M:	m.hulsman@tudelft.nl
 L:	lm-sensors@lm-sensors.org
-S:	Odd Fixes
+S:	Maintained
 
 W83793 HARDWARE MONITORING DRIVER
 P:	Rudolf Marek

Makefile

 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 26
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Rotary Wombat
 
 # *DOCUMENTATION*

arch/alpha/Makefile

@@ -13,6 +13,7 @@ NM := $(NM) -B
 LDFLAGS_vmlinux	:= -static -N #-relax
 CHECKFLAGS	+= -D__alpha__ -m64
 cflags-y	:= -pipe -mno-fp-regs -ffixed-8 -msmall-data
+cflags-y	+= $(call cc-option, -fno-jump-tables)
 
 cpuflags-$(CONFIG_ALPHA_EV4)		:= -mcpu=ev4
 cpuflags-$(CONFIG_ALPHA_EV5)		:= -mcpu=ev5

arch/alpha/kernel/core_t2.c

@@ -74,6 +74,8 @@
 # define DBG(args)
 #endif
 
+DEFINE_SPINLOCK(t2_hae_lock);
+
 static volatile unsigned int t2_mcheck_any_expected;
 static volatile unsigned int t2_mcheck_last_taken;
 

arch/alpha/kernel/pci.c

@@ -71,6 +71,23 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82378, quirk_i
 static void __init
 quirk_cypress(struct pci_dev *dev)
 {
+	/* The Notorious Cy82C693 chip.  */
+
+	/* The generic legacy mode IDE fixup in drivers/pci/probe.c
+	   doesn't work correctly with the Cypress IDE controller as
+	   it has non-standard register layout.  Fix that.  */
+	if (dev->class >> 8 == PCI_CLASS_STORAGE_IDE) {
+		dev->resource[2].start = dev->resource[3].start = 0;
+		dev->resource[2].end = dev->resource[3].end = 0;
+		dev->resource[2].flags = dev->resource[3].flags = 0;
+		if (PCI_FUNC(dev->devfn) == 2) {
+			dev->resource[0].start = 0x170;
+			dev->resource[0].end = 0x177;
+			dev->resource[1].start = 0x376;
+			dev->resource[1].end = 0x376;
+		}
+	}
+
 	/* The Cypress bridge responds on the PCI bus in the address range
 	   0xffff0000-0xffffffff (conventional x86 BIOS ROM).  There is no
 	   way to turn this off.  The bridge also supports several extended

arch/alpha/kernel/traps.c

@@ -447,7 +447,7 @@ struct unaligned_stat {
 
 
 /* Macro for exception fixup code to access integer registers.  */
-#define una_reg(r)  (regs->regs[(r) >= 16 && (r) <= 18 ? (r)+19 : (r)])
+#define una_reg(r)  (_regs[(r) >= 16 && (r) <= 18 ? (r)+19 : (r)])
 
 
 asmlinkage void
@@ -456,6 +456,7 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,
 {
 	long error, tmp1, tmp2, tmp3, tmp4;
 	unsigned long pc = regs->pc - 4;
+	unsigned long *_regs = regs->regs;
 	const struct exception_table_entry *fixup;
 
 	unaligned[0].count++;

arch/ia64/sn/kernel/sn2/sn2_smp.c

@@ -512,6 +512,8 @@ static ssize_t sn2_ptc_proc_write(struct file *file, const char __user *user, si
 	int cpu;
 	char optstr[64];
 
+	if (count > sizeof(optstr))
+		return -EINVAL;
 	if (copy_from_user(optstr, user, count))
 		return -EFAULT;
 	optstr[count - 1] = '\0';

arch/powerpc/kernel/vdso.c

@@ -142,7 +142,7 @@ static void dump_one_vdso_page(struct page *pg, struct page *upg)
 	printk("kpg: %p (c:%d,f:%08lx)", __va(page_to_pfn(pg) << PAGE_SHIFT),
 	       page_count(pg),
 	       pg->flags);
-	if (upg/* && pg != upg*/) {
+	if (upg && !IS_ERR(upg) /* && pg != upg*/) {
 		printk(" upg: %p (c:%d,f:%08lx)", __va(page_to_pfn(upg)
 						       << PAGE_SHIFT),
 		       page_count(upg),

arch/x86/kernel/geode_32.c

@@ -166,6 +166,8 @@ int geode_has_vsa2(void)
 	static int has_vsa2 = -1;
 
 	if (has_vsa2 == -1) {
+		u16 val;
+
 		/*
 		 * The VSA has virtual registers that we can query for a
 		 * signature.
@@ -173,7 +175,8 @@ int geode_has_vsa2(void)
 		outw(VSA_VR_UNLOCK, VSA_VRC_INDEX);
 		outw(VSA_VR_SIGNATURE, VSA_VRC_INDEX);
 
-		has_vsa2 = (inw(VSA_VRC_DATA) == VSA_SIG);
+		val = inw(VSA_VRC_DATA);
+		has_vsa2 = (val == AMD_VSA_SIG || val == GSW_VSA_SIG);
 	}
 
 	return has_vsa2;

arch/x86/kernel/process_32.c

@@ -333,6 +333,7 @@ void flush_thread(void)
 	/*
 	 * Forget coprocessor state..
 	 */
+	tsk->fpu_counter = 0;
 	clear_fpu(tsk);
 	clear_used_math();
 }

arch/x86/kernel/process_64.c

@@ -294,6 +294,7 @@ void flush_thread(void)
 	/*
 	 * Forget coprocessor state..
 	 */
+	tsk->fpu_counter = 0;
 	clear_fpu(tsk);
 	clear_used_math();
 }

arch/x86/kernel/setup_32.c

@@ -532,10 +532,16 @@ static void __init reserve_crashkernel(void)
 					(unsigned long)(crash_size >> 20),
 					(unsigned long)(crash_base >> 20),
 					(unsigned long)(total_mem >> 20));
+
+			if (reserve_bootmem(crash_base, crash_size,
+					BOOTMEM_EXCLUSIVE) < 0) {
+				printk(KERN_INFO "crashkernel reservation "
+					"failed - memory is in use\n");
+				return;
+			}
+
 			crashk_res.start = crash_base;
 			crashk_res.end   = crash_base + crash_size - 1;
-			reserve_bootmem(crash_base, crash_size,
-					BOOTMEM_DEFAULT);
 		} else
 			printk(KERN_INFO "crashkernel reservation failed - "
 					"you have to specify a base address\n");

arch/x86/kernel/tsc_32.c

@@ -14,7 +14,10 @@
 
 #include "mach_timer.h"
 
-static int tsc_disabled;
+/* native_sched_clock() is called before tsc_init(), so
+   we must start with the TSC soft disabled to prevent
+   erroneous rdtsc usage on !cpu_has_tsc processors */
+static int tsc_disabled = -1;
 
 /*
  * On some systems the TSC frequency does not
@@ -402,25 +405,20 @@ void __init tsc_init(void)
 {
 	int cpu;
 
-	if (!cpu_has_tsc || tsc_disabled) {
-		/* Disable the TSC in case of !cpu_has_tsc */
-		tsc_disabled = 1;
+	if (!cpu_has_tsc || tsc_disabled > 0)
 		return;
-	}
 
 	cpu_khz = calculate_cpu_khz();
 	tsc_khz = cpu_khz;
 
 	if (!cpu_khz) {
 		mark_tsc_unstable("could not calculate TSC khz");
-		/*
-		 * We need to disable the TSC completely in this case
-		 * to prevent sched_clock() from using it.
-		 */
-		tsc_disabled = 1;
 		return;
 	}
 
+	/* now allow native_sched_clock() to use rdtsc */
+	tsc_disabled = 0;
+
 	printk("Detected %lu.%03lu MHz processor.\n",
 				(unsigned long)cpu_khz / 1000,
 				(unsigned long)cpu_khz % 1000);

drivers/acpi/ac.c

@@ -233,6 +233,9 @@ static void acpi_ac_notify(acpi_handle handle, u32 event, void *data)
 
 	device = ac->device;
 	switch (event) {
+	default:
+		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
+				  "Unsupported event [0x%x]\n", event));
 	case ACPI_AC_NOTIFY_STATUS:
 	case ACPI_NOTIFY_BUS_CHECK:
 	case ACPI_NOTIFY_DEVICE_CHECK:
@@ -244,11 +247,6 @@ static void acpi_ac_notify(acpi_handle handle, u32 event, void *data)
 #ifdef CONFIG_ACPI_SYSFS_POWER
 		kobject_uevent(&ac->charger.dev->kobj, KOBJ_CHANGE);
 #endif
-		break;
-	default:
-		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-				  "Unsupported event [0x%x]\n", event));
-		break;
 	}
 
 	return;

drivers/acpi/video.c

@@ -1713,7 +1713,8 @@ acpi_video_bus_get_devices(struct acpi_video_bus *video,
 
 		status = acpi_video_bus_get_one_device(dev, video);
 		if (ACPI_FAILURE(status)) {
-			ACPI_EXCEPTION((AE_INFO, status, "Cant attach device"));
+			ACPI_DEBUG_PRINT((ACPI_DB_WARN,
+					"Cant attach device"));
 			continue;
 		}
 	}

drivers/ata/Kconfig

@@ -651,9 +651,17 @@ config PATA_WINBOND_VLB
 	  Support for the Winbond W83759A controller on Vesa Local Bus
 	  systems.
 
+config HAVE_PATA_PLATFORM
+	bool
+	help
+	  This is an internal configuration node for any machine that
+	  uses pata-platform driver to enable the relevant driver in the
+	  configuration structure without having to submit endless patches
+	  to update the PATA_PLATFORM entry.
+
 config PATA_PLATFORM
 	tristate "Generic platform device PATA support"
-	depends on EMBEDDED || ARCH_RPC || PPC
+	depends on EMBEDDED || ARCH_RPC || PPC || HAVE_PATA_PLATFORM
 	help
 	  This option enables support for generic directly connected ATA
 	  devices commonly found on embedded systems.

drivers/ata/ahci.c

@@ -90,6 +90,7 @@ enum {
 	board_ahci_mv		= 4,
 	board_ahci_sb700	= 5,
 	board_ahci_mcp65	= 6,
+	board_ahci_nopmp	= 7,
 
 	/* global controller registers */
 	HOST_CAP		= 0x00, /* host capabilities */
@@ -401,6 +402,14 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
+	/* board_ahci_nopmp */
+	{
+		AHCI_HFLAGS	(AHCI_HFLAG_NO_PMP),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= 0x1f, /* pio0-4 */
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
 };
 
 static const struct pci_device_id ahci_pci_tbl[] = {
@@ -525,9 +534,9 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(NVIDIA, 0x0bc7), board_ahci },		/* MCP7B */
 
 	/* SiS */
-	{ PCI_VDEVICE(SI, 0x1184), board_ahci }, /* SiS 966 */
-	{ PCI_VDEVICE(SI, 0x1185), board_ahci }, /* SiS 966 */
-	{ PCI_VDEVICE(SI, 0x0186), board_ahci }, /* SiS 968 */
+	{ PCI_VDEVICE(SI, 0x1184), board_ahci_nopmp },		/* SiS 966 */
+	{ PCI_VDEVICE(SI, 0x1185), board_ahci_nopmp },		/* SiS 968 */
+	{ PCI_VDEVICE(SI, 0x0186), board_ahci_nopmp },		/* SiS 968 */
 
 	/* Marvell */
 	{ PCI_VDEVICE(MARVELL, 0x6145), board_ahci_mv },	/* 6145 */
@@ -653,6 +662,14 @@ static void ahci_save_initial_config(struct pci_dev *pdev,
 		cap &= ~HOST_CAP_PMP;
 	}
 
+	if (pdev->vendor == PCI_VENDOR_ID_JMICRON && pdev->device == 0x2361 &&
+	    port_map != 1) {
+		dev_printk(KERN_INFO, &pdev->dev,
+			   "JMB361 has only one port, port_map 0x%x -> 0x%x\n",
+			   port_map, 1);
+		port_map = 1;
+	}
+
 	/*
 	 * Temporary Marvell 6145 hack: PATA port presence
 	 * is asserted through the standard AHCI port

drivers/ata/ata_piix.c

@@ -1042,6 +1042,13 @@ static int piix_broken_suspend(void)
 				DMI_MATCH(DMI_PRODUCT_NAME, "Tecra M4"),
 			},
 		},
+		{
+			.ident = "TECRA M4",
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+				DMI_MATCH(DMI_PRODUCT_NAME, "TECRA M4"),
+			},
+		},
 		{
 			.ident = "TECRA M5",
 			.matches = {

drivers/ata/libata-core.c

@@ -4297,7 +4297,7 @@ void ata_sg_clean(struct ata_queued_cmd *qc)
 }
 
 /**
- *	ata_check_atapi_dma - Check whether ATAPI DMA can be supported
+ *	atapi_check_dma - Check whether ATAPI DMA can be supported
  *	@qc: Metadata associated with taskfile to check
  *
  *	Allow low-level driver to filter ATA PACKET commands, returning
@@ -4310,7 +4310,7 @@ void ata_sg_clean(struct ata_queued_cmd *qc)
  *	RETURNS: 0 when ATAPI DMA can be used
  *               nonzero otherwise
  */
-int ata_check_atapi_dma(struct ata_queued_cmd *qc)
+int atapi_check_dma(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 

drivers/ata/libata-scsi.c

@@ -2343,8 +2343,8 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc)
 {
 	struct scsi_cmnd *scmd = qc->scsicmd;
 	struct ata_device *dev = qc->dev;
-	int using_pio = (dev->flags & ATA_DFLAG_PIO);
 	int nodata = (scmd->sc_data_direction == DMA_NONE);
+	int using_pio = !nodata && (dev->flags & ATA_DFLAG_PIO);
 	unsigned int nbytes;
 
 	memset(qc->cdb, 0, dev->cdb_len);
@@ -2362,7 +2362,7 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc)
 	ata_qc_set_pc_nbytes(qc);
 
 	/* check whether ATAPI DMA is safe */
-	if (!using_pio && ata_check_atapi_dma(qc))
+	if (!nodata && !using_pio && atapi_check_dma(qc))
 		using_pio = 1;
 
 	/* Some controller variants snoop this value for Packet
@@ -2402,13 +2402,11 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc)
 	qc->tf.lbam = (nbytes & 0xFF);
 	qc->tf.lbah = (nbytes >> 8);
 
-	if (using_pio || nodata) {
-		/* no data, or PIO data xfer */
-		if (nodata)
-			qc->tf.protocol = ATAPI_PROT_NODATA;
-		else
-			qc->tf.protocol = ATAPI_PROT_PIO;
-	} else {
+	if (nodata)
+		qc->tf.protocol = ATAPI_PROT_NODATA;
+	else if (using_pio)
+		qc->tf.protocol = ATAPI_PROT_PIO;
+	else {
 		/* DMA data xfer */
 		qc->tf.protocol = ATAPI_PROT_DMA;
 		qc->tf.feature |= ATAPI_PKT_DMA;

drivers/ata/libata.h

@@ -106,7 +106,7 @@ extern void ata_sg_clean(struct ata_queued_cmd *qc);
 extern void ata_qc_free(struct ata_queued_cmd *qc);
 extern void ata_qc_issue(struct ata_queued_cmd *qc);
 extern void __ata_qc_complete(struct ata_queued_cmd *qc);
-extern int ata_check_atapi_dma(struct ata_queued_cmd *qc);
+extern int atapi_check_dma(struct ata_queued_cmd *qc);
 extern void swap_buf_le16(u16 *buf, unsigned int buf_words);
 extern void ata_dev_init(struct ata_device *dev);
 extern void ata_link_init(struct ata_port *ap, struct ata_link *link, int pmp);

drivers/ata/pata_pcmcia.c

@@ -414,6 +414,7 @@ static struct pcmcia_device_id pcmcia_devices[] = {
 	PCMCIA_DEVICE_PROD_ID12("IO DATA", "PCIDE", 0x547e66dc, 0x5c5ab149),
 	PCMCIA_DEVICE_PROD_ID12("IO DATA", "PCIDEII", 0x547e66dc, 0xb3662674),
 	PCMCIA_DEVICE_PROD_ID12("LOOKMEET", "CBIDE2      ", 0xe37be2b5, 0x8671043b),
+	PCMCIA_DEVICE_PROD_ID12("M-Systems", "CF300", 0x7ed2ad87, 0x7e9e78ee),
 	PCMCIA_DEVICE_PROD_ID12("M-Systems", "CF500", 0x7ed2ad87, 0x7a13045c),
 	PCMCIA_DEVICE_PROD_ID2("NinjaATA-", 0xebe0bd79),
 	PCMCIA_DEVICE_PROD_ID12("PCMCIA", "CD-ROM", 0x281f1c5d, 0x66536591),
@@ -424,6 +425,7 @@ static struct pcmcia_device_id pcmcia_devices[] = {
 	PCMCIA_DEVICE_PROD_ID12("SMI VENDOR", "SMI PRODUCT", 0x30896c92, 0x703cc5f6),
 	PCMCIA_DEVICE_PROD_ID12("TOSHIBA", "MK2001MPL", 0xb4585a1a, 0x3489e003),
 	PCMCIA_DEVICE_PROD_ID1("TRANSCEND    512M   ", 0xd0909443),
+	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS1GCF45", 0x709b1bf1, 0xf68b6f32),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS1GCF80", 0x709b1bf1, 0x2a54d4b1),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS2GCF120", 0x709b1bf1, 0x969aa4f2),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS4GCF120", 0x709b1bf1, 0xf54a91c8),

drivers/ata/sata_mv.c

@@ -1322,6 +1322,9 @@ static int mv_port_start(struct ata_port *ap)
 		goto out_port_free_dma_mem;
 	memset(pp->crpb, 0, MV_CRPB_Q_SZ);
 
+	/* 6041/6081 Rev. "C0" (and newer) are okay with async notify */
+	if (hpriv->hp_flags & MV_HP_ERRATA_60X1C0)
+		ap->flags |= ATA_FLAG_AN;
 	/*
 	 * For GEN_I, there's no NCQ, so we only allocate a single sg_tbl.
 	 * For later hardware, we need one unique sg_tbl per NCQ tag.
@@ -1592,6 +1595,24 @@ static unsigned int mv_qc_issue(struct ata_queued_cmd *qc)
 
 	if ((qc->tf.protocol != ATA_PROT_DMA) &&
 	    (qc->tf.protocol != ATA_PROT_NCQ)) {
+		static int limit_warnings = 10;
+		/*
+		 * Errata SATA#16, SATA#24: warn if multiple DRQs expected.
+		 *
+		 * Someday, we might implement special polling workarounds
+		 * for these, but it all seems rather unnecessary since we
+		 * normally use only DMA for commands which transfer more
+		 * than a single block of data.
+		 *
+		 * Much of the time, this could just work regardless.
+		 * So for now, just log the incident, and allow the attempt.
+		 */
+		if (limit_warnings && (qc->nbytes / qc->sect_size) > 1) {
+			--limit_warnings;
+			ata_link_printk(qc->dev->link, KERN_WARNING, DRV_NAME
+					": attempting PIO w/multiple DRQ: "
+					"this may fail due to h/w errata\n");
+		}
 		/*
 		 * We're about to send a non-EDMA capable command to the
 		 * port.  Turn off EDMA so there won't be problems accessing

drivers/char/agp/intel-agp.c

@@ -948,7 +948,7 @@ static void intel_i9xx_setup_flush(void)
 	intel_private.ifp_resource.flags = IORESOURCE_MEM;
 
 	/* Setup chipset flush for 915 */
-	if (IS_I965 || IS_G33) {
+	if (IS_I965 || IS_G33 || IS_G4X) {
 		intel_i965_g33_setup_chipset_flush();
 	} else {
 		intel_i915_setup_chipset_flush();

drivers/char/drm/ati_pcigart.c

@@ -76,7 +76,7 @@ int drm_ati_pcigart_cleanup(struct drm_device *dev, struct drm_ati_pcigart_info
 		for (i = 0; i < pages; i++) {
 			if (!entry->busaddr[i])
 				break;
-			pci_unmap_single(dev->pdev, entry->busaddr[i],
+			pci_unmap_page(dev->pdev, entry->busaddr[i],
 					 PAGE_SIZE, PCI_DMA_TODEVICE);
 		}
 
@@ -137,10 +137,8 @@ int drm_ati_pcigart_init(struct drm_device *dev, struct drm_ati_pcigart_info *ga
 
 	for (i = 0; i < pages; i++) {
 		/* we need to support large memory configurations */
-		entry->busaddr[i] = pci_map_single(dev->pdev,
-						   page_address(entry->
-								pagelist[i]),
-						   PAGE_SIZE, PCI_DMA_TODEVICE);
+		entry->busaddr[i] = pci_map_page(dev->pdev, entry->pagelist[i],
+						 0, PAGE_SIZE, PCI_DMA_TODEVICE);
 		if (entry->busaddr[i] == 0) {
 			DRM_ERROR("unable to map PCIGART pages!\n");
 			drm_ati_pcigart_cleanup(dev, gart_info);

drivers/char/drm/drm.h

@@ -628,7 +628,7 @@ struct drm_set_version {
 #define DRM_IOCTL_AGP_BIND		DRM_IOW( 0x36, struct drm_agp_binding)
 #define DRM_IOCTL_AGP_UNBIND		DRM_IOW( 0x37, struct drm_agp_binding)
 
-#define DRM_IOCTL_SG_ALLOC		DRM_IOW( 0x38, struct drm_scatter_gather)
+#define DRM_IOCTL_SG_ALLOC		DRM_IOWR(0x38, struct drm_scatter_gather)
 #define DRM_IOCTL_SG_FREE		DRM_IOW( 0x39, struct drm_scatter_gather)
 
 #define DRM_IOCTL_WAIT_VBLANK		DRM_IOWR(0x3a, union drm_wait_vblank)

drivers/char/drm/drm_drv.c

@@ -470,17 +470,18 @@ int drm_ioctl(struct inode *inode, struct file *filp,
 	if ((nr >= DRM_COMMAND_BASE) && (nr < DRM_COMMAND_END) &&
 	    (nr < DRM_COMMAND_BASE + dev->driver->num_ioctls))
 		ioctl = &dev->driver->ioctls[nr - DRM_COMMAND_BASE];
-	else if ((nr >= DRM_COMMAND_END) || (nr < DRM_COMMAND_BASE))
+	else if ((nr >= DRM_COMMAND_END) || (nr < DRM_COMMAND_BASE)) {
 		ioctl = &drm_ioctls[nr];
-	else
+		cmd = ioctl->cmd;
+	} else
 		goto err_i1;
 
+	/* Do not trust userspace, use our own definition */
 	func = ioctl->func;
 	/* is there a local override? */
 	if ((nr == DRM_IOCTL_NR(DRM_IOCTL_DMA)) && dev->driver->dma_ioctl)
 		func = dev->driver->dma_ioctl;
 
-
 	if (!func) {
 		DRM_DEBUG("no function\n");
 		retcode = -EINVAL;

drivers/char/drm/drm_pciids.h

@@ -103,20 +103,18 @@
 	{0x1002, 0x5653, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5834, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS300|RADEON_IS_IGP}, \
 	{0x1002, 0x5835, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS300|RADEON_IS_IGP|RADEON_IS_MOBILITY}, \
-	{0x1002, 0x5954, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5955, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5974, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5975, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5954, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5955, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5974, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5975, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
 	{0x1002, 0x5960, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280}, \
 	{0x1002, 0x5961, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280}, \
 	{0x1002, 0x5962, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280}, \
 	{0x1002, 0x5964, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280}, \
 	{0x1002, 0x5965, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280}, \
 	{0x1002, 0x5969, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV100}, \
-	{0x1002, 0x5a41, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5a42, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5a61, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5a62, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5a61, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5a62, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
 	{0x1002, 0x5b60, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5b62, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5b63, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_NEW_MEMMAP}, \
@@ -411,4 +409,7 @@
 	{0x8086, 0x2a02, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \
 	{0x8086, 0x2a12, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \
 	{0x8086, 0x2a42, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \
+	{0x8086, 0x2e02, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \
+	{0x8086, 0x2e12, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \
+	{0x8086, 0x2e22, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \
 	{0, 0, 0}

drivers/char/drm/i915_drv.h

@@ -1112,12 +1112,19 @@ extern int i915_wait_ring(struct drm_device * dev, int n, const char *caller);
 		       (dev)->pci_device == 0x29A2 || \
 		       (dev)->pci_device == 0x2A02 || \
 		       (dev)->pci_device == 0x2A12 || \
-		       (dev)->pci_device == 0x2A42)
+		       (dev)->pci_device == 0x2A42 || \
+		       (dev)->pci_device == 0x2E02 || \
+		       (dev)->pci_device == 0x2E12 || \
+		       (dev)->pci_device == 0x2E22)
 
 #define IS_I965GM(dev) ((dev)->pci_device == 0x2A02)
 
 #define IS_IGD_GM(dev) ((dev)->pci_device == 0x2A42)
 
+#define IS_G4X(dev) ((dev)->pci_device == 0x2E02 || \
+		     (dev)->pci_device == 0x2E12 || \
+		     (dev)->pci_device == 0x2E22)
+
 #define IS_G33(dev)    ((dev)->pci_device == 0x29C2 ||	\
 			(dev)->pci_device == 0x29B2 ||	\
 			(dev)->pci_device == 0x29D2)
@@ -1128,7 +1135,7 @@ extern int i915_wait_ring(struct drm_device * dev, int n, const char *caller);
 #define IS_MOBILE(dev) (IS_I830(dev) || IS_I85X(dev) || IS_I915GM(dev) || \
 			IS_I945GM(dev) || IS_I965GM(dev) || IS_IGD_GM(dev))
 
-#define I915_NEED_GFX_HWS(dev) (IS_G33(dev) || IS_IGD_GM(dev))
+#define I915_NEED_GFX_HWS(dev) (IS_G33(dev) || IS_IGD_GM(dev) || IS_G4X(dev))
 
 #define PRIMARY_RINGBUFFER_SIZE         (128*1024)
 

drivers/char/drm/r300_cmdbuf.c

@@ -189,18 +189,12 @@ void r300_init_reg_flags(struct drm_device *dev)
 	ADD_RANGE(R300_RE_CULL_CNTL, 1);
 	ADD_RANGE(0x42C0, 2);
 	ADD_RANGE(R300_RS_CNTL_0, 2);
-	ADD_RANGE(R300_RS_INTERP_0, 8);
-	ADD_RANGE(R300_RS_ROUTE_0, 8);
-	ADD_RANGE(0x43A4, 2);
+
+	ADD_RANGE(R300_SC_HYPERZ, 2);
 	ADD_RANGE(0x43E8, 1);
-	ADD_RANGE(R300_PFS_CNTL_0, 3);
-	ADD_RANGE(R300_PFS_NODE_0, 4);
-	ADD_RANGE(R300_PFS_TEXI_0, 64);
+
 	ADD_RANGE(0x46A4, 5);
-	ADD_RANGE(R300_PFS_INSTR0_0, 64);
-	ADD_RANGE(R300_PFS_INSTR1_0, 64);
-	ADD_RANGE(R300_PFS_INSTR2_0, 64);
-	ADD_RANGE(R300_PFS_INSTR3_0, 64);
+
 	ADD_RANGE(R300_RE_FOG_STATE, 1);
 	ADD_RANGE(R300_FOG_COLOR_R, 3);
 	ADD_RANGE(R300_PP_ALPHA_TEST, 2);
@@ -215,14 +209,12 @@ void r300_init_reg_flags(struct drm_device *dev)
 	ADD_RANGE(0x4E50, 9);
 	ADD_RANGE(0x4E88, 1);
 	ADD_RANGE(0x4EA0, 2);
-	ADD_RANGE(R300_RB3D_ZSTENCIL_CNTL_0, 3);
-	ADD_RANGE(R300_RB3D_ZSTENCIL_FORMAT, 4);
-	ADD_RANGE_MARK(R300_RB3D_DEPTHOFFSET, 1, MARK_CHECK_OFFSET);	/* check offset */
-	ADD_RANGE(R300_RB3D_DEPTHPITCH, 1);
-	ADD_RANGE(0x4F28, 1);
-	ADD_RANGE(0x4F30, 2);
-	ADD_RANGE(0x4F44, 1);
-	ADD_RANGE(0x4F54, 1);
+	ADD_RANGE(R300_ZB_CNTL, 3);
+	ADD_RANGE(R300_ZB_FORMAT, 4);
+	ADD_RANGE_MARK(R300_ZB_DEPTHOFFSET, 1, MARK_CHECK_OFFSET);	/* check offset */
+	ADD_RANGE(R300_ZB_DEPTHPITCH, 1);
+	ADD_RANGE(R300_ZB_DEPTHCLEARVALUE, 1);
+	ADD_RANGE(R300_ZB_ZMASK_OFFSET, 13);
 
 	ADD_RANGE(R300_TX_FILTER_0, 16);
 	ADD_RANGE(R300_TX_FILTER1_0, 16);
@@ -235,13 +227,32 @@ void r300_init_reg_flags(struct drm_device *dev)
 	ADD_RANGE(R300_TX_BORDER_COLOR_0, 16);
 
 	/* Sporadic registers used as primitives are emitted */
-	ADD_RANGE(R300_RB3D_ZCACHE_CTLSTAT, 1);
+	ADD_RANGE(R300_ZB_ZCACHE_CTLSTAT, 1);
 	ADD_RANGE(R300_RB3D_DSTCACHE_CTLSTAT, 1);
 	ADD_RANGE(R300_VAP_INPUT_ROUTE_0_0, 8);
 	ADD_RANGE(R300_VAP_INPUT_ROUTE_1_0, 8);
 
 	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RV515) {
-		ADD_RANGE(0x4074, 16);
+		ADD_RANGE(R500_VAP_INDEX_OFFSET, 1);
+		ADD_RANGE(R500_US_CONFIG, 2);
+		ADD_RANGE(R500_US_CODE_ADDR, 3);
+		ADD_RANGE(R500_US_FC_CTRL, 1);
+		ADD_RANGE(R500_RS_IP_0, 16);
+		ADD_RANGE(R500_RS_INST_0, 16);
+		ADD_RANGE(R500_RB3D_COLOR_CLEAR_VALUE_AR, 2);
+		ADD_RANGE(R500_RB3D_CONSTANT_COLOR_AR, 2);
+		ADD_RANGE(R500_ZB_FIFO_SIZE, 2);
+	} else {
+		ADD_RANGE(R300_PFS_CNTL_0, 3);
+		ADD_RANGE(R300_PFS_NODE_0, 4);
+		ADD_RANGE(R300_PFS_TEXI_0, 64);
+		ADD_RANGE(R300_PFS_INSTR0_0, 64);
+		ADD_RANGE(R300_PFS_INSTR1_0, 64);
+		ADD_RANGE(R300_PFS_INSTR2_0, 64);
+		ADD_RANGE(R300_PFS_INSTR3_0, 64);
+		ADD_RANGE(R300_RS_INTERP_0, 8);
+		ADD_RANGE(R300_RS_ROUTE_0, 8);
+
 	}
 }
 
@@ -707,8 +718,9 @@ static __inline__ void r300_pacify(drm_radeon_private_t *dev_priv)
 	BEGIN_RING(6);
 	OUT_RING(CP_PACKET0(R300_RB3D_DSTCACHE_CTLSTAT, 0));
 	OUT_RING(R300_RB3D_DSTCACHE_UNKNOWN_0A);
-	OUT_RING(CP_PACKET0(R300_RB3D_ZCACHE_CTLSTAT, 0));
-	OUT_RING(R300_RB3D_ZCACHE_UNKNOWN_03);
+	OUT_RING(CP_PACKET0(R300_ZB_ZCACHE_CTLSTAT, 0));
+	OUT_RING(R300_ZB_ZCACHE_CTLSTAT_ZC_FLUSH_FLUSH_AND_FREE|
+		 R300_ZB_ZCACHE_CTLSTAT_ZC_FREE_FREE);
 	OUT_RING(CP_PACKET3(RADEON_CP_NOP, 0));
 	OUT_RING(0x0);
 	ADVANCE_RING();
@@ -828,6 +840,54 @@ static int r300_scratch(drm_radeon_private_t *dev_priv,
 	return 0;
 }
 
+/**
+ * Uploads user-supplied vertex program instructions or parameters onto
+ * the graphics card.
+ * Called by r300_do_cp_cmdbuf.
+ */
+static inline int r300_emit_r500fp(drm_radeon_private_t *dev_priv,
+				       drm_radeon_kcmd_buffer_t *cmdbuf,
+				       drm_r300_cmd_header_t header)
+{
+	int sz;
+	int addr;
+	int type;
+	int clamp;
+	int stride;
+	RING_LOCALS;
+
+	sz = header.r500fp.count;
+	/* address is 9 bits 0 - 8, bit 1 of flags is part of address */
+	addr = ((header.r500fp.adrhi_flags & 1) << 8) | header.r500fp.adrlo;
+
+	type = !!(header.r500fp.adrhi_flags & R500FP_CONSTANT_TYPE);
+	clamp = !!(header.r500fp.adrhi_flags & R500FP_CONSTANT_CLAMP);
+
+	addr |= (type << 16);
+	addr |= (clamp << 17);
+
+	stride = type ? 4 : 6;
+
+	DRM_DEBUG("r500fp %d %d type: %d\n", sz, addr, type);
+	if (!sz)
+		return 0;
+	if (sz * stride * 4 > cmdbuf->bufsz)
+		return -EINVAL;
+
+	BEGIN_RING(3 + sz * stride);
+	OUT_RING_REG(R500_GA_US_VECTOR_INDEX, addr);
+	OUT_RING(CP_PACKET0_TABLE(R500_GA_US_VECTOR_DATA, sz * stride - 1));
+	OUT_RING_TABLE((int *)cmdbuf->buf, sz * stride);
+
+	ADVANCE_RING();
+
+	cmdbuf->buf += sz * stride * 4;
+	cmdbuf->bufsz -= sz * stride * 4;
+
+	return 0;
+}
+
+
 /**
  * Parses and validates a user-supplied command buffer and emits appropriate
  * commands on the DMA ring buffer.
@@ -963,6 +1023,19 @@ int r300_do_cp_cmdbuf(struct drm_device *dev,
 			}
 			break;
 
+		case R300_CMD_R500FP:
+			if ((dev_priv->flags & RADEON_FAMILY_MASK) < CHIP_RV515) {
+				DRM_ERROR("Calling r500 command on r300 card\n");
+				ret = -EINVAL;
+				goto cleanup;
+			}
+			DRM_DEBUG("R300_CMD_R500FP\n");
+			ret = r300_emit_r500fp(dev_priv, cmdbuf, header);
+			if (ret) {
+				DRM_ERROR("r300_emit_r500fp failed\n");
+				goto cleanup;
+			}
+			break;
 		default:
 			DRM_ERROR("bad cmd_type %i at %p\n",
 				  header.header.cmd_type,

drivers/char/drm/radeon_drm.h

@@ -240,6 +240,7 @@ typedef union {
 #	define R300_NEW_WAIT_2D_2D_CLEAN_3D_3D_CLEAN	0x8
 
 #define R300_CMD_SCRATCH		8
+#define R300_CMD_R500FP                 9
 
 typedef union {
 	unsigned int u;
@@ -268,6 +269,9 @@ typedef union {
 	struct {
 		unsigned char cmd_type, reg, n_bufs, flags;
 	} scratch;
+	struct {
+		unsigned char cmd_type, count, adrlo, adrhi_flags;
+	} r500fp;
 } drm_r300_cmd_header_t;
 
 #define RADEON_FRONT			0x1
@@ -278,6 +282,9 @@ typedef union {
 #define RADEON_USE_HIERZ		0x40000000
 #define RADEON_USE_COMP_ZBUF		0x20000000
 
+#define R500FP_CONSTANT_TYPE  (1 << 1)
+#define R500FP_CONSTANT_CLAMP (1 << 2)
+
 /* Primitive types
  */
 #define RADEON_POINTS			0x1
@@ -669,6 +676,7 @@ typedef struct drm_radeon_indirect {
 #define RADEON_PARAM_CARD_TYPE             12
 #define RADEON_PARAM_VBLANK_CRTC           13   /* VBLANK CRTC */
 #define RADEON_PARAM_FB_LOCATION           14   /* FB location */
+#define RADEON_PARAM_NUM_GB_PIPES          15   /* num GB pipes */
 
 typedef struct drm_radeon_getparam {
 	int param;

drivers/char/drm/radeon_irq.c

@@ -234,7 +234,7 @@ int radeon_irq_wait(struct drm_device *dev, void *data, struct drm_file *file_pr
 	return radeon_wait_irq(dev, irqwait->irq_seq);
 }
 
-static void radeon_enable_interrupt(struct drm_device *dev)
+void radeon_enable_interrupt(struct drm_device *dev)
 {
 	drm_radeon_private_t *dev_priv = (drm_radeon_private_t *) dev->dev_private;
 

drivers/char/drm/radeon_state.c

@@ -1662,7 +1662,7 @@ static int radeon_cp_dispatch_texture(struct drm_device * dev,
 	u32 height;
 	int i;
 	u32 texpitch, microtile;
-	u32 offset;
+	u32 offset, byte_offset;
 	RING_LOCALS;
 
 	if (radeon_check_and_fixup_offset(dev_priv, file_priv, &tex->offset)) {
@@ -1727,6 +1727,13 @@ static int radeon_cp_dispatch_texture(struct drm_device * dev,
 	} else
 		microtile = 0;
 
+	/* this might fail for zero-sized uploads - are those illegal? */
+	if (!radeon_check_offset(dev_priv, tex->offset + image->height *
+				blit_width - 1)) {
+		DRM_ERROR("Invalid final destination offset\n");
+		return -EINVAL;
+	}
+
 	DRM_DEBUG("tex=%dx%d blit=%d\n", tex_width, tex->height, blit_width);
 
 	do {
@@ -1840,6 +1847,7 @@ static int radeon_cp_dispatch_texture(struct drm_device * dev,
 		}
 
 #undef RADEON_COPY_MT
+		byte_offset = (image->y & ~2047) * blit_width;
 		buf->file_priv = file_priv;
 		buf->used = size;
 		offset = dev_priv->gart_buffers_offset + buf->offset;
@@ -1854,9 +1862,9 @@ static int radeon_cp_dispatch_texture(struct drm_device * dev,
 			 RADEON_DP_SRC_SOURCE_MEMORY |
 			 RADEON_GMC_CLR_CMP_CNTL_DIS | RADEON_GMC_WR_MSK_DIS);
 		OUT_RING((spitch << 22) | (offset >> 10));
-		OUT_RING((texpitch << 22) | (tex->offset >> 10));
+		OUT_RING((texpitch << 22) | ((tex->offset >> 10) + (byte_offset >> 10)));
 		OUT_RING(0);
-		OUT_RING((image->x << 16) | image->y);
+		OUT_RING((image->x << 16) | (image->y % 2048));
 		OUT_RING((image->width << 16) | height);
 		RADEON_WAIT_UNTIL_2D_IDLE();
 		ADVANCE_RING();
@@ -3037,6 +3045,9 @@ static int radeon_cp_getparam(struct drm_device *dev, void *data, struct drm_fil
 	case RADEON_PARAM_FB_LOCATION:
 		value = radeon_read_fb_location(dev_priv);
 		break;
+	case RADEON_PARAM_NUM_GB_PIPES:
+		value = dev_priv->num_gb_pipes;
+		break;
 	default:
 		DRM_DEBUG("Invalid parameter %d\n", param->param);
 		return -EINVAL;

drivers/firewire/Kconfig

-comment "An alternative FireWire stack is available with EXPERIMENTAL=y"
+comment "A new alternative FireWire stack is available with EXPERIMENTAL=y"
 	depends on EXPERIMENTAL=n
 
+comment "Enable only one of the two stacks, unless you know what you are doing"
+	depends on EXPERIMENTAL
+
 config FIREWIRE
-	tristate "IEEE 1394 (FireWire) support - alternative stack, EXPERIMENTAL"
+	tristate "New FireWire stack, EXPERIMENTAL"
 	depends on EXPERIMENTAL
 	select CRC_ITU_T
 	help
 	  This is the "Juju" FireWire stack, a new alternative implementation
 	  designed for robustness and simplicity.  You can build either this
-	  stack, or the classic stack (the ieee1394 driver, ohci1394 etc.)
-	  or both.  Please read http://wiki.linux1394.org/JujuMigration before
-	  you enable the new stack.
+	  stack, or the old stack (the ieee1394 driver, ohci1394 etc.) or both.
+	  Please read http://wiki.linux1394.org/JujuMigration before you
+	  enable the new stack.
 
 	  To compile this driver as a module, say M here: the module will be
 	  called firewire-core.  It functionally replaces ieee1394, raw1394,
 	  and video1394.
 
-          NOTE:
-
-	  You should only build ONE of the stacks, unless you REALLY know what
-	  you are doing.
-
 config FIREWIRE_OHCI
-	tristate "Support for OHCI FireWire host controllers"
+	tristate "OHCI-1394 controllers"
 	depends on PCI && FIREWIRE
 	help
 	  Enable this driver if you have a FireWire controller based
@@ -33,12 +31,12 @@ config FIREWIRE_OHCI
 	  called firewire-ohci.  It replaces ohci1394 of the classic IEEE 1394
 	  stack.
 
-          NOTE:
+	  NOTE:
 
-	  You should only build ohci1394 or firewire-ohci, but not both.
-	  If you nevertheless want to install both, you should configure them
-	  only as modules and blacklist the driver(s) which you don't want to
-	  have auto-loaded.  Add either
+	  You should only build either firewire-ohci or the old ohci1394 driver,
+	  but not both.  If you nevertheless want to install both, you should
+	  configure them only as modules and blacklist the driver(s) which you
+	  don't want to have auto-loaded.  Add either
 
 	      blacklist firewire-ohci
 	  or
@@ -60,7 +58,7 @@ config FIREWIRE_OHCI_DEBUG
 	default y
 
 config FIREWIRE_SBP2
-	tristate "Support for storage devices (SBP-2 protocol driver)"
+	tristate "Storage devices (SBP-2 protocol)"
 	depends on FIREWIRE && SCSI
 	help
 	  This option enables you to use SBP-2 devices connected to a

drivers/firewire/fw-cdev.c

@@ -205,6 +205,7 @@ fw_device_op_read(struct file *file,
 	return dequeue_event(client, buffer, count);
 }
 
+/* caller must hold card->lock so that node pointers can be dereferenced here */
 static void
 fill_bus_reset_event(struct fw_cdev_event_bus_reset *event,
 		     struct client *client)
@@ -214,7 +215,6 @@ fill_bus_reset_event(struct fw_cdev_event_bus_reset *event,
 	event->closure	     = client->bus_reset_closure;
 	event->type          = FW_CDEV_EVENT_BUS_RESET;
 	event->generation    = client->device->generation;
-	smp_rmb();           /* node_id must not be older than generation */
 	event->node_id       = client->device->node_id;
 	event->local_node_id = card->local_node->node_id;
 	event->bm_node_id    = 0; /* FIXME: We don't track the BM. */
@@ -274,6 +274,7 @@ static int ioctl_get_info(struct client *client, void *buffer)
 {
 	struct fw_cdev_get_info *get_info = buffer;
 	struct fw_cdev_event_bus_reset bus_reset;
+	struct fw_card *card = client->device->card;
 	unsigned long ret = 0;
 
 	client->version = get_info->version;
@@ -299,13 +300,17 @@ static int ioctl_get_info(struct client *client, void *buffer)
 	client->bus_reset_closure = get_info->bus_reset_closure;
 	if (get_info->bus_reset != 0) {
 		void __user *uptr = u64_to_uptr(get_info->bus_reset);
+		unsigned long flags;
 
+		spin_lock_irqsave(&card->lock, flags);
 		fill_bus_reset_event(&bus_reset, client);
+		spin_unlock_irqrestore(&card->lock, flags);
+
 		if (copy_to_user(uptr, &bus_reset, sizeof(bus_reset)))
 			return -EFAULT;
 	}
 
-	get_info->card = client->device->card->index;
+	get_info->card = card->index;
 
 	return 0;
 }

drivers/firewire/fw-ohci.c

@@ -265,27 +265,25 @@ static void log_irqs(u32 evt)
 	    !(evt & OHCI1394_busReset))
 		return;
 
-	printk(KERN_DEBUG KBUILD_MODNAME ": IRQ "
-	       "%08x%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
-	       evt,
-	       evt & OHCI1394_selfIDComplete	? " selfID"		: "",
-	       evt & OHCI1394_RQPkt		? " AR_req"		: "",
-	       evt & OHCI1394_RSPkt		? " AR_resp"		: "",
-	       evt & OHCI1394_reqTxComplete	? " AT_req"		: "",
-	       evt & OHCI1394_respTxComplete	? " AT_resp"		: "",
-	       evt & OHCI1394_isochRx		? " IR"			: "",
-	       evt & OHCI1394_isochTx		? " IT"			: "",
-	       evt & OHCI1394_postedWriteErr	? " postedWriteErr"	: "",
-	       evt & OHCI1394_cycleTooLong	? " cycleTooLong"	: "",
-	       evt & OHCI1394_cycle64Seconds	? " cycle64Seconds"	: "",
-	       evt & OHCI1394_regAccessFail	? " regAccessFail"	: "",
-	       evt & OHCI1394_busReset		? " busReset"		: "",
-	       evt & ~(OHCI1394_selfIDComplete | OHCI1394_RQPkt |
-		       OHCI1394_RSPkt | OHCI1394_reqTxComplete |
-		       OHCI1394_respTxComplete | OHCI1394_isochRx |
-		       OHCI1394_isochTx | OHCI1394_postedWriteErr |
-		       OHCI1394_cycleTooLong | OHCI1394_cycle64Seconds |
-		       OHCI1394_regAccessFail | OHCI1394_busReset)
+	fw_notify("IRQ %08x%s%s%s%s%s%s%s%s%s%s%s%s%s\n", evt,
+	    evt & OHCI1394_selfIDComplete	? " selfID"		: "",
+	    evt & OHCI1394_RQPkt		? " AR_req"		: "",
+	    evt & OHCI1394_RSPkt		? " AR_resp"		: "",
+	    evt & OHCI1394_reqTxComplete	? " AT_req"		: "",
+	    evt & OHCI1394_respTxComplete	? " AT_resp"		: "",
+	    evt & OHCI1394_isochRx		? " IR"			: "",
+	    evt & OHCI1394_isochTx		? " IT"			: "",
+	    evt & OHCI1394_postedWriteErr	? " postedWriteErr"	: "",
+	    evt & OHCI1394_cycleTooLong		? " cycleTooLong"	: "",
+	    evt & OHCI1394_cycle64Seconds	? " cycle64Seconds"	: "",
+	    evt & OHCI1394_regAccessFail	? " regAccessFail"	: "",
+	    evt & OHCI1394_busReset		? " busReset"		: "",
+	    evt & ~(OHCI1394_selfIDComplete | OHCI1394_RQPkt |
+		    OHCI1394_RSPkt | OHCI1394_reqTxComplete |
+		    OHCI1394_respTxComplete | OHCI1394_isochRx |
+		    OHCI1394_isochTx | OHCI1394_postedWriteErr |
+		    OHCI1394_cycleTooLong | OHCI1394_cycle64Seconds |
+		    OHCI1394_regAccessFail | OHCI1394_busReset)
 						? " ?"			: "");
 }
 
@@ -308,23 +306,22 @@ static void log_selfids(int node_id, int generation, int self_id_count, u32 *s)
 	if (likely(!(param_debug & OHCI_PARAM_DEBUG_SELFIDS)))
 		return;
 
-	printk(KERN_DEBUG KBUILD_MODNAME ": %d selfIDs, generation %d, "
-	       "local node ID %04x\n", self_id_count, generation, node_id);
+	fw_notify("%d selfIDs, generation %d, local node ID %04x\n",
+		  self_id_count, generation, node_id);
 
 	for (; self_id_count--; ++s)
 		if ((*s & 1 << 23) == 0)
-			printk(KERN_DEBUG "selfID 0: %08x, phy %d [%c%c%c] "
-			       "%s gc=%d %s %s%s%s\n",
-			       *s, *s >> 24 & 63, _p(s, 6), _p(s, 4), _p(s, 2),
-			       speed[*s >> 14 & 3], *s >> 16 & 63,
-			       power[*s >> 8 & 7], *s >> 22 & 1 ? "L" : "",
-			       *s >> 11 & 1 ? "c" : "", *s & 2 ? "i" : "");
+			fw_notify("selfID 0: %08x, phy %d [%c%c%c] "
+			    "%s gc=%d %s %s%s%s\n",
+			    *s, *s >> 24 & 63, _p(s, 6), _p(s, 4), _p(s, 2),
+			    speed[*s >> 14 & 3], *s >> 16 & 63,
+			    power[*s >> 8 & 7], *s >> 22 & 1 ? "L" : "",
+			    *s >> 11 & 1 ? "c" : "", *s & 2 ? "i" : "");
 		else
-			printk(KERN_DEBUG "selfID n: %08x, phy %d "
-			       "[%c%c%c%c%c%c%c%c]\n",
-			       *s, *s >> 24 & 63,
-			       _p(s, 16), _p(s, 14), _p(s, 12), _p(s, 10),
-			       _p(s,  8), _p(s,  6), _p(s,  4), _p(s,  2));
+			fw_notify("selfID n: %08x, phy %d [%c%c%c%c%c%c%c%c]\n",
+			    *s, *s >> 24 & 63,
+			    _p(s, 16), _p(s, 14), _p(s, 12), _p(s, 10),
+			    _p(s,  8), _p(s,  6), _p(s,  4), _p(s,  2));
 }
 
 static const char *evts[] = {
@@ -373,15 +370,14 @@ static void log_ar_at_event(char dir, int speed, u32 *header, int evt)
 			evt = 0x1f;
 
 	if (evt == OHCI1394_evt_bus_reset) {
-		printk(KERN_DEBUG "A%c evt_bus_reset, generation %d\n",
-		       dir, (header[2] >> 16) & 0xff);
+		fw_notify("A%c evt_bus_reset, generation %d\n",
+		    dir, (header[2] >> 16) & 0xff);
 		return;
 	}
 
 	if (header[0] == ~header[1]) {
-		printk(KERN_DEBUG "A%c %s, %s, %08x\n",
-		       dir, evts[evt], phys[header[0] >> 30 & 0x3],
-		       header[0]);
+		fw_notify("A%c %s, %s, %08x\n",
+		    dir, evts[evt], phys[header[0] >> 30 & 0x3], header[0]);
 		return;
 	}
 
@@ -400,24 +396,23 @@ static void log_ar_at_event(char dir, int speed, u32 *header, int evt)
 
 	switch (tcode) {
 	case 0xe: case 0xa:
-		printk(KERN_DEBUG "A%c %s, %s\n",
-		       dir, evts[evt], tcodes[tcode]);
+		fw_notify("A%c %s, %s\n", dir, evts[evt], tcodes[tcode]);
 		break;
 	case 0x0: case 0x1: case 0x4: case 0x5: case 0x9:
-		printk(KERN_DEBUG "A%c spd %x tl %02x, "
-		       "%04x -> %04x, %s, "
-		       "%s, %04x%08x%s\n",
-		       dir, speed, header[0] >> 10 & 0x3f,
-		       header[1] >> 16, header[0] >> 16, evts[evt],
-		       tcodes[tcode], header[1] & 0xffff, header[2], specific);
+		fw_notify("A%c spd %x tl %02x, "
+		    "%04x -> %04x, %s, "
+		    "%s, %04x%08x%s\n",
+		    dir, speed, header[0] >> 10 & 0x3f,
+		    header[1] >> 16, header[0] >> 16, evts[evt],
+		    tcodes[tcode], header[1] & 0xffff, header[2], specific);
 		break;
 	default:
-		printk(KERN_DEBUG "A%c spd %x tl %02x, "
-		       "%04x -> %04x, %s, "
-		       "%s%s\n",
-		       dir, speed, header[0] >> 10 & 0x3f,
-		       header[1] >> 16, header[0] >> 16, evts[evt],
-		       tcodes[tcode], specific);
+		fw_notify("A%c spd %x tl %02x, "
+		    "%04x -> %04x, %s, "
+		    "%s%s\n",
+		    dir, speed, header[0] >> 10 & 0x3f,
+		    header[1] >> 16, header[0] >> 16, evts[evt],
+		    tcodes[tcode], specific);
 	}
 }
 
@@ -548,6 +543,11 @@ static __le32 *handle_ar_packet(struct ar_context *ctx, __le32 *buffer)
 		p.header_length = 12;
 		p.payload_length = 0;
 		break;
+
+	default:
+		/* FIXME: Stop context, discard everything, and restart? */
+		p.header_length = 0;
+		p.payload_length = 0;
 	}
 
 	p.payload = (void *) buffer + p.header_length;
@@ -1468,6 +1468,9 @@ static int ohci_enable(struct fw_card *card, u32 *config_rom, size_t length)
 	reg_write(ohci, OHCI1394_HCControlClear,
 		  OHCI1394_HCControl_noByteSwapData);
 
+	reg_write(ohci, OHCI1394_SelfIDBuffer, ohci->self_id_bus);
+	reg_write(ohci, OHCI1394_LinkControlClear,
+		  OHCI1394_LinkControl_rcvPhyPkt);
 	reg_write(ohci, OHCI1394_LinkControlSet,
 		  OHCI1394_LinkControl_rcvSelfID |
 		  OHCI1394_LinkControl_cycleTimerEnable |
@@ -1481,7 +1484,6 @@ static int ohci_enable(struct fw_card *card, u32 *config_rom, size_t length)
 	ar_context_run(&ohci->ar_request_ctx);
 	ar_context_run(&ohci->ar_response_ctx);
 
-	reg_write(ohci, OHCI1394_SelfIDBuffer, ohci->self_id_bus);
 	reg_write(ohci, OHCI1394_PhyUpperBound, 0x00010000);
 	reg_write(ohci, OHCI1394_IntEventClear, ~0);
 	reg_write(ohci, OHCI1394_IntMaskClear, ~0);

drivers/firewire/fw-transaction.c

@@ -20,6 +20,7 @@
 
 #include <linux/completion.h>
 #include <linux/kernel.h>
+#include <linux/kref.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -297,37 +298,55 @@ EXPORT_SYMBOL(fw_send_request);
 struct fw_phy_packet {
 	struct fw_packet packet;
 	struct completion done;
+	struct kref kref;
 };
 
-static void
-transmit_phy_packet_callback(struct fw_packet *packet,
-			     struct fw_card *card, int status)
+static void phy_packet_release(struct kref *kref)
+{
+	struct fw_phy_packet *p =
+			container_of(kref, struct fw_phy_packet, kref);
+	kfree(p);
+}
+
+static void transmit_phy_packet_callback(struct fw_packet *packet,
+					 struct fw_card *card, int status)
 {
 	struct fw_phy_packet *p =
 			container_of(packet, struct fw_phy_packet, packet);
 
 	complete(&p->done);
+	kref_put(&p->kref, phy_packet_release);
 }
 
 void fw_send_phy_config(struct fw_card *card,
 			int node_id, int generation, int gap_count)
 {
-	struct fw_phy_packet p;
+	struct fw_phy_packet *p;
+	long timeout = DIV_ROUND_UP(HZ, 10);
 	u32 data = PHY_IDENTIFIER(PHY_PACKET_CONFIG) |
 		   PHY_CONFIG_ROOT_ID(node_id) |
 		   PHY_CONFIG_GAP_COUNT(gap_count);
 
-	p.packet.header[0] = data;
-	p.packet.header[1] = ~data;
-	p.packet.header_length = 8;
-	p.packet.payload_length = 0;
-	p.packet.speed = SCODE_100;
-	p.packet.generation = generation;
-	p.packet.callback = transmit_phy_packet_callback;
-	init_completion(&p.done);
-
-	card->driver->send_request(card, &p.packet);
-	wait_for_completion(&p.done);
+	p = kmalloc(sizeof(*p), GFP_KERNEL);
+	if (p == NULL)
+		return;
+
+	p->packet.header[0] = data;
+	p->packet.header[1] = ~data;
+	p->packet.header_length = 8;
+	p->packet.payload_length = 0;
+	p->packet.speed = SCODE_100;
+	p->packet.generation = generation;
+	p->packet.callback = transmit_phy_packet_callback;
+	init_completion(&p->done);
+	kref_set(&p->kref, 2);
+
+	card->driver->send_request(card, &p->packet);
+	timeout = wait_for_completion_timeout(&p->done, timeout);
+	kref_put(&p->kref, phy_packet_release);
+
+	/* will leak p if the callback is never executed */
+	WARN_ON(timeout == 0);
 }
 
 void fw_flush_transactions(struct fw_card *card)
@@ -572,7 +591,8 @@ allocate_request(struct fw_packet *p)
 		break;
 
 	default:
-		BUG();
+		fw_error("ERROR - corrupt request received - %08x %08x %08x\n",
+			 p->header[0], p->header[1], p->header[2]);
 		return NULL;
 	}