Linux 3.2.9

commit 822bfa51ce upstream.

"nframes" comes from the user and "nframes * CD_FRAMESIZE_RAW" can wrap
on 32 bit systems.  That would have been ok if we used the same wrapped
value for the copy, but we use a shifted value.  We should just use the
checked version of copy_to_user() because it's not going to make a
difference to the speed.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Documentation/HOWTO

@@ -275,8 +275,8 @@ versions.
 If no 2.6.x.y kernel is available, then the highest numbered 2.6.x
 kernel is the current stable kernel.
 
-2.6.x.y are maintained by the "stable" team <stable@kernel.org>, and are
-released as needs dictate.  The normal release period is approximately 
+2.6.x.y are maintained by the "stable" team <stable@vger.kernel.org>, and
+are released as needs dictate.  The normal release period is approximately
 two weeks, but it can be longer if there are no pressing problems.  A
 security-related problem, instead, can cause a release to happen almost
 instantly.

Documentation/development-process/5.Posting

@@ -271,10 +271,10 @@ copies should go to:
    the linux-kernel list.
 
  - If you are fixing a bug, think about whether the fix should go into the
-   next stable update.  If so, stable@kernel.org should get a copy of the
-   patch.  Also add a "Cc: stable@kernel.org" to the tags within the patch
-   itself; that will cause the stable team to get a notification when your
-   fix goes into the mainline.
+   next stable update.  If so, stable@vger.kernel.org should get a copy of
+   the patch.  Also add a "Cc: stable@vger.kernel.org" to the tags within
+   the patch itself; that will cause the stable team to get a notification
+   when your fix goes into the mainline.
 
 When selecting recipients for a patch, it is good to have an idea of who
 you think will eventually accept the patch and get it merged.  While it

Documentation/usb/usbmon.txt

@@ -47,10 +47,11 @@ This allows to filter away annoying devices that talk continuously.
 
 2. Find which bus connects to the desired device
 
-Run "cat /proc/bus/usb/devices", and find the T-line which corresponds to
-the device. Usually you do it by looking for the vendor string. If you have
-many similar devices, unplug one and compare two /proc/bus/usb/devices outputs.
-The T-line will have a bus number. Example:
+Run "cat /sys/kernel/debug/usb/devices", and find the T-line which corresponds
+to the device. Usually you do it by looking for the vendor string. If you have
+many similar devices, unplug one and compare the two
+/sys/kernel/debug/usb/devices outputs. The T-line will have a bus number.
+Example:
 
 T:  Bus=03 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12  MxCh= 0
 D:  Ver= 1.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
@@ -58,7 +59,10 @@ P:  Vendor=0557 ProdID=2004 Rev= 1.00
 S:  Manufacturer=ATEN
 S:  Product=UC100KM V2.00
 
-Bus=03 means it's bus 3.
+"Bus=03" means it's bus 3. Alternatively, you can look at the output from
+"lsusb" and get the bus number from the appropriate line. Example:
+
+Bus 003 Device 002: ID 0557:2004 ATEN UC100KM V2.00
 
 3. Start 'cat'
 

MAINTAINERS

@@ -6258,7 +6258,7 @@ F:	arch/alpha/kernel/srm_env.c
 
 STABLE BRANCH
 M:	Greg Kroah-Hartman <greg@kroah.com>
-L:	stable@kernel.org
+L:	stable@vger.kernel.org
 S:	Maintained
 
 STAGING SUBSYSTEM

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 2
-SUBLEVEL = 0
+SUBLEVEL = 9
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 

arch/arm/common/pl330.c

@@ -1496,12 +1496,13 @@ int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op)
 	struct pl330_thread *thrd = ch_id;
 	struct pl330_dmac *pl330;
 	unsigned long flags;
-	int ret = 0, active = thrd->req_running;
+	int ret = 0, active;
 
 	if (!thrd || thrd->free || thrd->dmac->state == DYING)
 		return -EINVAL;
 
 	pl330 = thrd->dmac;
+	active = thrd->req_running;
 
 	spin_lock_irqsave(&pl330->lock, flags);
 

arch/arm/include/asm/assembler.h

@@ -137,6 +137,11 @@
 	disable_irq
 	.endm
 
+	.macro	save_and_disable_irqs_notrace, oldcpsr
+	mrs	\oldcpsr, cpsr
+	disable_irq_notrace
+	.endm
+
 /*
  * Restore interrupt state previously stored in a register.  We don't
  * guarantee that this will preserve the flags.

arch/arm/kernel/ptrace.c

@@ -699,10 +699,13 @@ static int vfp_set(struct task_struct *target,
 {
 	int ret;
 	struct thread_info *thread = task_thread_info(target);
-	struct vfp_hard_struct new_vfp = thread->vfpstate.hard;
+	struct vfp_hard_struct new_vfp;
 	const size_t user_fpregs_offset = offsetof(struct user_vfp, fpregs);
 	const size_t user_fpscr_offset = offsetof(struct user_vfp, fpscr);
 
+	vfp_sync_hwstate(thread);
+	new_vfp = thread->vfpstate.hard;
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				  &new_vfp.fpregs,
 				  user_fpregs_offset,
@@ -723,9 +726,8 @@ static int vfp_set(struct task_struct *target,
 	if (ret)
 		return ret;
 
-	vfp_sync_hwstate(thread);
-	thread->vfpstate.hard = new_vfp;
 	vfp_flush_hwstate(thread);
+	thread->vfpstate.hard = new_vfp;
 
 	return 0;
 }

arch/arm/kernel/signal.c

@@ -227,6 +227,8 @@ static int restore_vfp_context(struct vfp_sigframe __user *frame)
 	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
 		return -EINVAL;
 
+	vfp_flush_hwstate(thread);
+
 	/*
 	 * Copy the floating point registers. There can be unused
 	 * registers see asm/hwcap.h for details.
@@ -251,9 +253,6 @@ static int restore_vfp_context(struct vfp_sigframe __user *frame)
 	__get_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
 	__get_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
 
-	if (!err)
-		vfp_flush_hwstate(thread);
-
 	return err ? -EFAULT : 0;
 }
 

arch/arm/mach-at91/at91rm9200_devices.c

@@ -83,7 +83,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data) {}
  *  USB Device (Gadget)
  * -------------------------------------------------------------------- */
 
-#ifdef CONFIG_USB_AT91
+#if defined(CONFIG_USB_AT91) || defined(CONFIG_USB_AT91_MODULE)
 static struct at91_udc_data udc_data;
 
 static struct resource udc_resources[] = {

arch/arm/mach-at91/at91sam9260_devices.c

@@ -84,7 +84,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data) {}
  *  USB Device (Gadget)
  * -------------------------------------------------------------------- */
 
-#ifdef CONFIG_USB_AT91
+#if defined(CONFIG_USB_AT91) || defined(CONFIG_USB_AT91_MODULE)
 static struct at91_udc_data udc_data;
 
 static struct resource udc_resources[] = {

arch/arm/mach-at91/at91sam9261_devices.c

@@ -87,7 +87,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data) {}
  *  USB Device (Gadget)
  * -------------------------------------------------------------------- */
 
-#ifdef CONFIG_USB_AT91
+#if defined(CONFIG_USB_AT91) || defined(CONFIG_USB_AT91_MODULE)
 static struct at91_udc_data udc_data;
 
 static struct resource udc_resources[] = {

arch/arm/mach-at91/at91sam9263_devices.c

@@ -92,7 +92,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data) {}
  *  USB Device (Gadget)
  * -------------------------------------------------------------------- */
 
-#ifdef CONFIG_USB_AT91
+#if defined(CONFIG_USB_AT91) || defined(CONFIG_USB_AT91_MODULE)
 static struct at91_udc_data udc_data;
 
 static struct resource udc_resources[] = {

arch/arm/mach-at91/setup.c

@@ -27,9 +27,12 @@ EXPORT_SYMBOL(at91_soc_initdata);
 void __init at91rm9200_set_type(int type)
 {
 	if (type == ARCH_REVISON_9200_PQFP)
-		at91_soc_initdata.subtype = AT91_SOC_RM9200_BGA;
-	else
 		at91_soc_initdata.subtype = AT91_SOC_RM9200_PQFP;
+	else
+		at91_soc_initdata.subtype = AT91_SOC_RM9200_BGA;
+
+	pr_info("AT91: filled in soc subtype: %s\n",
+		at91_get_soc_subtype(&at91_soc_initdata));
 }
 
 void __init at91_init_irq_default(void)

arch/arm/mach-omap2/gpmc.c

@@ -528,7 +528,13 @@ int gpmc_cs_configure(int cs, int cmd, int wval)
 
 	case GPMC_CONFIG_DEV_SIZE:
 		regval  = gpmc_cs_read_reg(cs, GPMC_CS_CONFIG1);
+
+		/* clear 2 target bits */
+		regval &= ~GPMC_CONFIG1_DEVICESIZE(3);
+
+		/* set the proper value */
 		regval |= GPMC_CONFIG1_DEVICESIZE(wval);
+
 		gpmc_cs_write_reg(cs, GPMC_CS_CONFIG1, regval);
 		break;
 

arch/arm/mach-omap2/vp.c

@@ -41,6 +41,11 @@ void __init omap_vp_init(struct voltagedomain *voltdm)
 	u32 val, sys_clk_rate, timeout, waittime;
 	u32 vddmin, vddmax, vstepmin, vstepmax;
 
+	if (!voltdm->pmic || !voltdm->pmic->uv_to_vsel) {
+		pr_err("%s: No PMIC info for vdd_%s\n", __func__, voltdm->name);
+		return;
+	}
+
 	if (!voltdm->read || !voltdm->write) {
 		pr_err("%s: No read/write API for accessing vdd_%s regs\n",
 			__func__, voltdm->name);

arch/arm/mach-ux500/Kconfig

@@ -7,6 +7,7 @@ config UX500_SOC_COMMON
 	select HAS_MTU
 	select ARM_ERRATA_753970
 	select ARM_ERRATA_754322
+	select ARM_ERRATA_764369
 
 menu "Ux500 SoC"
 

arch/arm/mach-ux500/board-mop500-sdi.c

@@ -233,6 +233,8 @@ void __init snowball_sdi_init(void)
 {
 	u32 periphid = 0x10480180;
 
+	/* On Snowball MMC_CAP_SD_HIGHSPEED isn't supported on sdi0 */
+	mop500_sdi0_data.capabilities &= ~MMC_CAP_SD_HIGHSPEED;
 	mop500_sdi2_data.capabilities |= MMC_CAP_MMC_HIGHSPEED;
 
 	/* On-board eMMC */

arch/arm/mm/cache-v7.S

@@ -54,9 +54,15 @@ loop1:
 	and	r1, r1, #7			@ mask of the bits for current cache only
 	cmp	r1, #2				@ see what cache we have at this level
 	blt	skip				@ skip if no cache, or just i-cache
+#ifdef CONFIG_PREEMPT
+	save_and_disable_irqs_notrace r9	@ make cssr&csidr read atomic
+#endif
 	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
 	isb					@ isb to sych the new cssr&csidr
 	mrc	p15, 1, r1, c0, c0, 0		@ read the new csidr
+#ifdef CONFIG_PREEMPT
+	restore_irqs_notrace r9
+#endif
 	and	r2, r1, #7			@ extract the length of the cache lines
 	add	r2, r2, #4			@ add 4 (line length offset)
 	ldr	r4, =0x3ff

arch/arm/mm/proc-v7.S

@@ -271,10 +271,6 @@ ENDPROC(cpu_v7_do_resume)
  *	Initialise TLB, Caches, and MMU state ready to switch the MMU
  *	on.  Return in r0 the new CP15 C1 control register setting.
  *
- *	We automatically detect if we have a Harvard cache, and use the
- *	Harvard cache control instructions insead of the unified cache
- *	control instructions.
- *
  *	This should be able to cover all ARMv7 cores.
  *
  *	It is assumed that:
@@ -373,9 +369,7 @@ __v7_setup:
 #endif
 
 3:	mov	r10, #0
-#ifdef HARVARD_CACHE
 	mcr	p15, 0, r10, c7, c5, 0		@ I+BTB cache invalidate
-#endif
 	dsb
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r10, c8, c7, 0		@ invalidate I + D TLBs

arch/ia64/kernel/acpi.c

@@ -429,22 +429,24 @@ static u32 __devinitdata pxm_flag[PXM_FLAG_LEN];
 static struct acpi_table_slit __initdata *slit_table;
 cpumask_t early_cpu_possible_map = CPU_MASK_NONE;
 
-static int get_processor_proximity_domain(struct acpi_srat_cpu_affinity *pa)
+static int __init
+get_processor_proximity_domain(struct acpi_srat_cpu_affinity *pa)
 {
 	int pxm;
 
 	pxm = pa->proximity_domain_lo;
-	if (ia64_platform_is("sn2"))
+	if (ia64_platform_is("sn2") || acpi_srat_revision >= 2)
 		pxm += pa->proximity_domain_hi[0] << 8;
 	return pxm;
 }
 
-static int get_memory_proximity_domain(struct acpi_srat_mem_affinity *ma)
+static int __init
+get_memory_proximity_domain(struct acpi_srat_mem_affinity *ma)
 {
 	int pxm;
 
 	pxm = ma->proximity_domain;
-	if (!ia64_platform_is("sn2"))
+	if (!ia64_platform_is("sn2") && acpi_srat_revision <= 1)
 		pxm &= 0xff;
 
 	return pxm;

arch/m68k/atari/config.c

@@ -414,9 +414,9 @@ void __init config_atari(void)
 					 * FDC val = 4 -> Supervisor only */
 		asm volatile ("\n"
 			"	.chip	68030\n"
-			"	pmove	%0@,%/tt1\n"
+			"	pmove	%0,%/tt1\n"
 			"	.chip	68k"
-			: : "a" (&tt1_val));
+			: : "m" (tt1_val));
 	} else {
 	        asm volatile ("\n"
 			"	.chip	68040\n"
@@ -569,10 +569,10 @@ static void atari_reset(void)
 			: "d0");
 	} else
 		asm volatile ("\n"
-			"	pmove	%0@,%%tc\n"
+			"	pmove	%0,%%tc\n"
 			"	jmp	%1@"
 			: /* no outputs */
-			: "a" (&tc_val), "a" (reset_addr));
+			: "m" (tc_val), "a" (reset_addr));
 }
 
 

arch/m68k/kernel/process_mm.c

@@ -189,8 +189,8 @@ void flush_thread(void)
 	current->thread.fs = __USER_DS;
 	if (!FPU_IS_EMU)
 		asm volatile (".chip 68k/68881\n\t"
-			      "frestore %0@\n\t"
-			      ".chip 68k" : : "a" (&zero));
+			      "frestore %0\n\t"
+			      ".chip 68k" : : "m" (zero));
 }
 
 /*

arch/m68k/kernel/process_no.c

@@ -163,8 +163,8 @@ void flush_thread(void)
 #ifdef CONFIG_FPU
 	if (!FPU_IS_EMU)
 		asm volatile (".chip 68k/68881\n\t"
-			      "frestore %0@\n\t"
-			      ".chip 68k" : : "a" (&zero));
+			      "frestore %0\n\t"
+			      ".chip 68k" : : "m" (zero));
 #endif
 }
 

arch/m68k/kernel/traps.c

@@ -552,13 +552,13 @@ static inline void bus_error030 (struct frame *fp)
 
 #ifdef DEBUG
 		asm volatile ("ptestr %3,%2@,#7,%0\n\t"
-			      "pmove %%psr,%1@"
-			      : "=a&" (desc)
-			      : "a" (&temp), "a" (addr), "d" (ssw));
+			      "pmove %%psr,%1"
+			      : "=a&" (desc), "=m" (temp)
+			      : "a" (addr), "d" (ssw));
 #else
 		asm volatile ("ptestr %2,%1@,#7\n\t"
-			      "pmove %%psr,%0@"
-			      : : "a" (&temp), "a" (addr), "d" (ssw));
+			      "pmove %%psr,%0"
+			      : "=m" (temp) : "a" (addr), "d" (ssw));
 #endif
 		mmusr = temp;
 
@@ -605,20 +605,18 @@ static inline void bus_error030 (struct frame *fp)
 			       !(ssw & RW) ? "write" : "read", addr,
 			       fp->ptregs.pc, ssw);
 			asm volatile ("ptestr #1,%1@,#0\n\t"
-				      "pmove %%psr,%0@"
-				      : /* no outputs */
-				      : "a" (&temp), "a" (addr));
+				      "pmove %%psr,%0"
+				      : "=m" (temp)
+				      : "a" (addr));
 			mmusr = temp;
 
 			printk ("level 0 mmusr is %#x\n", mmusr);
 #if 0
-			asm volatile ("pmove %%tt0,%0@"
-				      : /* no outputs */
-				      : "a" (&tlong));
+			asm volatile ("pmove %%tt0,%0"
+				      : "=m" (tlong));
 			printk("tt0 is %#lx, ", tlong);
-			asm volatile ("pmove %%tt1,%0@"
-				      : /* no outputs */
-				      : "a" (&tlong));
+			asm volatile ("pmove %%tt1,%0"
+				      : "=m" (tlong));
 			printk("tt1 is %#lx\n", tlong);
 #endif
 #ifdef DEBUG
@@ -668,13 +666,13 @@ static inline void bus_error030 (struct frame *fp)
 
 #ifdef DEBUG
 	asm volatile ("ptestr #1,%2@,#7,%0\n\t"
-		      "pmove %%psr,%1@"
-		      : "=a&" (desc)
-		      : "a" (&temp), "a" (addr));
+		      "pmove %%psr,%1"
+		      : "=a&" (desc), "=m" (temp)
+		      : "a" (addr));
 #else
 	asm volatile ("ptestr #1,%1@,#7\n\t"
-		      "pmove %%psr,%0@"
-		      : : "a" (&temp), "a" (addr));
+		      "pmove %%psr,%0"
+		      : "=m" (temp) : "a" (addr));
 #endif
 	mmusr = temp;
 

arch/m68k/mm/cache.c

@@ -52,9 +52,9 @@ static unsigned long virt_to_phys_slow(unsigned long vaddr)
 		unsigned long *descaddr;
 
 		asm volatile ("ptestr %3,%2@,#7,%0\n\t"
-			      "pmove %%psr,%1@"
-			      : "=a&" (descaddr)
-			      : "a" (&mmusr), "a" (vaddr), "d" (get_fs().seg));
+			      "pmove %%psr,%1"
+			      : "=a&" (descaddr), "=m" (mmusr)
+			      : "a" (vaddr), "d" (get_fs().seg));
 		if (mmusr & (MMU_I|MMU_B|MMU_L))
 			return 0;
 		descaddr = phys_to_virt((unsigned long)descaddr);

arch/powerpc/include/asm/time.h

@@ -219,5 +219,7 @@ DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array);
 extern void secondary_cpu_time_init(void);
 extern void iSeries_time_init_early(void);
 
+extern void decrementer_check_overflow(void);
+
 #endif /* __KERNEL__ */
 #endif /* __POWERPC_TIME_H */

arch/powerpc/kernel/irq.c

@@ -164,16 +164,13 @@ notrace void arch_local_irq_restore(unsigned long en)
 	 */
 	local_paca->hard_enabled = en;
 
-#ifndef CONFIG_BOOKE
-	/* On server, re-trigger the decrementer if it went negative since
-	 * some processors only trigger on edge transitions of the sign bit.
-	 *
-	 * BookE has a level sensitive decrementer (latches in TSR) so we
-	 * don't need that
+	/*
+	 * Trigger the decrementer if we have a pending event. Some processors
+	 * only trigger on edge transitions of the sign bit. We might also
+	 * have disabled interrupts long enough that the decrementer wrapped
+	 * to positive.
 	 */
-	if ((int)mfspr(SPRN_DEC) < 0)
-		mtspr(SPRN_DEC, 1);
-#endif /* CONFIG_BOOKE */
+	decrementer_check_overflow();
 
 	/*
 	 * Force the delivery of pending soft-disabled interrupts on PS3.

arch/powerpc/kernel/perf_event.c

@@ -865,6 +865,7 @@ static void power_pmu_start(struct perf_event *event, int ef_flags)
 {
 	unsigned long flags;
 	s64 left;
+	unsigned long val;
 
 	if (!event->hw.idx || !event->hw.sample_period)
 		return;
@@ -880,7 +881,12 @@ static void power_pmu_start(struct perf_event *event, int ef_flags)
 
 	event->hw.state = 0;
 	left = local64_read(&event->hw.period_left);
-	write_pmc(event->hw.idx, left);
+
+	val = 0;
+	if (left < 0x80000000L)
+		val = 0x80000000L - left;
+
+	write_pmc(event->hw.idx, val);
 
 	perf_event_update_userpage(event);
 	perf_pmu_enable(event->pmu);

arch/powerpc/kernel/time.c

@@ -889,6 +889,15 @@ static void __init clocksource_init(void)
 	       clock->name, clock->mult, clock->shift);
 }
 
+void decrementer_check_overflow(void)
+{
+	u64 now = get_tb_or_rtc();
+	struct decrementer_clock *decrementer = &__get_cpu_var(decrementers);
+
+	if (now >= decrementer->next_tb)
+		set_dec(1);
+}
+
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev)
 {

arch/powerpc/platforms/pseries/hvCall_inst.c

@@ -109,7 +109,7 @@ static void probe_hcall_entry(void *ignored, unsigned long opcode, unsigned long
 	if (opcode > MAX_HCALL_OPCODE)
 		return;
 
-	h = &get_cpu_var(hcall_stats)[opcode / 4];
+	h = &__get_cpu_var(hcall_stats)[opcode / 4];
 	h->tb_start = mftb();
 	h->purr_start = mfspr(SPRN_PURR);
 }
@@ -126,8 +126,6 @@ static void probe_hcall_exit(void *ignored, unsigned long opcode, unsigned long
 	h->num_calls++;
 	h->tb_total += mftb() - h->tb_start;
 	h->purr_total += mfspr(SPRN_PURR) - h->purr_start;
-
-	put_cpu_var(hcall_stats);
 }
 
 static int __init hcall_inst_init(void)

arch/powerpc/platforms/pseries/lpar.c

@@ -554,6 +554,7 @@ void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
 		goto out;
 
 	(*depth)++;
+	preempt_disable();
 	trace_hcall_entry(opcode, args);
 	(*depth)--;
 
@@ -576,6 +577,7 @@ void __trace_hcall_exit(long opcode, unsigned long retval,
 
 	(*depth)++;
 	trace_hcall_exit(opcode, retval, retbuf);
+	preempt_enable();
 	(*depth)--;
 
 out:

arch/s390/kernel/time.c

@@ -113,11 +113,14 @@ static void fixup_clock_comparator(unsigned long long delta)
 static int s390_next_ktime(ktime_t expires,
 			   struct clock_event_device *evt)
 {
+	struct timespec ts;
 	u64 nsecs;
 
-	nsecs = ktime_to_ns(ktime_sub(expires, ktime_get_monotonic_offset()));
+	ts.tv_sec = ts.tv_nsec = 0;
+	monotonic_to_bootbased(&ts);
+	nsecs = ktime_to_ns(ktime_add(timespec_to_ktime(ts), expires));
 	do_div(nsecs, 125);
-	S390_lowcore.clock_comparator = TOD_UNIX_EPOCH + (nsecs << 9);
+	S390_lowcore.clock_comparator = sched_clock_base_cc + (nsecs << 9);
 	set_clock_comparator(S390_lowcore.clock_comparator);
 	return 0;
 }

arch/score/kernel/entry.S

@@ -408,7 +408,7 @@ ENTRY(handle_sys)
 	sw	r9, [r0, PT_EPC]
 
 	cmpi.c	r27, __NR_syscalls 	# check syscall number
-	bgtu	illegal_syscall
+	bgeu	illegal_syscall
 
 	slli	r8, r27, 2		# get syscall routine
 	la	r11, sys_call_table

arch/x86/include/asm/amd_nb.h

@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_AMD_NB_H
 #define _ASM_X86_AMD_NB_H
 
+#include <linux/ioport.h>
 #include <linux/pci.h>
 
 struct amd_nb_bus_dev_range {
@@ -13,6 +14,7 @@ extern const struct pci_device_id amd_nb_misc_ids[];
 extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[];
 
 extern bool early_is_amd_nb(u32 value);
+extern struct resource *amd_get_mmconfig_range(struct resource *res);
 extern int amd_cache_northbridges(void);
 extern void amd_flush_garts(void);
 extern int amd_numa_init(void);

arch/x86/include/asm/i387.h

@@ -29,8 +29,8 @@ extern unsigned int sig_xstate_size;
 extern void fpu_init(void);
 extern void mxcsr_feature_mask_init(void);
 extern int init_fpu(struct task_struct *child);
-extern asmlinkage void math_state_restore(void);
-extern void __math_state_restore(void);
+extern void __math_state_restore(struct task_struct *);
+extern void math_state_restore(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
 extern user_regset_active_fn fpregs_active, xfpregs_active;
@@ -212,19 +212,11 @@ static inline void fpu_fxsave(struct fpu *fpu)
 
 #endif	/* CONFIG_X86_64 */
 
-/* We need a safe address that is cheap to find and that is already
-   in L1 during context switch. The best choices are unfortunately
-   different for UP and SMP */
-#ifdef CONFIG_SMP
-#define safe_address (__per_cpu_offset[0])
-#else
-#define safe_address (kstat_cpu(0).cpustat.user)
-#endif
-
 /*
- * These must be called with preempt disabled
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact.
  */
-static inline void fpu_save_init(struct fpu *fpu)
+static inline int fpu_save_init(struct fpu *fpu)
 {
 	if (use_xsave()) {
 		fpu_xsave(fpu);
@@ -233,33 +225,33 @@ static inline void fpu_save_init(struct fpu *fpu)
 		 * xsave header may indicate the init state of the FP.
 		 */
 		if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
-			return;
+			return 1;
 	} else if (use_fxsr()) {
 		fpu_fxsave(fpu);
 	} else {
 		asm volatile("fnsave %[fx]; fwait"
 			     : [fx] "=m" (fpu->state->fsave));
-		return;
+		return 0;
 	}
 
-	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES))
+	/*
+	 * If exceptions are pending, we need to clear them so
+	 * that we don't randomly get exceptions later.
+	 *
+	 * FIXME! Is this perhaps only true for the old-style
+	 * irq13 case? Maybe we could leave the x87 state
+	 * intact otherwise?
+	 */
+	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
 		asm volatile("fnclex");
-
-	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
-	   is pending.  Clear the x87 state here by setting it to fixed
-	   values. safe_address is a random variable that should be in L1 */
-	alternative_input(
-		ASM_NOP8 ASM_NOP2,
-		"emms\n\t"	  	/* clear stack tags */
-		"fildl %P[addr]",	/* set F?P to defined value */
-		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (safe_address));
+		return 0;
+	}
+	return 1;
 }
 
-static inline void __save_init_fpu(struct task_struct *tsk)
+static inline int __save_init_fpu(struct task_struct *tsk)
 {
-	fpu_save_init(&tsk->thread.fpu);
-	task_thread_info(tsk)->status &= ~TS_USEDFPU;
+	return fpu_save_init(&tsk->thread.fpu);
 }
 
 static inline int fpu_fxrstor_checking(struct fpu *fpu)
@@ -280,40 +272,186 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
 	return fpu_restore_checking(&tsk->thread.fpu);
 }
 
+/*
+ * Software FPU state helpers. Careful: these need to
+ * be preemption protection *and* they need to be
+ * properly paired with the CR0.TS changes!
+ */
+static inline int __thread_has_fpu(struct task_struct *tsk)
+{
+	return tsk->thread.has_fpu;
+}
+
+/* Must be paired with an 'stts' after! */
+static inline void __thread_clear_has_fpu(struct task_struct *tsk)
+{
+	tsk->thread.has_fpu = 0;
+}
+
+/* Must be paired with a 'clts' before! */
+static inline void __thread_set_has_fpu(struct task_struct *tsk)
+{
+	tsk->thread.has_fpu = 1;
+}
+
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void __thread_fpu_end(struct task_struct *tsk)
+{
+	__thread_clear_has_fpu(tsk);
+	stts();
+}
+
+static inline void __thread_fpu_begin(struct task_struct *tsk)
+{
+	clts();
+	__thread_set_has_fpu(tsk);
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ *  - switch_fpu_prepare() saves the old state and
+ *    sets the new state of the CR0.TS bit. This is
+ *    done within the context of the old process.
+ *
+ *  - switch_fpu_finish() restores the new state as
+ *    necessary.
+ */
+typedef struct { int preload; } fpu_switch_t;
+
+/*
+ * FIXME! We could do a totally lazy restore, but we need to
+ * add a per-cpu "this was the task that last touched the FPU
+ * on this CPU" variable, and the task needs to have a "I last
+ * touched the FPU on this CPU" and check them.
+ *
+ * We don't do that yet, so "fpu_lazy_restore()" always returns
+ * false, but some day..
+ */
+#define fpu_lazy_restore(tsk) (0)
+#define fpu_lazy_state_intact(tsk) do { } while (0)
+
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new)
+{
+	fpu_switch_t fpu;
+
+	fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+	if (__thread_has_fpu(old)) {
+		if (__save_init_fpu(old))
+			fpu_lazy_state_intact(old);
+		__thread_clear_has_fpu(old);
+		old->fpu_counter++;
+
+		/* Don't change CR0.TS if we just switch! */
+		if (fpu.preload) {
+			__thread_set_has_fpu(new);
+			prefetch(new->thread.fpu.state);
+		} else
+			stts();
+	} else {
+		old->fpu_counter = 0;
+		if (fpu.preload) {
+			if (fpu_lazy_restore(new))
+				fpu.preload = 0;
+			else
+				prefetch(new->thread.fpu.state);
+			__thread_fpu_begin(new);
+		}
+	}
+	return fpu;
+}
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
+{
+	if (fpu.preload)
+		__math_state_restore(new);
+}
+
 /*
  * Signal frame handlers...
  */
 extern int save_i387_xstate(void __user *buf);
 extern int restore_i387_xstate(void __user *buf);
 
-static inline void __unlazy_fpu(struct task_struct *tsk)
-{
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
-		__save_init_fpu(tsk);
-		stts();
-	} else
-		tsk->fpu_counter = 0;
-}
-
 static inline void __clear_fpu(struct task_struct *tsk)
 {
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+	if (__thread_has_fpu(tsk)) {
 		/* Ignore delayed exceptions from user space */
 		asm volatile("1: fwait\n"
 			     "2:\n"
 			     _ASM_EXTABLE(1b, 2b));
-		task_thread_info(tsk)->status &= ~TS_USEDFPU;
-		stts();
+		__thread_fpu_end(tsk);
 	}
 }
 
+/*
+ * Were we in an interrupt that interrupted kernel mode?
+ *
+ * We can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * pair does nothing at all: the thread must not have fpu (so
+ * that we don't try to save the FPU state), and TS must
+ * be set (so that the clts/stts pair does nothing that is
+ * visible in the interrupted kernel thread).
+ */
+static inline bool interrupted_kernel_fpu_idle(void)
+{
+	return !__thread_has_fpu(current) &&
+		(read_cr0() & X86_CR0_TS);
+}
+
+/*
+ * Were we in user mode (or vm86 mode) when we were
+ * interrupted?
+ *
+ * Doing kernel_fpu_begin/end() is ok if we are running
+ * in an interrupt context from user mode - we'll just
+ * save the FPU state as required.
+ */
+static inline bool interrupted_user_mode(void)
+{
+	struct pt_regs *regs = get_irq_regs();
+	return regs && user_mode_vm(regs);
+}
+
+/*
+ * Can we use the FPU in kernel mode with the
+ * whole "kernel_fpu_begin/end()" sequence?
+ *
+ * It's always ok in process context (ie "not interrupt")
+ * but it is sometimes ok even from an irq.
+ */
+static inline bool irq_fpu_usable(void)
+{
+	return !in_interrupt() ||
+		interrupted_user_mode() ||
+		interrupted_kernel_fpu_idle();
+}
+
 static inline void kernel_fpu_begin(void)
 {
-	struct thread_info *me = current_thread_info();
+	struct task_struct *me = current;
+
+	WARN_ON_ONCE(!irq_fpu_usable());
 	preempt_disable();
-	if (me->status & TS_USEDFPU)
-		__save_init_fpu(me->task);
-	else
+	if (__thread_has_fpu(me)) {
+		__save_init_fpu(me);
+		__thread_clear_has_fpu(me);
+		/* We do 'stts()' in kernel_fpu_end() */
+	} else
 		clts();
 }
 
@@ -323,14 +461,6 @@ static inline void kernel_fpu_end(void)
 	preempt_enable();
 }
 
-static inline bool irq_fpu_usable(void)
-{
-	struct pt_regs *regs;
-
-	return !in_interrupt() || !(regs = get_irq_regs()) || \
-		user_mode(regs) || (read_cr0() & X86_CR0_TS);
-}
-
 /*
  * Some instructions like VIA's padlock instructions generate a spurious
  * DNA fault but don't modify SSE registers. And these instructions
@@ -362,21 +492,65 @@ static inline void irq_ts_restore(int TS_state)
 		stts();
 }
 
+/*
+ * The question "does this thread have fpu access?"
+ * is slightly racy, since preemption could come in
+ * and revoke it immediately after the test.
+ *
+ * However, even in that very unlikely scenario,
+ * we can just assume we have FPU access - typically
+ * to save the FP state - we'll just take a #NM
+ * fault and get the FPU access back.
+ *
+ * The actual user_fpu_begin/end() functions
+ * need to be preemption-safe, though.
+ *
+ * NOTE! user_fpu_end() must be used only after you
+ * have saved the FP state, and user_fpu_begin() must
+ * be used only immediately before restoring it.
+ * These functions do not do any save/restore on
+ * their own.
+ */
+static inline int user_has_fpu(void)
+{
+	return __thread_has_fpu(current);
+}
+
+static inline void user_fpu_end(void)
+{
+	preempt_disable();
+	__thread_fpu_end(current);
+	preempt_enable();
+}
+
+static inline void user_fpu_begin(void)
+{
+	preempt_disable();
+	if (!user_has_fpu())
+		__thread_fpu_begin(current);
+	preempt_enable();
+}
+
 /*
  * These disable preemption on their own and are safe
  */
 static inline void save_init_fpu(struct task_struct *tsk)
 {
+	WARN_ON_ONCE(!__thread_has_fpu(tsk));
 	preempt_disable();
 	__save_init_fpu(tsk);
-	stts();
+	__thread_fpu_end(tsk);
 	preempt_enable();
 }
 
 static inline void unlazy_fpu(struct task_struct *tsk)
 {
 	preempt_disable();
-	__unlazy_fpu(tsk);
+	if (__thread_has_fpu(tsk)) {
+		__save_init_fpu(tsk);
+		__thread_fpu_end(tsk);
+	} else
+		tsk->fpu_counter = 0;
 	preempt_enable();
 }
 

arch/x86/include/asm/processor.h

@@ -456,6 +456,7 @@ struct thread_struct {
 	unsigned long		trap_no;
 	unsigned long		error_code;
 	/* floating point and extended processor state */
+	unsigned long		has_fpu;
 	struct fpu		fpu;
 #ifdef CONFIG_X86_32
 	/* Virtual 86 mode info */

arch/x86/include/asm/thread_info.h

@@ -242,8 +242,6 @@ static inline struct thread_info *current_thread_info(void)
  * ever touches our thread-synchronous status, so we don't
  * have to worry about atomic accesses.
  */
-#define TS_USEDFPU		0x0001	/* FPU was used by this task
-					   this quantum (SMP) */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
 #define TS_POLLING		0x0004	/* idle task polling need_resched,
 					   skip sending interrupt */

arch/x86/include/asm/uv/uv_bau.h

@@ -65,7 +65,7 @@
  * UV2: Bit 19 selects between
  *  (0): 10 microsecond timebase and
  *  (1): 80 microseconds
- *  we're using 655us, similar to UV1: 65 units of 10us
+ *  we're using 560us, similar to UV1: 65 units of 10us
  */
 #define UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD (9UL)
 #define UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD (15UL)
@@ -167,6 +167,7 @@
 #define FLUSH_RETRY_TIMEOUT		2
 #define FLUSH_GIVEUP			3
 #define FLUSH_COMPLETE			4
+#define FLUSH_RETRY_BUSYBUG		5
 
 /*
  * tuning the action when the numalink network is extremely delayed
@@ -235,10 +236,10 @@ struct bau_msg_payload {
 
 
 /*
- * Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * UV1 Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
  * see table 4.2.3.0.1 in broacast_assist spec.
  */
-struct bau_msg_header {
+struct uv1_bau_msg_header {
 	unsigned int	dest_subnodeid:6;	/* must be 0x10, for the LB */
 	/* bits 5:0 */
 	unsigned int	base_dest_nasid:15;	/* nasid of the first bit */
@@ -317,20 +318,88 @@ struct bau_msg_header {
 	/* bits 127:107 */
 };
 
+/*
+ * UV2 Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * see figure 9-2 of harp_sys.pdf
+ */
+struct uv2_bau_msg_header {
+	unsigned int	base_dest_nasid:15;	/* nasid of the first bit */
+	/* bits 14:0 */				/* in uvhub map */
+	unsigned int	dest_subnodeid:5;	/* must be 0x10, for the LB */
+	/* bits 19:15 */
+	unsigned int	rsvd_1:1;		/* must be zero */
+	/* bit 20 */
+	/* Address bits 59:21 */
+	/* bits 25:2 of address (44:21) are payload */
+	/* these next 24 bits become bytes 12-14 of msg */
+	/* bits 28:21 land in byte 12 */
+	unsigned int	replied_to:1;		/* sent as 0 by the source to
+						   byte 12 */
+	/* bit 21 */
+	unsigned int	msg_type:3;		/* software type of the
+						   message */
+	/* bits 24:22 */
+	unsigned int	canceled:1;		/* message canceled, resource
+						   is to be freed*/
+	/* bit 25 */
+	unsigned int	payload_1:3;		/* not currently used */
+	/* bits 28:26 */
+
+	/* bits 36:29 land in byte 13 */
+	unsigned int	payload_2a:3;		/* not currently used */
+	unsigned int	payload_2b:5;		/* not currently used */
+	/* bits 36:29 */
+
+	/* bits 44:37 land in byte 14 */
+	unsigned int	payload_3:8;		/* not currently used */
+	/* bits 44:37 */
+
+	unsigned int	rsvd_2:7;		/* reserved */
+	/* bits 51:45 */
+	unsigned int	swack_flag:1;		/* software acknowledge flag */
+	/* bit 52 */
+	unsigned int	rsvd_3a:3;		/* must be zero */
+	unsigned int	rsvd_3b:8;		/* must be zero */
+	unsigned int	rsvd_3c:8;		/* must be zero */
+	unsigned int	rsvd_3d:3;		/* must be zero */
+	/* bits 74:53 */
+	unsigned int	fairness:3;		/* usually zero */
+	/* bits 77:75 */
+
+	unsigned int	sequence:16;		/* message sequence number */
+	/* bits 93:78  Suppl_A  */
+	unsigned int	chaining:1;		/* next descriptor is part of
+						   this activation*/
+	/* bit 94 */
+	unsigned int	multilevel:1;		/* multi-level multicast
+						   format */
+	/* bit 95 */
+	unsigned int	rsvd_4:24;		/* ordered / source node /
+						   source subnode / aging
+						   must be zero */
+	/* bits 119:96 */
+	unsigned int	command:8;		/* message type */
+	/* bits 127:120 */
+};
+
 /*
  * The activation descriptor:
  * The format of the message to send, plus all accompanying control
  * Should be 64 bytes
  */
 struct bau_desc {
-	struct pnmask			distribution;
+	struct pnmask				distribution;
 	/*
 	 * message template, consisting of header and payload:
 	 */
-	struct bau_msg_header		header;
-	struct bau_msg_payload		payload;
+	union bau_msg_header {
+		struct uv1_bau_msg_header	uv1_hdr;
+		struct uv2_bau_msg_header	uv2_hdr;
+	} header;
+
+	struct bau_msg_payload			payload;
 };
-/*
+/* UV1:
  *   -payload--    ---------header------
  *   bytes 0-11    bits 41-56  bits 58-81
  *       A           B  (2)      C (3)
@@ -340,6 +409,16 @@ struct bau_desc {
  *   bytes 0-11  bytes 12-14  bytes 16-17  (byte 15 filled in by hw as vector)
  *   ------------payload queue-----------
  */
+/* UV2:
+ *   -payload--    ---------header------
+ *   bytes 0-11    bits 70-78  bits 21-44
+ *       A           B  (2)      C (3)
+ *
+ *            A/B/C are moved to:
+ *       A            C          B
+ *   bytes 0-11  bytes 12-14  bytes 16-17  (byte 15 filled in by hw as vector)
+ *   ------------payload queue-----------
+ */
 
 /*
  * The payload queue on the destination side is an array of these.
@@ -385,7 +464,6 @@ struct bau_pq_entry {
 struct msg_desc {
 	struct bau_pq_entry	*msg;
 	int			msg_slot;
-	int			swack_slot;
 	struct bau_pq_entry	*queue_first;
 	struct bau_pq_entry	*queue_last;
 };
@@ -439,6 +517,9 @@ struct ptc_stats {
 	unsigned long	s_retry_messages;	/* retry broadcasts */
 	unsigned long	s_bau_reenabled;	/* for bau enable/disable */
 	unsigned long	s_bau_disabled;		/* for bau enable/disable */
+	unsigned long	s_uv2_wars;		/* uv2 workaround, perm. busy */
+	unsigned long	s_uv2_wars_hw;		/* uv2 workaround, hiwater */
+	unsigned long	s_uv2_war_waits;	/* uv2 workaround, long waits */
 	/* destination statistics */
 	unsigned long	d_alltlb;		/* times all tlb's on this
 						   cpu were flushed */
@@ -511,9 +592,12 @@ struct bau_control {
 	short			osnode;
 	short			uvhub_cpu;
 	short			uvhub;
+	short			uvhub_version;
 	short			cpus_in_socket;
 	short			cpus_in_uvhub;
 	short			partition_base_pnode;
+	short			using_desc; /* an index, like uvhub_cpu */
+	unsigned int		inuse_map;
 	unsigned short		message_number;
 	unsigned short		uvhub_quiesce;
 	short			socket_acknowledge_count[DEST_Q_SIZE];
@@ -531,6 +615,7 @@ struct bau_control {
 	int			cong_response_us;
 	int			cong_reps;
 	int			cong_period;
+	unsigned long		clocks_per_100_usec;
 	cycles_t		period_time;
 	long			period_requests;
 	struct hub_and_pnode	*thp;
@@ -591,6 +676,11 @@ static inline void write_mmr_sw_ack(unsigned long mr)
 	uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
 }
 
+static inline void write_gmmr_sw_ack(int pnode, unsigned long mr)
+{
+	write_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
+}
+
 static inline unsigned long read_mmr_sw_ack(void)
 {
 	return read_lmmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);

arch/x86/include/asm/uv/uv_hub.h

@@ -318,13 +318,13 @@ uv_gpa_in_mmr_space(unsigned long gpa)
 /* UV global physical address --> socket phys RAM */
 static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa)
 {
-	unsigned long paddr = gpa & uv_hub_info->gpa_mask;
+	unsigned long paddr;
 	unsigned long remap_base = uv_hub_info->lowmem_remap_base;
 	unsigned long remap_top =  uv_hub_info->lowmem_remap_top;
 
 	gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
 		((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val);
-	gpa = gpa & uv_hub_info->gpa_mask;
+	paddr = gpa & uv_hub_info->gpa_mask;
 	if (paddr >= remap_base && paddr < remap_base + remap_top)
 		paddr -= remap_base;
 	return paddr;

arch/x86/kernel/amd_nb.c

@@ -119,6 +119,37 @@ bool __init early_is_amd_nb(u32 device)
 	return false;
 }
 
+struct resource *amd_get_mmconfig_range(struct resource *res)
+{
+	u32 address;
+	u64 base, msr;
+	unsigned segn_busn_bits;
+
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+		return NULL;
+
+	/* assume all cpus from fam10h have mmconfig */
+        if (boot_cpu_data.x86 < 0x10)
+		return NULL;
+
+	address = MSR_FAM10H_MMIO_CONF_BASE;
+	rdmsrl(address, msr);
+
+	/* mmconfig is not enabled */
+	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
+		return NULL;
+
+	base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT);
+
+	segn_busn_bits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) &
+			 FAM10H_MMIO_CONF_BUSRANGE_MASK;
+
+	res->flags = IORESOURCE_MEM;
+	res->start = base;
+	res->end = base + (1ULL<<(segn_busn_bits + 20)) - 1;
+	return res;
+}
+
 int amd_get_subcaches(int cpu)
 {
 	struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link;

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -769,7 +769,12 @@ void __init uv_system_init(void)
 	for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++)
 		uv_possible_blades +=
 		  hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8));
-	printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades());
+
+	/* uv_num_possible_blades() is really the hub count */
+	printk(KERN_INFO "UV: Found %d blades, %d hubs\n",
+			is_uv1_hub() ? uv_num_possible_blades() :
+			(uv_num_possible_blades() + 1) / 2,
+			uv_num_possible_blades());
 
 	bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
 	uv_blade_info = kzalloc(bytes, GFP_KERNEL);

arch/x86/kernel/cpu/intel_cacheinfo.c

@@ -326,8 +326,7 @@ static void __cpuinit amd_calc_l3_indices(struct amd_northbridge *nb)
 	l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
 }
 
-static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf,
-					int index)
+static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index)
 {
 	int node;
 
@@ -725,14 +724,16 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info);
 #define CPUID4_INFO_IDX(x, y)	(&((per_cpu(ici_cpuid4_info, x))[y]))
 
 #ifdef CONFIG_SMP
-static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
+
+static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index)
 {
-	struct _cpuid4_info	*this_leaf, *sibling_leaf;
-	unsigned long num_threads_sharing;
-	int index_msb, i, sibling;
+	struct _cpuid4_info *this_leaf;
+	int ret, i, sibling;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
+	ret = 0;
+	if (index == 3) {
+		ret = 1;
 		for_each_cpu(i, cpu_llc_shared_mask(cpu)) {
 			if (!per_cpu(ici_cpuid4_info, i))
 				continue;
@@ -743,8 +744,35 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 				set_bit(sibling, this_leaf->shared_cpu_map);
 			}
 		}
-		return;
+	} else if ((c->x86 == 0x15) && ((index == 1) || (index == 2))) {
+		ret = 1;
+		for_each_cpu(i, cpu_sibling_mask(cpu)) {
+			if (!per_cpu(ici_cpuid4_info, i))
+				continue;
+			this_leaf = CPUID4_INFO_IDX(i, index);
+			for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
+				if (!cpu_online(sibling))
+					continue;
+				set_bit(sibling, this_leaf->shared_cpu_map);
+			}
+		}
 	}
+
+	return ret;
+}
+
+static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
+{
+	struct _cpuid4_info *this_leaf, *sibling_leaf;
+	unsigned long num_threads_sharing;
+	int index_msb, i;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		if (cache_shared_amd_cpu_map_setup(cpu, index))
+			return;
+	}
+
 	this_leaf = CPUID4_INFO_IDX(cpu, index);
 	num_threads_sharing = 1 + this_leaf->base.eax.split.num_threads_sharing;
 

arch/x86/kernel/microcode_amd.c

@@ -300,13 +300,33 @@ free_table:
 	return state;
 }
 
+/*
+ * AMD microcode firmware naming convention, up to family 15h they are in
+ * the legacy file:
+ *
+ *    amd-ucode/microcode_amd.bin
+ *
+ * This legacy file is always smaller than 2K in size.
+ *
+ * Starting at family 15h they are in family specific firmware files:
+ *
+ *    amd-ucode/microcode_amd_fam15h.bin
+ *    amd-ucode/microcode_amd_fam16h.bin
+ *    ...
+ *
+ * These might be larger than 2K.
+ */
 static enum ucode_state request_microcode_amd(int cpu, struct device *device)
 {
-	const char *fw_name = "amd-ucode/microcode_amd.bin";
+	char fw_name[36] = "amd-ucode/microcode_amd.bin";
 	const struct firmware *fw;
 	enum ucode_state ret = UCODE_NFOUND;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	if (request_firmware(&fw, fw_name, device)) {
+	if (c->x86 >= 0x15)
+		snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
+
+	if (request_firmware(&fw, (const char *)fw_name, device)) {
 		pr_err("failed to load file %s\n", fw_name);
 		goto out;
 	}

arch/x86/kernel/process_32.c

@@ -297,22 +297,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 				 *next = &next_p->thread;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(init_tss, cpu);
-	bool preload_fpu;
+	fpu_switch_t fpu;
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	/*
-	 * If the task has used fpu the last 5 timeslices, just do a full
-	 * restore of the math state immediately to avoid the trap; the
-	 * chances of needing FPU soon are obviously high now
-	 */
-	preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
-
-	__unlazy_fpu(prev_p);
-
-	/* we're going to use this soon, after a few expensive things */
-	if (preload_fpu)
-		prefetch(next->fpu.state);
+	fpu = switch_fpu_prepare(prev_p, next_p);
 
 	/*
 	 * Reload esp0.
@@ -352,11 +341,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		     task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
 		__switch_to_xtra(prev_p, next_p, tss);
 
-	/* If we're going to preload the fpu context, make sure clts
-	   is run while we're batching the cpu state updates. */
-	if (preload_fpu)
-		clts();
-
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
@@ -366,15 +350,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 */
 	arch_end_context_switch(next_p);
 
-	if (preload_fpu)
-		__math_state_restore();
-
 	/*
 	 * Restore %gs if needed (which is common)
 	 */
 	if (prev->gs | next->gs)
 		lazy_load_gs(next->gs);
 
+	switch_fpu_finish(next_p, fpu);
+
 	percpu_write(current_task, next_p);
 
 	return prev_p;

arch/x86/kernel/process_64.c

@@ -381,18 +381,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(init_tss, cpu);
 	unsigned fsindex, gsindex;
-	bool preload_fpu;
+	fpu_switch_t fpu;
 
-	/*
-	 * If the task has used fpu the last 5 timeslices, just do a full
-	 * restore of the math state immediately to avoid the trap; the
-	 * chances of needing FPU soon are obviously high now
-	 */
-	preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
-
-	/* we're going to use this soon, after a few expensive things */
-	if (preload_fpu)
-		prefetch(next->fpu.state);
+	fpu = switch_fpu_prepare(prev_p, next_p);
 
 	/*
 	 * Reload esp0, LDT and the page table pointer:
@@ -422,13 +413,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	load_TLS(next, cpu);
 
-	/* Must be after DS reload */
-	__unlazy_fpu(prev_p);
-
-	/* Make sure cpu is ready for new context */
-	if (preload_fpu)
-		clts();
-
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
@@ -469,6 +453,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
 	prev->gsindex = gsindex;
 
+	switch_fpu_finish(next_p, fpu);
+
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
@@ -487,13 +473,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		     task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
 		__switch_to_xtra(prev_p, next_p, tss);
 
-	/*
-	 * Preload the FPU context, now that we've determined that the
-	 * task is likely to be using it. 
-	 */
-	if (preload_fpu)
-		__math_state_restore();
-
 	return prev_p;
 }
 

arch/x86/kernel/traps.c

@@ -562,25 +562,34 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void)
 }
 
 /*
- * __math_state_restore assumes that cr0.TS is already clear and the
- * fpu state is all ready for use.  Used during context switch.
+ * This gets called with the process already owning the
+ * FPU state, and with CR0.TS cleared. It just needs to
+ * restore the FPU register state.
  */
-void __math_state_restore(void)
+void __math_state_restore(struct task_struct *tsk)
 {
-	struct thread_info *thread = current_thread_info();
-	struct task_struct *tsk = thread->task;
+	/* We need a safe address that is cheap to find and that is already
+	   in L1. We've just brought in "tsk->thread.has_fpu", so use that */
+#define safe_address (tsk->thread.has_fpu)
+
+	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+	   is pending.  Clear the x87 state here by setting it to fixed
+	   values. safe_address is a random variable that should be in L1 */
+	alternative_input(
+		ASM_NOP8 ASM_NOP2,
+		"emms\n\t"	  	/* clear stack tags */
+		"fildl %P[addr]",	/* set F?P to defined value */
+		X86_FEATURE_FXSAVE_LEAK,
+		[addr] "m" (safe_address));
 
 	/*
 	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
 	 */
 	if (unlikely(restore_fpu_checking(tsk))) {
-		stts();
+		__thread_fpu_end(tsk);
 		force_sig(SIGSEGV, tsk);
 		return;
 	}
-
-	thread->status |= TS_USEDFPU;	/* So we fnsave on switch_to() */
-	tsk->fpu_counter++;
 }
 
 /*
@@ -590,13 +599,12 @@ void __math_state_restore(void)
  * Careful.. There are problems with IBM-designed IRQ13 behaviour.
  * Don't touch unless you *really* know how it works.
  *
- * Must be called with kernel preemption disabled (in this case,
- * local interrupts are disabled at the call-site in entry.S).
+ * Must be called with kernel preemption disabled (eg with local
+ * local interrupts as in the case of do_device_not_available).
  */
-asmlinkage void math_state_restore(void)
+void math_state_restore(void)
 {
-	struct thread_info *thread = current_thread_info();
-	struct task_struct *tsk = thread->task;
+	struct task_struct *tsk = current;
 
 	if (!tsk_used_math(tsk)) {
 		local_irq_enable();
@@ -613,9 +621,10 @@ asmlinkage void math_state_restore(void)
 		local_irq_disable();
 	}
 
-	clts();				/* Allow maths ops (or we recurse) */
+	__thread_fpu_begin(tsk);
+	__math_state_restore(tsk);
 
-	__math_state_restore();
+	tsk->fpu_counter++;
 }
 EXPORT_SYMBOL_GPL(math_state_restore);
 

arch/x86/kernel/xsave.c

@@ -47,7 +47,7 @@ void __sanitize_i387_state(struct task_struct *tsk)
 	if (!fx)
 		return;
 
-	BUG_ON(task_thread_info(tsk)->status & TS_USEDFPU);
+	BUG_ON(__thread_has_fpu(tsk));
 
 	xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
 
@@ -168,7 +168,7 @@ int save_i387_xstate(void __user *buf)
 	if (!used_math())
 		return 0;
 
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+	if (user_has_fpu()) {
 		if (use_xsave())
 			err = xsave_user(buf);
 		else
@@ -176,8 +176,7 @@ int save_i387_xstate(void __user *buf)
 
 		if (err)
 			return err;
-		task_thread_info(tsk)->status &= ~TS_USEDFPU;
-		stts();
+		user_fpu_end();
 	} else {
 		sanitize_i387_state(tsk);
 		if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
@@ -292,10 +291,7 @@ int restore_i387_xstate(void __user *buf)
 			return err;
 	}
 
-	if (!(task_thread_info(current)->status & TS_USEDFPU)) {
-		clts();
-		task_thread_info(current)->status |= TS_USEDFPU;
-	}
+	user_fpu_begin();
 	if (use_xsave())
 		err = restore_user_xstate(buf);
 	else

arch/x86/kvm/vmx.c

@@ -1456,7 +1456,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
-	if (current_thread_info()->status & TS_USEDFPU)
+	if (__thread_has_fpu(current))
 		clts();
 	load_gdt(&__get_cpu_var(host_gdt));
 }

arch/x86/mm/mmap.c

@@ -75,9 +75,9 @@ static unsigned long mmap_rnd(void)
 	*/
 	if (current->flags & PF_RANDOMIZE) {
 		if (mmap_is_ia32())
-			rnd = (long)get_random_int() % (1<<8);
+			rnd = get_random_int() % (1<<8);
 		else
-			rnd = (long)(get_random_int() % (1<<28));
+			rnd = get_random_int() % (1<<28);
 	}
 	return rnd << PAGE_SHIFT;
 }

arch/x86/mm/srat.c

@@ -104,6 +104,8 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 	if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0)
 		return;
 	pxm = pa->proximity_domain_lo;
+	if (acpi_srat_revision >= 2)
+		pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8;
 	node = setup_node(pxm);
 	if (node < 0) {
 		printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
@@ -155,6 +157,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 	start = ma->base_address;
 	end = start + ma->length;
 	pxm = ma->proximity_domain;
+	if (acpi_srat_revision <= 1)
+		pxm &= 0xff;
 	node = setup_node(pxm);
 	if (node < 0) {
 		printk(KERN_ERR "SRAT: Too many proximity domains.\n");

arch/x86/net/bpf_jit_comp.c

@@ -151,17 +151,18 @@ void bpf_jit_compile(struct sk_filter *fp)
 	cleanup_addr = proglen; /* epilogue address */
 
 	for (pass = 0; pass < 10; pass++) {
+		u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen;
 		/* no prologue/epilogue for trivial filters (RET something) */
 		proglen = 0;
 		prog = temp;
 
-		if (seen) {
+		if (seen_or_pass0) {
 			EMIT4(0x55, 0x48, 0x89, 0xe5); /* push %rbp; mov %rsp,%rbp */
 			EMIT4(0x48, 0x83, 0xec, 96);	/* subq  $96,%rsp	*/
 			/* note : must save %rbx in case bpf_error is hit */
-			if (seen & (SEEN_XREG | SEEN_DATAREF))
+			if (seen_or_pass0 & (SEEN_XREG | SEEN_DATAREF))
 				EMIT4(0x48, 0x89, 0x5d, 0xf8); /* mov %rbx, -8(%rbp) */
-			if (seen & SEEN_XREG)
+			if (seen_or_pass0 & SEEN_XREG)
 				CLEAR_X(); /* make sure we dont leek kernel memory */
 
 			/*
@@ -170,7 +171,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 			 *  r9 = skb->len - skb->data_len
 			 *  r8 = skb->data
 			 */
-			if (seen & SEEN_DATAREF) {
+			if (seen_or_pass0 & SEEN_DATAREF) {
 				if (offsetof(struct sk_buff, len) <= 127)
 					/* mov    off8(%rdi),%r9d */
 					EMIT4(0x44, 0x8b, 0x4f, offsetof(struct sk_buff, len));
@@ -260,9 +261,14 @@ void bpf_jit_compile(struct sk_filter *fp)
 			case BPF_S_ALU_DIV_X: /* A /= X; */
 				seen |= SEEN_XREG;
 				EMIT2(0x85, 0xdb);	/* test %ebx,%ebx */
-				if (pc_ret0 != -1)
-					EMIT_COND_JMP(X86_JE, addrs[pc_ret0] - (addrs[i] - 4));
-				else {
+				if (pc_ret0 > 0) {
+					/* addrs[pc_ret0 - 1] is start address of target
+					 * (addrs[i] - 4) is the address following this jmp
+					 * ("xor %edx,%edx; div %ebx" being 4 bytes long)
+					 */
+					EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] -
+								(addrs[i] - 4));
+				} else {
 					EMIT_COND_JMP(X86_JNE, 2 + 5);
 					CLEAR_A();
 					EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 4)); /* jmp .+off32 */
@@ -335,12 +341,12 @@ void bpf_jit_compile(struct sk_filter *fp)
 				}
 				/* fallinto */
 			case BPF_S_RET_A:
-				if (seen) {
+				if (seen_or_pass0) {
 					if (i != flen - 1) {
 						EMIT_JMP(cleanup_addr - addrs[i]);
 						break;
 					}
-					if (seen & SEEN_XREG)
+					if (seen_or_pass0 & SEEN_XREG)
 						EMIT4(0x48, 0x8b, 0x5d, 0xf8);  /* mov  -8(%rbp),%rbx */
 					EMIT1(0xc9);		/* leaveq */
 				}
@@ -483,8 +489,9 @@ common_load:			seen |= SEEN_DATAREF;
 				goto common_load;
 			case BPF_S_LDX_B_MSH:
 				if ((int)K < 0) {
-					if (pc_ret0 != -1) {
-						EMIT_JMP(addrs[pc_ret0] - addrs[i]);
+					if (pc_ret0 > 0) {
+						/* addrs[pc_ret0 - 1] is the start address */
+						EMIT_JMP(addrs[pc_ret0 - 1] - addrs[i]);
 						break;
 					}
 					CLEAR_A();
@@ -599,13 +606,14 @@ cond_branch:			f_offset = addrs[i + filter[i].jf] - addrs[i];
 		 * use it to give the cleanup instruction(s) addr
 		 */
 		cleanup_addr = proglen - 1; /* ret */
-		if (seen)
+		if (seen_or_pass0)
 			cleanup_addr -= 1; /* leaveq */
-		if (seen & SEEN_XREG)
+		if (seen_or_pass0 & SEEN_XREG)
 			cleanup_addr -= 4; /* mov  -8(%rbp),%rbx */
 
 		if (image) {
-			WARN_ON(proglen != oldproglen);
+			if (proglen != oldproglen)
+				pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n", proglen, oldproglen);
 			break;
 		}
 		if (proglen == oldproglen) {

arch/x86/pci/Makefile

@@ -18,8 +18,9 @@ obj-$(CONFIG_X86_NUMAQ)		+= numaq_32.o
 obj-$(CONFIG_X86_MRST)		+= mrst.o
 
 obj-y				+= common.o early.o
-obj-y				+= amd_bus.o bus_numa.o
+obj-y				+= bus_numa.o
 
+obj-$(CONFIG_AMD_NB)		+= amd_bus.o
 obj-$(CONFIG_PCI_CNB20LE_QUIRK)	+= broadcom_bus.o
 
 ifeq ($(CONFIG_PCI_DEBUG),y)

arch/x86/pci/acpi.c

@@ -149,7 +149,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	struct acpi_resource_address64 addr;
 	acpi_status status;
 	unsigned long flags;
-	u64 start, end;
+	u64 start, orig_end, end;
 
 	status = resource_to_addr(acpi_res, &addr);
 	if (!ACPI_SUCCESS(status))
@@ -165,7 +165,21 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 		return AE_OK;
 
 	start = addr.minimum + addr.translation_offset;
-	end = addr.maximum + addr.translation_offset;
+	orig_end = end = addr.maximum + addr.translation_offset;
+
+	/* Exclude non-addressable range or non-addressable portion of range */
+	end = min(end, (u64)iomem_resource.end);
+	if (end <= start) {
+		dev_info(&info->bridge->dev,
+			"host bridge window [%#llx-%#llx] "
+			"(ignored, not CPU addressable)\n", start, orig_end);
+		return AE_OK;
+	} else if (orig_end != end) {
+		dev_info(&info->bridge->dev,
+			"host bridge window [%#llx-%#llx] "
+			"([%#llx-%#llx] ignored, not CPU addressable)\n",
+			start, orig_end, end + 1, orig_end);
+	}
 
 	res = &info->res[info->res_num];
 	res->name = info->name;

arch/x86/pci/amd_bus.c

@@ -30,34 +30,6 @@ static struct pci_hostbridge_probe pci_probes[] __initdata = {
 	{ 0, 0x18, PCI_VENDOR_ID_AMD, 0x1300 },
 };
 
-static u64 __initdata fam10h_mmconf_start;
-static u64 __initdata fam10h_mmconf_end;
-static void __init get_pci_mmcfg_amd_fam10h_range(void)
-{
-	u32 address;
-	u64 base, msr;
-	unsigned segn_busn_bits;
-
-	/* assume all cpus from fam10h have mmconf */
-        if (boot_cpu_data.x86 < 0x10)
-		return;
-
-	address = MSR_FAM10H_MMIO_CONF_BASE;
-	rdmsrl(address, msr);
-
-	/* mmconfig is not enable */
-	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
-		return;
-
-	base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT);
-
-	segn_busn_bits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) &
-			 FAM10H_MMIO_CONF_BUSRANGE_MASK;
-
-	fam10h_mmconf_start = base;
-	fam10h_mmconf_end = base + (1ULL<<(segn_busn_bits + 20)) - 1;
-}
-
 #define RANGE_NUM 16
 
 /**
@@ -85,6 +57,9 @@ static int __init early_fill_mp_bus_info(void)
 	u64 val;
 	u32 address;
 	bool found;
+	struct resource fam10h_mmconf_res, *fam10h_mmconf;
+	u64 fam10h_mmconf_start;
+	u64 fam10h_mmconf_end;
 
 	if (!early_pci_allowed())
 		return -1;
@@ -211,12 +186,17 @@ static int __init early_fill_mp_bus_info(void)
 		subtract_range(range, RANGE_NUM, 0, end);
 
 	/* get mmconfig */
-	get_pci_mmcfg_amd_fam10h_range();
+	fam10h_mmconf = amd_get_mmconfig_range(&fam10h_mmconf_res);
 	/* need to take out mmconf range */
-	if (fam10h_mmconf_end) {
-		printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end);
+	if (fam10h_mmconf) {
+		printk(KERN_DEBUG "Fam 10h mmconf %pR\n", fam10h_mmconf);
+		fam10h_mmconf_start = fam10h_mmconf->start;
+		fam10h_mmconf_end = fam10h_mmconf->end;
 		subtract_range(range, RANGE_NUM, fam10h_mmconf_start,
 				 fam10h_mmconf_end + 1);
+	} else {
+		fam10h_mmconf_start = 0;
+		fam10h_mmconf_end = 0;
 	}
 
 	/* mmio resource */

arch/x86/pci/xen.c

@@ -374,7 +374,7 @@ int __init pci_xen_init(void)
 
 int __init pci_xen_hvm_init(void)
 {
-	if (!xen_feature(XENFEAT_hvm_pirqs))
+	if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs))
 		return 0;
 
 #ifdef CONFIG_ACPI

arch/x86/platform/uv/tlb_uv.c

@@ -157,13 +157,14 @@ static int __init uvhub_to_first_apicid(int uvhub)
  * clear of the Timeout bit (as well) will free the resource. No reply will
  * be sent (the hardware will only do one reply per message).
  */
-static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp)
+static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp,
+						int do_acknowledge)
 {
 	unsigned long dw;
 	struct bau_pq_entry *msg;
 
 	msg = mdp->msg;
-	if (!msg->canceled) {
+	if (!msg->canceled && do_acknowledge) {
 		dw = (msg->swack_vec << UV_SW_ACK_NPENDING) | msg->swack_vec;
 		write_mmr_sw_ack(dw);
 	}
@@ -212,8 +213,8 @@ static void bau_process_retry_msg(struct msg_desc *mdp,
 			if (mmr & (msg_res << UV_SW_ACK_NPENDING)) {
 				unsigned long mr;
 				/*
-				 * is the resource timed out?
-				 * make everyone ignore the cancelled message.
+				 * Is the resource timed out?
+				 * Make everyone ignore the cancelled message.
 				 */
 				msg2->canceled = 1;
 				stat->d_canceled++;
@@ -231,8 +232,8 @@ static void bau_process_retry_msg(struct msg_desc *mdp,
  * Do all the things a cpu should do for a TLB shootdown message.
  * Other cpu's may come here at the same time for this message.
  */
-static void bau_process_message(struct msg_desc *mdp,
-					struct bau_control *bcp)
+static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp,
+						int do_acknowledge)
 {
 	short socket_ack_count = 0;
 	short *sp;
@@ -284,8 +285,9 @@ static void bau_process_message(struct msg_desc *mdp,
 		if (msg_ack_count == bcp->cpus_in_uvhub) {
 			/*
 			 * All cpus in uvhub saw it; reply
+			 * (unless we are in the UV2 workaround)
 			 */
-			reply_to_message(mdp, bcp);
+			reply_to_message(mdp, bcp, do_acknowledge);
 		}
 	}
 
@@ -491,27 +493,138 @@ static int uv1_wait_completion(struct bau_desc *bau_desc,
 /*
  * UV2 has an extra bit of status in the ACTIVATION_STATUS_2 register.
  */
-static unsigned long uv2_read_status(unsigned long offset, int rshft, int cpu)
+static unsigned long uv2_read_status(unsigned long offset, int rshft, int desc)
 {
 	unsigned long descriptor_status;
 	unsigned long descriptor_status2;
 
 	descriptor_status = ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK);
-	descriptor_status2 = (read_mmr_uv2_status() >> cpu) & 0x1UL;
+	descriptor_status2 = (read_mmr_uv2_status() >> desc) & 0x1UL;
 	descriptor_status = (descriptor_status << 1) | descriptor_status2;
 	return descriptor_status;
 }
 
+/*
+ * Return whether the status of the descriptor that is normally used for this
+ * cpu (the one indexed by its hub-relative cpu number) is busy.
+ * The status of the original 32 descriptors is always reflected in the 64
+ * bits of UVH_LB_BAU_SB_ACTIVATION_STATUS_0.
+ * The bit provided by the activation_status_2 register is irrelevant to
+ * the status if it is only being tested for busy or not busy.
+ */
+int normal_busy(struct bau_control *bcp)
+{
+	int cpu = bcp->uvhub_cpu;
+	int mmr_offset;
+	int right_shift;
+
+	mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
+	right_shift = cpu * UV_ACT_STATUS_SIZE;
+	return (((((read_lmmr(mmr_offset) >> right_shift) &
+				UV_ACT_STATUS_MASK)) << 1) == UV2H_DESC_BUSY);
+}
+
+/*
+ * Entered when a bau descriptor has gone into a permanent busy wait because
+ * of a hardware bug.
+ * Workaround the bug.
+ */
+int handle_uv2_busy(struct bau_control *bcp)
+{
+	int busy_one = bcp->using_desc;
+	int normal = bcp->uvhub_cpu;
+	int selected = -1;
+	int i;
+	unsigned long descriptor_status;
+	unsigned long status;
+	int mmr_offset;
+	struct bau_desc *bau_desc_old;
+	struct bau_desc *bau_desc_new;
+	struct bau_control *hmaster = bcp->uvhub_master;
+	struct ptc_stats *stat = bcp->statp;
+	cycles_t ttm;
+
+	stat->s_uv2_wars++;
+	spin_lock(&hmaster->uvhub_lock);
+	/* try for the original first */
+	if (busy_one != normal) {
+		if (!normal_busy(bcp))
+			selected = normal;
+	}
+	if (selected < 0) {
+		/* can't use the normal, select an alternate */
+		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
+		descriptor_status = read_lmmr(mmr_offset);
+
+		/* scan available descriptors 32-63 */
+		for (i = 0; i < UV_CPUS_PER_AS; i++) {
+			if ((hmaster->inuse_map & (1 << i)) == 0) {
+				status = ((descriptor_status >>
+						(i * UV_ACT_STATUS_SIZE)) &
+						UV_ACT_STATUS_MASK) << 1;
+				if (status != UV2H_DESC_BUSY) {
+					selected = i + UV_CPUS_PER_AS;
+					break;
+				}
+			}
+		}
+	}
+
+	if (busy_one != normal)
+		/* mark the busy alternate as not in-use */
+		hmaster->inuse_map &= ~(1 << (busy_one - UV_CPUS_PER_AS));
+
+	if (selected >= 0) {
+		/* switch to the selected descriptor */
+		if (selected != normal) {
+			/* set the selected alternate as in-use */
+			hmaster->inuse_map |=
+					(1 << (selected - UV_CPUS_PER_AS));
+			if (selected > stat->s_uv2_wars_hw)
+				stat->s_uv2_wars_hw = selected;
+		}
+		bau_desc_old = bcp->descriptor_base;
+		bau_desc_old += (ITEMS_PER_DESC * busy_one);
+		bcp->using_desc = selected;
+		bau_desc_new = bcp->descriptor_base;
+		bau_desc_new += (ITEMS_PER_DESC * selected);
+		*bau_desc_new = *bau_desc_old;
+	} else {
+		/*
+		 * All are busy. Wait for the normal one for this cpu to
+		 * free up.
+		 */
+		stat->s_uv2_war_waits++;
+		spin_unlock(&hmaster->uvhub_lock);
+		ttm = get_cycles();
+		do {
+			cpu_relax();
+		} while (normal_busy(bcp));
+		spin_lock(&hmaster->uvhub_lock);
+		/* switch to the original descriptor */
+		bcp->using_desc = normal;
+		bau_desc_old = bcp->descriptor_base;
+		bau_desc_old += (ITEMS_PER_DESC * bcp->using_desc);
+		bcp->using_desc = (ITEMS_PER_DESC * normal);
+		bau_desc_new = bcp->descriptor_base;
+		bau_desc_new += (ITEMS_PER_DESC * normal);
+		*bau_desc_new = *bau_desc_old; /* copy the entire descriptor */
+	}
+	spin_unlock(&hmaster->uvhub_lock);
+	return FLUSH_RETRY_BUSYBUG;
+}
+
 static int uv2_wait_completion(struct bau_desc *bau_desc,
 				unsigned long mmr_offset, int right_shift,
 				struct bau_control *bcp, long try)
 {
 	unsigned long descriptor_stat;
 	cycles_t ttm;
-	int cpu = bcp->uvhub_cpu;
+	int desc = bcp->using_desc;
+	long busy_reps = 0;
 	struct ptc_stats *stat = bcp->statp;
 
-	descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu);
+	descriptor_stat = uv2_read_status(mmr_offset, right_shift, desc);
 
 	/* spin on the status MMR, waiting for it to go idle */
 	while (descriptor_stat != UV2H_DESC_IDLE) {
@@ -542,12 +655,23 @@ static int uv2_wait_completion(struct bau_desc *bau_desc,
 			bcp->conseccompletes = 0;
 			return FLUSH_RETRY_TIMEOUT;
 		} else {
+			busy_reps++;
+			if (busy_reps > 1000000) {
+				/* not to hammer on the clock */
+				busy_reps = 0;
+				ttm = get_cycles();
+				if ((ttm - bcp->send_message) >
+					(bcp->clocks_per_100_usec)) {
+					return handle_uv2_busy(bcp);
+				}
+			}
 			/*
 			 * descriptor_stat is still BUSY
 			 */
 			cpu_relax();
 		}
-		descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu);
+		descriptor_stat = uv2_read_status(mmr_offset, right_shift,
+									desc);
 	}
 	bcp->conseccompletes++;
 	return FLUSH_COMPLETE;
@@ -563,17 +687,17 @@ static int wait_completion(struct bau_desc *bau_desc,
 {
 	int right_shift;
 	unsigned long mmr_offset;
-	int cpu = bcp->uvhub_cpu;
+	int desc = bcp->using_desc;
 
-	if (cpu < UV_CPUS_PER_AS) {
+	if (desc < UV_CPUS_PER_AS) {
 		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
-		right_shift = cpu * UV_ACT_STATUS_SIZE;
+		right_shift = desc * UV_ACT_STATUS_SIZE;
 	} else {
 		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
-		right_shift = ((cpu - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE);
+		right_shift = ((desc - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE);
 	}
 
-	if (is_uv1_hub())
+	if (bcp->uvhub_version == 1)
 		return uv1_wait_completion(bau_desc, mmr_offset, right_shift,
 								bcp, try);
 	else
@@ -752,19 +876,22 @@ static void handle_cmplt(int completion_status, struct bau_desc *bau_desc,
  * Returns 1 if it gives up entirely and the original cpu mask is to be
  * returned to the kernel.
  */
-int uv_flush_send_and_wait(struct bau_desc *bau_desc,
-			struct cpumask *flush_mask, struct bau_control *bcp)
+int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp)
 {
 	int seq_number = 0;
 	int completion_stat = 0;
+	int uv1 = 0;
 	long try = 0;
 	unsigned long index;
 	cycles_t time1;
 	cycles_t time2;
 	struct ptc_stats *stat = bcp->statp;
 	struct bau_control *hmaster = bcp->uvhub_master;
+	struct uv1_bau_msg_header *uv1_hdr = NULL;
+	struct uv2_bau_msg_header *uv2_hdr = NULL;
+	struct bau_desc *bau_desc;
 
-	if (is_uv1_hub())
+	if (bcp->uvhub_version == 1)
 		uv1_throttle(hmaster, stat);
 
 	while (hmaster->uvhub_quiesce)
@@ -772,22 +899,39 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
 
 	time1 = get_cycles();
 	do {
-		if (try == 0) {
-			bau_desc->header.msg_type = MSG_REGULAR;
+		bau_desc = bcp->descriptor_base;
+		bau_desc += (ITEMS_PER_DESC * bcp->using_desc);
+		if (bcp->uvhub_version == 1) {
+			uv1 = 1;
+			uv1_hdr = &bau_desc->header.uv1_hdr;
+		} else
+			uv2_hdr = &bau_desc->header.uv2_hdr;
+		if ((try == 0) || (completion_stat == FLUSH_RETRY_BUSYBUG)) {
+			if (uv1)
+				uv1_hdr->msg_type = MSG_REGULAR;
+			else
+				uv2_hdr->msg_type = MSG_REGULAR;
 			seq_number = bcp->message_number++;
 		} else {
-			bau_desc->header.msg_type = MSG_RETRY;
+			if (uv1)
+				uv1_hdr->msg_type = MSG_RETRY;
+			else
+				uv2_hdr->msg_type = MSG_RETRY;
 			stat->s_retry_messages++;
 		}
 
-		bau_desc->header.sequence = seq_number;
-		index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu;
+		if (uv1)
+			uv1_hdr->sequence = seq_number;
+		else
+			uv2_hdr->sequence = seq_number;
+		index = (1UL << AS_PUSH_SHIFT) | bcp->using_desc;
 		bcp->send_message = get_cycles();
 
 		write_mmr_activation(index);
 
 		try++;
 		completion_stat = wait_completion(bau_desc, bcp, try);
+		/* UV2: wait_completion() may change the bcp->using_desc */
 
 		handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat);
 
@@ -798,6 +942,7 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
 		}
 		cpu_relax();
 	} while ((completion_stat == FLUSH_RETRY_PLUGGED) ||
+		 (completion_stat == FLUSH_RETRY_BUSYBUG) ||
 		 (completion_stat == FLUSH_RETRY_TIMEOUT));
 
 	time2 = get_cycles();
@@ -812,6 +957,7 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
 	record_send_stats(time1, time2, bcp, stat, completion_stat, try);
 
 	if (completion_stat == FLUSH_GIVEUP)
+		/* FLUSH_GIVEUP will fall back to using IPI's for tlb flush */
 		return 1;
 	return 0;
 }
@@ -967,7 +1113,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 		stat->s_ntargself++;
 
 	bau_desc = bcp->descriptor_base;
-	bau_desc += ITEMS_PER_DESC * bcp->uvhub_cpu;
+	bau_desc += (ITEMS_PER_DESC * bcp->using_desc);
 	bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
 	if (set_distrib_bits(flush_mask, bcp, bau_desc, &locals, &remotes))
 		return NULL;
@@ -980,12 +1126,85 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 	 * uv_flush_send_and_wait returns 0 if all cpu's were messaged,
 	 * or 1 if it gave up and the original cpumask should be returned.
 	 */
-	if (!uv_flush_send_and_wait(bau_desc, flush_mask, bcp))
+	if (!uv_flush_send_and_wait(flush_mask, bcp))
 		return NULL;
 	else
 		return cpumask;
 }
 
+/*
+ * Search the message queue for any 'other' message with the same software
+ * acknowledge resource bit vector.
+ */
+struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg,
+			struct bau_control *bcp, unsigned char swack_vec)
+{
+	struct bau_pq_entry *msg_next = msg + 1;
+
+	if (msg_next > bcp->queue_last)
+		msg_next = bcp->queue_first;
+	while ((msg_next->swack_vec != 0) && (msg_next != msg)) {
+		if (msg_next->swack_vec == swack_vec)
+			return msg_next;
+		msg_next++;
+		if (msg_next > bcp->queue_last)
+			msg_next = bcp->queue_first;
+	}
+	return NULL;
+}
+
+/*
+ * UV2 needs to work around a bug in which an arriving message has not
+ * set a bit in the UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE register.
+ * Such a message must be ignored.
+ */
+void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp)
+{
+	unsigned long mmr_image;
+	unsigned char swack_vec;
+	struct bau_pq_entry *msg = mdp->msg;
+	struct bau_pq_entry *other_msg;
+
+	mmr_image = read_mmr_sw_ack();
+	swack_vec = msg->swack_vec;
+
+	if ((swack_vec & mmr_image) == 0) {
+		/*
+		 * This message was assigned a swack resource, but no
+		 * reserved acknowlegment is pending.
+		 * The bug has prevented this message from setting the MMR.
+		 * And no other message has used the same sw_ack resource.
+		 * Do the requested shootdown but do not reply to the msg.
+		 * (the 0 means make no acknowledge)
+		 */
+		bau_process_message(mdp, bcp, 0);
+		return;
+	}
+
+	/*
+	 * Some message has set the MMR 'pending' bit; it might have been
+	 * another message.  Look for that message.
+	 */
+	other_msg = find_another_by_swack(msg, bcp, msg->swack_vec);
+	if (other_msg) {
+		/* There is another.  Do not ack the current one. */
+		bau_process_message(mdp, bcp, 0);
+		/*
+		 * Let the natural processing of that message acknowledge
+		 * it. Don't get the processing of sw_ack's out of order.
+		 */
+		return;
+	}
+
+	/*
+	 * There is no other message using this sw_ack, so it is safe to
+	 * acknowledge it.
+	 */
+	bau_process_message(mdp, bcp, 1);
+
+	return;
+}
+
 /*
  * The BAU message interrupt comes here. (registered by set_intr_gate)
  * See entry_64.S
@@ -1022,9 +1241,11 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
 		count++;
 
 		msgdesc.msg_slot = msg - msgdesc.queue_first;
-		msgdesc.swack_slot = ffs(msg->swack_vec) - 1;
 		msgdesc.msg = msg;
-		bau_process_message(&msgdesc, bcp);
+		if (bcp->uvhub_version == 2)
+			process_uv2_message(&msgdesc, bcp);
+		else
+			bau_process_message(&msgdesc, bcp, 1);
 
 		msg++;
 		if (msg > msgdesc.queue_last)
@@ -1083,7 +1304,7 @@ static void __init enable_timeouts(void)
 		 */
 		mmr_image |= (1L << SOFTACK_MSHIFT);
 		if (is_uv2_hub()) {
-			mmr_image |= (1L << UV2_LEG_SHFT);
+			mmr_image &= ~(1L << UV2_LEG_SHFT);
 			mmr_image |= (1L << UV2_EXT_SHFT);
 		}
 		write_mmr_misc_control(pnode, mmr_image);
@@ -1142,7 +1363,7 @@ static int ptc_seq_show(struct seq_file *file, void *data)
 		seq_printf(file,
 			"all one mult none retry canc nocan reset rcan ");
 		seq_printf(file,
-			"disable enable\n");
+			"disable enable wars warshw warwaits\n");
 	}
 	if (cpu < num_possible_cpus() && cpu_online(cpu)) {
 		stat = &per_cpu(ptcstats, cpu);
@@ -1173,8 +1394,10 @@ static int ptc_seq_show(struct seq_file *file, void *data)
 			   stat->d_nomsg, stat->d_retries, stat->d_canceled,
 			   stat->d_nocanceled, stat->d_resets,
 			   stat->d_rcanceled);
-		seq_printf(file, "%ld %ld\n",
-			stat->s_bau_disabled, stat->s_bau_reenabled);
+		seq_printf(file, "%ld %ld %ld %ld %ld\n",
+			stat->s_bau_disabled, stat->s_bau_reenabled,
+			stat->s_uv2_wars, stat->s_uv2_wars_hw,
+			stat->s_uv2_war_waits);
 	}
 	return 0;
 }
@@ -1432,12 +1655,15 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
 {
 	int i;
 	int cpu;
+	int uv1 = 0;
 	unsigned long gpa;
 	unsigned long m;
 	unsigned long n;
 	size_t dsize;
 	struct bau_desc *bau_desc;
 	struct bau_desc *bd2;
+	struct uv1_bau_msg_header *uv1_hdr;
+	struct uv2_bau_msg_header *uv2_hdr;
 	struct bau_control *bcp;
 
 	/*
@@ -1451,6 +1677,8 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
 	gpa = uv_gpa(bau_desc);
 	n = uv_gpa_to_gnode(gpa);
 	m = uv_gpa_to_offset(gpa);
+	if (is_uv1_hub())
+		uv1 = 1;
 
 	/* the 14-bit pnode */
 	write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m));
@@ -1461,21 +1689,33 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
 	 */
 	for (i = 0, bd2 = bau_desc; i < (ADP_SZ * ITEMS_PER_DESC); i++, bd2++) {
 		memset(bd2, 0, sizeof(struct bau_desc));
-		bd2->header.swack_flag =	1;
-		/*
-		 * The base_dest_nasid set in the message header is the nasid
-		 * of the first uvhub in the partition. The bit map will
-		 * indicate destination pnode numbers relative to that base.
-		 * They may not be consecutive if nasid striding is being used.
-		 */
-		bd2->header.base_dest_nasid =	UV_PNODE_TO_NASID(base_pnode);
-		bd2->header.dest_subnodeid =	UV_LB_SUBNODEID;
-		bd2->header.command =		UV_NET_ENDPOINT_INTD;
-		bd2->header.int_both =		1;
-		/*
-		 * all others need to be set to zero:
-		 *   fairness chaining multilevel count replied_to
-		 */
+		if (uv1) {
+			uv1_hdr = &bd2->header.uv1_hdr;
+			uv1_hdr->swack_flag =	1;
+			/*
+			 * The base_dest_nasid set in the message header
+			 * is the nasid of the first uvhub in the partition.
+			 * The bit map will indicate destination pnode numbers
+			 * relative to that base. They may not be consecutive
+			 * if nasid striding is being used.
+			 */
+			uv1_hdr->base_dest_nasid =
+						UV_PNODE_TO_NASID(base_pnode);
+			uv1_hdr->dest_subnodeid =	UV_LB_SUBNODEID;
+			uv1_hdr->command =		UV_NET_ENDPOINT_INTD;
+			uv1_hdr->int_both =		1;
+			/*
+			 * all others need to be set to zero:
+			 *   fairness chaining multilevel count replied_to
+			 */
+		} else {
+			uv2_hdr = &bd2->header.uv2_hdr;
+			uv2_hdr->swack_flag =	1;
+			uv2_hdr->base_dest_nasid =
+						UV_PNODE_TO_NASID(base_pnode);
+			uv2_hdr->dest_subnodeid =	UV_LB_SUBNODEID;
+			uv2_hdr->command =		UV_NET_ENDPOINT_INTD;
+		}
 	}
 	for_each_present_cpu(cpu) {
 		if (pnode != uv_blade_to_pnode(uv_cpu_to_blade_id(cpu)))
@@ -1531,6 +1771,7 @@ static void pq_init(int node, int pnode)
 	write_mmr_payload_first(pnode, pn_first);
 	write_mmr_payload_tail(pnode, first);
 	write_mmr_payload_last(pnode, last);
+	write_gmmr_sw_ack(pnode, 0xffffUL);
 
 	/* in effect, all msg_type's are set to MSG_NOOP */
 	memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE);
@@ -1584,14 +1825,14 @@ static int calculate_destination_timeout(void)
 		ts_ns = base * mult1 * mult2;
 		ret = ts_ns / 1000;
 	} else {
-		/* 4 bits  0/1 for 10/80us, 3 bits of multiplier */
-		mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL);
+		/* 4 bits  0/1 for 10/80us base, 3 bits of multiplier */
+		mmr_image = uv_read_local_mmr(UVH_LB_BAU_MISC_CONTROL);
 		mmr_image = (mmr_image & UV_SA_MASK) >> UV_SA_SHFT;
 		if (mmr_image & (1L << UV2_ACK_UNITS_SHFT))
-			mult1 = 80;
+			base = 80;
 		else
-			mult1 = 10;
-		base = mmr_image & UV2_ACK_MASK;
+			base = 10;
+		mult1 = mmr_image & UV2_ACK_MASK;
 		ret = mult1 * base;
 	}
 	return ret;
@@ -1618,6 +1859,9 @@ static void __init init_per_cpu_tunables(void)
 		bcp->cong_response_us		= congested_respns_us;
 		bcp->cong_reps			= congested_reps;
 		bcp->cong_period		= congested_period;
+		bcp->clocks_per_100_usec =	usec_2_cycles(100);
+		spin_lock_init(&bcp->queue_lock);
+		spin_lock_init(&bcp->uvhub_lock);
 	}
 }
 
@@ -1728,8 +1972,17 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
 		bcp->cpus_in_socket = sdp->num_cpus;
 		bcp->socket_master = *smasterp;
 		bcp->uvhub = bdp->uvhub;
+		if (is_uv1_hub())
+			bcp->uvhub_version = 1;
+		else if (is_uv2_hub())
+			bcp->uvhub_version = 2;
+		else {
+			printk(KERN_EMERG "uvhub version not 1 or 2\n");
+			return 1;
+		}
 		bcp->uvhub_master = *hmasterp;
 		bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+		bcp->using_desc = bcp->uvhub_cpu;
 		if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
 			printk(KERN_EMERG "%d cpus per uvhub invalid\n",
 				bcp->uvhub_cpu);
@@ -1845,6 +2098,8 @@ static int __init uv_bau_init(void)
 			uv_base_pnode = uv_blade_to_pnode(uvhub);
 	}
 
+	enable_timeouts();
+
 	if (init_per_cpu(nuvhubs, uv_base_pnode)) {
 		nobau = 1;
 		return 0;
@@ -1855,7 +2110,6 @@ static int __init uv_bau_init(void)
 		if (uv_blade_nr_possible_cpus(uvhub))
 			init_uvhub(uvhub, vector, uv_base_pnode);
 
-	enable_timeouts();
 	alloc_intr_gate(vector, uv_bau_message_intr1);
 
 	for_each_possible_blade(uvhub) {
@@ -1867,7 +2121,8 @@ static int __init uv_bau_init(void)
 			val = 1L << 63;
 			write_gmmr_activation(pnode, val);
 			mmr = 1; /* should be 1 to broadcast to both sockets */
-			write_mmr_data_broadcast(pnode, mmr);
+			if (!is_uv1_hub())
+				write_mmr_data_broadcast(pnode, mmr);
 		}
 	}
 

arch/x86/platform/uv/uv_irq.c

@@ -25,7 +25,7 @@ struct uv_irq_2_mmr_pnode{
 	int			irq;
 };
 
-static spinlock_t		uv_irq_lock;
+static DEFINE_SPINLOCK(uv_irq_lock);
 static struct rb_root		uv_irq_root;
 
 static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);

arch/x86/xen/spinlock.c

@@ -116,9 +116,26 @@ static inline void spin_time_accum_blocked(u64 start)
 }
 #endif  /* CONFIG_XEN_DEBUG_FS */
 
+/*
+ * Size struct xen_spinlock so it's the same as arch_spinlock_t.
+ */
+#if NR_CPUS < 256
+typedef u8 xen_spinners_t;
+# define inc_spinners(xl) \
+	asm(LOCK_PREFIX " incb %0" : "+m" ((xl)->spinners) : : "memory");
+# define dec_spinners(xl) \
+	asm(LOCK_PREFIX " decb %0" : "+m" ((xl)->spinners) : : "memory");
+#else
+typedef u16 xen_spinners_t;
+# define inc_spinners(xl) \
+	asm(LOCK_PREFIX " incw %0" : "+m" ((xl)->spinners) : : "memory");
+# define dec_spinners(xl) \
+	asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory");
+#endif
+
 struct xen_spinlock {
 	unsigned char lock;		/* 0 -> free; 1 -> locked */
-	unsigned short spinners;	/* count of waiting cpus */
+	xen_spinners_t spinners;	/* count of waiting cpus */
 };
 
 static int xen_spin_is_locked(struct arch_spinlock *lock)
@@ -164,8 +181,7 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
 
 	wmb();			/* set lock of interest before count */
 
-	asm(LOCK_PREFIX " incw %0"
-	    : "+m" (xl->spinners) : : "memory");
+	inc_spinners(xl);
 
 	return prev;
 }
@@ -176,8 +192,7 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
  */
 static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock *prev)
 {
-	asm(LOCK_PREFIX " decw %0"
-	    : "+m" (xl->spinners) : : "memory");
+	dec_spinners(xl);
 	wmb();			/* decrement count before restoring lock */
 	__this_cpu_write(lock_spinners, prev);
 }
@@ -373,6 +388,8 @@ void xen_uninit_lock_cpu(int cpu)
 
 void __init xen_init_spinlocks(void)
 {
+	BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t));
+
 	pv_lock_ops.spin_is_locked = xen_spin_is_locked;
 	pv_lock_ops.spin_is_contended = xen_spin_is_contended;
 	pv_lock_ops.spin_lock = xen_spin_lock;

block/scsi_ioctl.c

@@ -24,6 +24,7 @@
 #include <linux/capability.h>
 #include <linux/completion.h>
 #include <linux/cdrom.h>
+#include <linux/ratelimit.h>
 #include <linux/slab.h>
 #include <linux/times.h>
 #include <asm/uaccess.h>
@@ -690,6 +691,57 @@ int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mod
 }
 EXPORT_SYMBOL(scsi_cmd_ioctl);
 
+int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd)
+{
+	if (bd && bd == bd->bd_contains)
+		return 0;
+
+	/* Actually none of these is particularly useful on a partition,
+	 * but they are safe.
+	 */
+	switch (cmd) {
+	case SCSI_IOCTL_GET_IDLUN:
+	case SCSI_IOCTL_GET_BUS_NUMBER:
+	case SCSI_IOCTL_GET_PCI:
+	case SCSI_IOCTL_PROBE_HOST:
+	case SG_GET_VERSION_NUM:
+	case SG_SET_TIMEOUT:
+	case SG_GET_TIMEOUT:
+	case SG_GET_RESERVED_SIZE:
+	case SG_SET_RESERVED_SIZE:
+	case SG_EMULATED_HOST:
+		return 0;
+	case CDROM_GET_CAPABILITY:
+		/* Keep this until we remove the printk below.  udev sends it
+		 * and we do not want to spam dmesg about it.   CD-ROMs do
+		 * not have partitions, so we get here only for disks.
+		 */
+		return -ENOTTY;
+	default:
+		break;
+	}
+
+	/* In particular, rule out all resets and host-specific ioctls.  */
+	printk_ratelimited(KERN_WARNING
+			   "%s: sending ioctl %x to a partition!\n", current->comm, cmd);
+
+	return capable(CAP_SYS_RAWIO) ? 0 : -ENOTTY;
+}
+EXPORT_SYMBOL(scsi_verify_blk_ioctl);
+
+int scsi_cmd_blk_ioctl(struct block_device *bd, fmode_t mode,
+		       unsigned int cmd, void __user *arg)
+{
+	int ret;
+
+	ret = scsi_verify_blk_ioctl(bd, cmd);
+	if (ret < 0)
+		return ret;
+
+	return scsi_cmd_ioctl(bd->bd_disk->queue, bd->bd_disk, mode, cmd, arg);
+}
+EXPORT_SYMBOL(scsi_cmd_blk_ioctl);
+
 static int __init blk_scsi_ioctl_init(void)
 {
 	blk_set_cmd_filter_defaults(&blk_default_cmd_filter);

crypto/sha512_generic.c

@@ -21,8 +21,6 @@
 #include <linux/percpu.h>
 #include <asm/byteorder.h>
 
-static DEFINE_PER_CPU(u64[80], msg_schedule);
-
 static inline u64 Ch(u64 x, u64 y, u64 z)
 {
         return z ^ (x & (y ^ z));
@@ -33,11 +31,6 @@ static inline u64 Maj(u64 x, u64 y, u64 z)
         return (x & y) | (z & (x | y));
 }
 
-static inline u64 RORu64(u64 x, u64 y)
-{
-        return (x >> y) | (x << (64 - y));
-}
-
 static const u64 sha512_K[80] = {
         0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL, 0xb5c0fbcfec4d3b2fULL,
         0xe9b5dba58189dbbcULL, 0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
@@ -68,10 +61,10 @@ static const u64 sha512_K[80] = {
         0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL,
 };
 
-#define e0(x)       (RORu64(x,28) ^ RORu64(x,34) ^ RORu64(x,39))
-#define e1(x)       (RORu64(x,14) ^ RORu64(x,18) ^ RORu64(x,41))
-#define s0(x)       (RORu64(x, 1) ^ RORu64(x, 8) ^ (x >> 7))
-#define s1(x)       (RORu64(x,19) ^ RORu64(x,61) ^ (x >> 6))
+#define e0(x)       (ror64(x,28) ^ ror64(x,34) ^ ror64(x,39))
+#define e1(x)       (ror64(x,14) ^ ror64(x,18) ^ ror64(x,41))
+#define s0(x)       (ror64(x, 1) ^ ror64(x, 8) ^ (x >> 7))
+#define s1(x)       (ror64(x,19) ^ ror64(x,61) ^ (x >> 6))
 
 static inline void LOAD_OP(int I, u64 *W, const u8 *input)
 {
@@ -80,7 +73,7 @@ static inline void LOAD_OP(int I, u64 *W, const u8 *input)
 
 static inline void BLEND_OP(int I, u64 *W)
 {
-	W[I] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16];
+	W[I & 15] += s1(W[(I-2) & 15]) + W[(I-7) & 15] + s0(W[(I-15) & 15]);
 }
 
 static void
@@ -89,15 +82,7 @@ sha512_transform(u64 *state, const u8 *input)
 	u64 a, b, c, d, e, f, g, h, t1, t2;
 
 	int i;
-	u64 *W = get_cpu_var(msg_schedule);
-
-	/* load the input */
-        for (i = 0; i < 16; i++)
-                LOAD_OP(i, W, input);
-
-        for (i = 16; i < 80; i++) {
-                BLEND_OP(i, W);
-        }
+	u64 W[16];
 
 	/* load the state into our registers */
 	a=state[0];   b=state[1];   c=state[2];   d=state[3];
@@ -105,21 +90,35 @@ sha512_transform(u64 *state, const u8 *input)
 
 	/* now iterate */
 	for (i=0; i<80; i+=8) {
-		t1 = h + e1(e) + Ch(e,f,g) + sha512_K[i  ] + W[i  ];
+		if (!(i & 8)) {
+			int j;
+
+			if (i < 16) {
+				/* load the input */
+				for (j = 0; j < 16; j++)
+					LOAD_OP(i + j, W, input);
+			} else {
+				for (j = 0; j < 16; j++) {
+					BLEND_OP(i + j, W);
+				}
+			}
+		}
+
+		t1 = h + e1(e) + Ch(e,f,g) + sha512_K[i  ] + W[(i & 15)];
 		t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
-		t1 = g + e1(d) + Ch(d,e,f) + sha512_K[i+1] + W[i+1];
+		t1 = g + e1(d) + Ch(d,e,f) + sha512_K[i+1] + W[(i & 15) + 1];
 		t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
-		t1 = f + e1(c) + Ch(c,d,e) + sha512_K[i+2] + W[i+2];
+		t1 = f + e1(c) + Ch(c,d,e) + sha512_K[i+2] + W[(i & 15) + 2];
 		t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
-		t1 = e + e1(b) + Ch(b,c,d) + sha512_K[i+3] + W[i+3];
+		t1 = e + e1(b) + Ch(b,c,d) + sha512_K[i+3] + W[(i & 15) + 3];
 		t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
-		t1 = d + e1(a) + Ch(a,b,c) + sha512_K[i+4] + W[i+4];
+		t1 = d + e1(a) + Ch(a,b,c) + sha512_K[i+4] + W[(i & 15) + 4];
 		t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
-		t1 = c + e1(h) + Ch(h,a,b) + sha512_K[i+5] + W[i+5];
+		t1 = c + e1(h) + Ch(h,a,b) + sha512_K[i+5] + W[(i & 15) + 5];
 		t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
-		t1 = b + e1(g) + Ch(g,h,a) + sha512_K[i+6] + W[i+6];
+		t1 = b + e1(g) + Ch(g,h,a) + sha512_K[i+6] + W[(i & 15) + 6];
 		t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
-		t1 = a + e1(f) + Ch(f,g,h) + sha512_K[i+7] + W[i+7];
+		t1 = a + e1(f) + Ch(f,g,h) + sha512_K[i+7] + W[(i & 15) + 7];
 		t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
 	}
 
@@ -128,8 +127,6 @@ sha512_transform(u64 *state, const u8 *input)
 
 	/* erase our data */
 	a = b = c = d = e = f = g = h = t1 = t2 = 0;
-	memset(W, 0, sizeof(__get_cpu_var(msg_schedule)));
-	put_cpu_var(msg_schedule);
 }
 
 static int

drivers/acpi/acpica/dsargs.c

@@ -387,5 +387,29 @@ acpi_status acpi_ds_get_region_arguments(union acpi_operand_object *obj_desc)
 	status = acpi_ds_execute_arguments(node, node->parent,
 					   extra_desc->extra.aml_length,
 					   extra_desc->extra.aml_start);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Validate the region address/length via the host OS */
+
+	status = acpi_os_validate_address(obj_desc->region.space_id,
+					  obj_desc->region.address,
+					  (acpi_size) obj_desc->region.length,
+					  acpi_ut_get_node_name(node));
+
+	if (ACPI_FAILURE(status)) {
+		/*
+		 * Invalid address/length. We will emit an error message and mark
+		 * the region as invalid, so that it will cause an additional error if
+		 * it is ever used. Then return AE_OK.
+		 */
+		ACPI_EXCEPTION((AE_INFO, status,
+				"During address validation of OpRegion [%4.4s]",
+				node->name.ascii));
+		obj_desc->common.flags |= AOPOBJ_INVALID;
+		status = AE_OK;
+	}
+
 	return_ACPI_STATUS(status);
 }

drivers/acpi/numa.c

@@ -45,6 +45,8 @@ static int pxm_to_node_map[MAX_PXM_DOMAINS]
 static int node_to_pxm_map[MAX_NUMNODES]
 			= { [0 ... MAX_NUMNODES - 1] = PXM_INVAL };
 
+unsigned char acpi_srat_revision __initdata;
+
 int pxm_to_node(int pxm)
 {
 	if (pxm < 0)
@@ -255,9 +257,13 @@ acpi_parse_memory_affinity(struct acpi_subtable_header * header,
 
 static int __init acpi_parse_srat(struct acpi_table_header *table)
 {
+	struct acpi_table_srat *srat;
 	if (!table)
 		return -EINVAL;
 
+	srat = (struct acpi_table_srat *)table;
+	acpi_srat_revision = srat->header.revision;
+
 	/* Real work done in acpi_table_parse_srat below. */
 
 	return 0;

drivers/acpi/pci_root.c

@@ -596,6 +596,13 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 		if (ACPI_SUCCESS(status)) {
 			dev_info(root->bus->bridge,
 				"ACPI _OSC control (0x%02x) granted\n", flags);
+			if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_ASPM) {
+				/*
+				 * We have ASPM control, but the FADT indicates
+				 * that it's unsupported. Clear it.
+				 */
+				pcie_clear_aspm(root->bus);
+			}
 		} else {
 			dev_info(root->bus->bridge,
 				"ACPI _OSC request failed (%s), "

drivers/acpi/processor_core.c

@@ -173,8 +173,30 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
 	apic_id = map_mat_entry(handle, type, acpi_id);
 	if (apic_id == -1)
 		apic_id = map_madt_entry(type, acpi_id);
-	if (apic_id == -1)
-		return apic_id;
+	if (apic_id == -1) {
+		/*
+		 * On UP processor, there is no _MAT or MADT table.
+		 * So above apic_id is always set to -1.
+		 *
+		 * BIOS may define multiple CPU handles even for UP processor.
+		 * For example,
+		 *
+		 * Scope (_PR)
+                 * {
+		 *     Processor (CPU0, 0x00, 0x00000410, 0x06) {}
+		 *     Processor (CPU1, 0x01, 0x00000410, 0x06) {}
+		 *     Processor (CPU2, 0x02, 0x00000410, 0x06) {}
+		 *     Processor (CPU3, 0x03, 0x00000410, 0x06) {}
+		 * }
+		 *
+		 * Ignores apic_id and always return 0 for CPU0's handle.
+		 * Return -1 for other CPU's handle.
+		 */
+		if (acpi_id == 0)
+			return acpi_id;
+		else
+			return apic_id;
+	}
 
 #ifdef CONFIG_SMP
 	for_each_possible_cpu(i) {

drivers/base/firmware_class.c

@@ -226,13 +226,13 @@ static ssize_t firmware_loading_store(struct device *dev,
 	int loading = simple_strtol(buf, NULL, 10);
 	int i;
 
+	mutex_lock(&fw_lock);
+
+	if (!fw_priv->fw)
+		goto out;
+
 	switch (loading) {
 	case 1:
-		mutex_lock(&fw_lock);
-		if (!fw_priv->fw) {
-			mutex_unlock(&fw_lock);
-			break;
-		}
 		firmware_free_data(fw_priv->fw);
 		memset(fw_priv->fw, 0, sizeof(struct firmware));
 		/* If the pages are not owned by 'struct firmware' */
@@ -243,7 +243,6 @@ static ssize_t firmware_loading_store(struct device *dev,
 		fw_priv->page_array_size = 0;
 		fw_priv->nr_pages = 0;
 		set_bit(FW_STATUS_LOADING, &fw_priv->status);
-		mutex_unlock(&fw_lock);
 		break;
 	case 0:
 		if (test_bit(FW_STATUS_LOADING, &fw_priv->status)) {
@@ -274,7 +273,8 @@ static ssize_t firmware_loading_store(struct device *dev,
 		fw_load_abort(fw_priv);
 		break;
 	}
-
+out:
+	mutex_unlock(&fw_lock);
 	return count;
 }
 

drivers/base/regmap/regcache.c

@@ -54,7 +54,7 @@ static int regcache_hw_init(struct regmap *map)
 	for (count = 0, i = 0; i < map->num_reg_defaults_raw; i++) {
 		val = regcache_get_val(map->reg_defaults_raw,
 				       i, map->cache_word_size);
-		if (!val)
+		if (regmap_volatile(map, i))
 			continue;
 		count++;
 	}
@@ -69,7 +69,7 @@ static int regcache_hw_init(struct regmap *map)
 	for (i = 0, j = 0; i < map->num_reg_defaults_raw; i++) {
 		val = regcache_get_val(map->reg_defaults_raw,
 				       i, map->cache_word_size);
-		if (!val)
+		if (regmap_volatile(map, i))
 			continue;
 		map->reg_defaults[j].reg = i;
 		map->reg_defaults[j].def = val;

drivers/bcma/bcma_private.h

@@ -18,6 +18,9 @@ void bcma_bus_unregister(struct bcma_bus *bus);
 int __init bcma_bus_early_register(struct bcma_bus *bus,
 				   struct bcma_device *core_cc,
 				   struct bcma_device *core_mips);
+#ifdef CONFIG_PM
+int bcma_bus_resume(struct bcma_bus *bus);
+#endif
 
 /* scan.c */
 int bcma_bus_scan(struct bcma_bus *bus);

drivers/bcma/host_pci.c

@@ -224,6 +224,44 @@ static void bcma_host_pci_remove(struct pci_dev *dev)
 	pci_set_drvdata(dev, NULL);
 }
 
+#ifdef CONFIG_PM
+static int bcma_host_pci_suspend(struct pci_dev *dev, pm_message_t state)
+{
+	struct bcma_bus *bus = pci_get_drvdata(dev);
+
+	/* Host specific */
+	pci_save_state(dev);
+	pci_disable_device(dev);
+	pci_set_power_state(dev, pci_choose_state(dev, state));
+
+	bus->mapped_core = NULL;
+	return 0;
+}
+
+static int bcma_host_pci_resume(struct pci_dev *dev)
+{
+	struct bcma_bus *bus = pci_get_drvdata(dev);
+	int err;
+
+	/* Host specific */
+	pci_set_power_state(dev, 0);
+	err = pci_enable_device(dev);
+	if (err)
+		return err;
+	pci_restore_state(dev);
+
+	/* Bus specific */
+	err = bcma_bus_resume(bus);
+	if (err)
+		return err;
+
+	return 0;
+}
+#else /* CONFIG_PM */
+# define bcma_host_pci_suspend	NULL
+# define bcma_host_pci_resume	NULL
+#endif /* CONFIG_PM */
+
 static DEFINE_PCI_DEVICE_TABLE(bcma_pci_bridge_tbl) = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, 0x0576) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, 0x4331) },
@@ -239,6 +277,8 @@ static struct pci_driver bcma_pci_bridge_driver = {
 	.id_table = bcma_pci_bridge_tbl,
 	.probe = bcma_host_pci_probe,
 	.remove = bcma_host_pci_remove,
+	.suspend = bcma_host_pci_suspend,
+	.resume = bcma_host_pci_resume,
 };
 
 int __init bcma_host_pci_init(void)

drivers/bcma/main.c

@@ -240,6 +240,22 @@ int __init bcma_bus_early_register(struct bcma_bus *bus,
 	return 0;
 }
 
+#ifdef CONFIG_PM
+int bcma_bus_resume(struct bcma_bus *bus)
+{
+	struct bcma_device *core;
+
+	/* Init CC core */
+	core = bcma_find_core(bus, BCMA_CORE_CHIPCOMMON);
+	if (core) {
+		bus->drv_cc.setup_done = false;
+		bcma_core_chipcommon_init(&bus->drv_cc);
+	}
+
+	return 0;
+}
+#endif
+
 int __bcma_driver_register(struct bcma_driver *drv, struct module *owner)
 {
 	drv->drv.name = drv->name;

drivers/block/cciss.c

@@ -1735,7 +1735,7 @@ static int cciss_ioctl(struct block_device *bdev, fmode_t mode,
 	case CCISS_BIG_PASSTHRU:
 		return cciss_bigpassthru(h, argp);
 
-	/* scsi_cmd_ioctl handles these, below, though some are not */
+	/* scsi_cmd_blk_ioctl handles these, below, though some are not */
 	/* very meaningful for cciss.  SG_IO is the main one people want. */
 
 	case SG_GET_VERSION_NUM:
@@ -1746,9 +1746,9 @@ static int cciss_ioctl(struct block_device *bdev, fmode_t mode,
 	case SG_EMULATED_HOST:
 	case SG_IO:
 	case SCSI_IOCTL_SEND_COMMAND:
-		return scsi_cmd_ioctl(disk->queue, disk, mode, cmd, argp);
+		return scsi_cmd_blk_ioctl(bdev, mode, cmd, argp);
 
-	/* scsi_cmd_ioctl would normally handle these, below, but */
+	/* scsi_cmd_blk_ioctl would normally handle these, below, but */
 	/* they aren't a good fit for cciss, as CD-ROMs are */
 	/* not supported, and we don't have any bus/target/lun */
 	/* which we present to the kernel. */

drivers/block/ub.c

@@ -1744,12 +1744,11 @@ static int ub_bd_release(struct gendisk *disk, fmode_t mode)
 static int ub_bd_ioctl(struct block_device *bdev, fmode_t mode,
     unsigned int cmd, unsigned long arg)
 {
-	struct gendisk *disk = bdev->bd_disk;
 	void __user *usermem = (void __user *) arg;
 	int ret;
 
 	mutex_lock(&ub_mutex);
-	ret = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, usermem);
+	ret = scsi_cmd_blk_ioctl(bdev, mode, cmd, usermem);
 	mutex_unlock(&ub_mutex);
 
 	return ret;

drivers/block/virtio_blk.c

@@ -243,8 +243,8 @@ static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
 		return -ENOTTY;
 
-	return scsi_cmd_ioctl(disk->queue, disk, mode, cmd,
-			      (void __user *)data);
+	return scsi_cmd_blk_ioctl(bdev, mode, cmd,
+				  (void __user *)data);
 }
 
 /* We provide getgeo only to please some old bootloader/partitioning tools */

drivers/cdrom/cdrom.c

@@ -2120,11 +2120,6 @@ static int cdrom_read_cdda_old(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 	if (!nr)
 		return -ENOMEM;
 
-	if (!access_ok(VERIFY_WRITE, ubuf, nframes * CD_FRAMESIZE_RAW)) {
-		ret = -EFAULT;
-		goto out;
-	}
-
 	cgc.data_direction = CGC_DATA_READ;
 	while (nframes > 0) {
 		if (nr > nframes)
@@ -2133,7 +2128,7 @@ static int cdrom_read_cdda_old(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 		ret = cdrom_read_block(cdi, &cgc, lba, nr, 1, CD_FRAMESIZE_RAW);
 		if (ret)
 			break;
-		if (__copy_to_user(ubuf, cgc.buffer, CD_FRAMESIZE_RAW * nr)) {
+		if (copy_to_user(ubuf, cgc.buffer, CD_FRAMESIZE_RAW * nr)) {
 			ret = -EFAULT;
 			break;
 		}
@@ -2141,7 +2136,6 @@ static int cdrom_read_cdda_old(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 		nframes -= nr;
 		lba += nr;
 	}
-out:
 	kfree(cgc.buffer);
 	return ret;
 }
@@ -2747,12 +2741,11 @@ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
 {
 	void __user *argp = (void __user *)arg;
 	int ret;
-	struct gendisk *disk = bdev->bd_disk;
 
 	/*
 	 * Try the generic SCSI command ioctl's first.
 	 */
-	ret = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, argp);
+	ret = scsi_cmd_blk_ioctl(bdev, mode, cmd, argp);
 	if (ret != -ENOTTY)
 		return ret;
 

drivers/char/tpm/tpm_tis.c

@@ -432,6 +432,9 @@ static int probe_itpm(struct tpm_chip *chip)
 out:
 	itpm = rem_itpm;
 	tpm_tis_ready(chip);
+	/* some TPMs need a break here otherwise they will not work
+	 * correctly on the immediately subsequent command */
+	msleep(chip->vendor.timeout_b);
 	release_locality(chip, chip->vendor.locality, 0);
 
 	return rc;

drivers/cpufreq/powernow-k8.c

@@ -54,6 +54,9 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
 
 static int cpu_family = CPU_OPTERON;
 
+/* array to map SW pstate number to acpi state */
+static u32 ps_to_as[8];
+
 /* core performance boost */
 static bool cpb_capable, cpb_enabled;
 static struct msr __percpu *msrs;
@@ -80,9 +83,9 @@ static u32 find_khz_freq_from_fid(u32 fid)
 }
 
 static u32 find_khz_freq_from_pstate(struct cpufreq_frequency_table *data,
-		u32 pstate)
+				     u32 pstate)
 {
-	return data[pstate].frequency;
+	return data[ps_to_as[pstate]].frequency;
 }
 
 /* Return the vco fid for an input fid
@@ -926,23 +929,27 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
 			invalidate_entry(powernow_table, i);
 			continue;
 		}
-		rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi);
-		if (!(hi & HW_PSTATE_VALID_MASK)) {
-			pr_debug("invalid pstate %d, ignoring\n", index);
-			invalidate_entry(powernow_table, i);
-			continue;
-		}
 
-		powernow_table[i].index = index;
+		ps_to_as[index] = i;
 
 		/* Frequency may be rounded for these */
 		if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
 				 || boot_cpu_data.x86 == 0x11) {
+
+			rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi);
+			if (!(hi & HW_PSTATE_VALID_MASK)) {
+				pr_debug("invalid pstate %d, ignoring\n", index);
+				invalidate_entry(powernow_table, i);
+				continue;
+			}
+
 			powernow_table[i].frequency =
 				freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
 		} else
 			powernow_table[i].frequency =
 				data->acpi_data.states[i].core_frequency * 1000;
+
+		powernow_table[i].index = index;
 	}
 	return 0;
 }
@@ -1189,7 +1196,8 @@ static int powernowk8_target(struct cpufreq_policy *pol,
 	powernow_k8_acpi_pst_values(data, newstate);
 
 	if (cpu_family == CPU_HW_PSTATE)
-		ret = transition_frequency_pstate(data, newstate);
+		ret = transition_frequency_pstate(data,
+			data->powernow_table[newstate].index);
 	else
 		ret = transition_frequency_fidvid(data, newstate);
 	if (ret) {
@@ -1202,7 +1210,7 @@ static int powernowk8_target(struct cpufreq_policy *pol,
 
 	if (cpu_family == CPU_HW_PSTATE)
 		pol->cur = find_khz_freq_from_pstate(data->powernow_table,
-				newstate);
+				data->powernow_table[newstate].index);
 	else
 		pol->cur = find_khz_freq_from_fid(data->currfid);
 	ret = 0;

drivers/dma/at_hdmac.c

@@ -1286,7 +1286,7 @@ static int __init at_dma_probe(struct platform_device *pdev)
 
 		tasklet_init(&atchan->tasklet, atc_tasklet,
 				(unsigned long)atchan);
-		atc_enable_irq(atchan);
+		atc_enable_chan_irq(atdma, i);
 	}
 
 	/* set base routines */
@@ -1353,7 +1353,7 @@ static int __exit at_dma_remove(struct platform_device *pdev)
 		struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 
 		/* Disable interrupts */
-		atc_disable_irq(atchan);
+		atc_disable_chan_irq(atdma, chan->chan_id);
 		tasklet_disable(&atchan->tasklet);
 
 		tasklet_kill(&atchan->tasklet);

drivers/dma/at_hdmac_regs.h

@@ -326,28 +326,27 @@ static void atc_dump_lli(struct at_dma_chan *atchan, struct at_lli *lli)
 }
 
 
-static void atc_setup_irq(struct at_dma_chan *atchan, int on)
+static void atc_setup_irq(struct at_dma *atdma, int chan_id, int on)
 {
-	struct at_dma	*atdma = to_at_dma(atchan->chan_common.device);
-	u32		ebci;
+	u32 ebci;
 
 	/* enable interrupts on buffer transfer completion & error */
-	ebci =    AT_DMA_BTC(atchan->chan_common.chan_id)
-		| AT_DMA_ERR(atchan->chan_common.chan_id);
+	ebci =    AT_DMA_BTC(chan_id)
+		| AT_DMA_ERR(chan_id);
 	if (on)
 		dma_writel(atdma, EBCIER, ebci);
 	else
 		dma_writel(atdma, EBCIDR, ebci);
 }
 
-static inline void atc_enable_irq(struct at_dma_chan *atchan)
+static void atc_enable_chan_irq(struct at_dma *atdma, int chan_id)
 {
-	atc_setup_irq(atchan, 1);
+	atc_setup_irq(atdma, chan_id, 1);
 }
 
-static inline void atc_disable_irq(struct at_dma_chan *atchan)
+static void atc_disable_chan_irq(struct at_dma *atdma, int chan_id)
 {
-	atc_setup_irq(atchan, 0);
+	atc_setup_irq(atdma, chan_id, 0);
 }
 
 

drivers/firewire/ohci.c

@@ -263,6 +263,7 @@ static inline struct fw_ohci *fw_ohci(struct fw_card *card)
 static char ohci_driver_name[] = KBUILD_MODNAME;
 
 #define PCI_DEVICE_ID_AGERE_FW643	0x5901
+#define PCI_DEVICE_ID_CREATIVE_SB1394	0x4001
 #define PCI_DEVICE_ID_JMICRON_JMB38X_FW	0x2380
 #define PCI_DEVICE_ID_TI_TSB12LV22	0x8009
 #define PCI_DEVICE_ID_TI_TSB12LV26	0x8020
@@ -289,6 +290,9 @@ static const struct {
 	{PCI_VENDOR_ID_ATT, PCI_DEVICE_ID_AGERE_FW643, 6,
 		QUIRK_NO_MSI},
 
+	{PCI_VENDOR_ID_CREATIVE, PCI_DEVICE_ID_CREATIVE_SB1394, PCI_ANY_ID,
+		QUIRK_RESET_PACKET},
+
 	{PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB38X_FW, PCI_ANY_ID,
 		QUIRK_NO_MSI},
 
@@ -299,7 +303,7 @@ static const struct {
 		QUIRK_NO_MSI},
 
 	{PCI_VENDOR_ID_RICOH, PCI_ANY_ID, PCI_ANY_ID,
-		QUIRK_CYCLE_TIMER},
+		QUIRK_CYCLE_TIMER | QUIRK_NO_MSI},
 
 	{PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_TSB12LV22, PCI_ANY_ID,
 		QUIRK_CYCLE_TIMER | QUIRK_RESET_PACKET | QUIRK_NO_1394A},

drivers/gpu/drm/drm_auth.c

@@ -101,7 +101,7 @@ static int drm_add_magic(struct drm_master *master, struct drm_file *priv,
  * Searches and unlinks the entry in drm_device::magiclist with the magic
  * number hash key, while holding the drm_device::struct_mutex lock.
  */
-static int drm_remove_magic(struct drm_master *master, drm_magic_t magic)
+int drm_remove_magic(struct drm_master *master, drm_magic_t magic)
 {
 	struct drm_magic_entry *pt;
 	struct drm_hash_item *hash;
@@ -136,6 +136,8 @@ static int drm_remove_magic(struct drm_master *master, drm_magic_t magic)
  * If there is a magic number in drm_file::magic then use it, otherwise
  * searches an unique non-zero magic number and add it associating it with \p
  * file_priv.
+ * This ioctl needs protection by the drm_global_mutex, which protects
+ * struct drm_file::magic and struct drm_magic_entry::priv.
  */
 int drm_getmagic(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
@@ -173,6 +175,8 @@ int drm_getmagic(struct drm_device *dev, void *data, struct drm_file *file_priv)
  * \return zero if authentication successed, or a negative number otherwise.
  *
  * Checks if \p file_priv is associated with the magic number passed in \arg.
+ * This ioctl needs protection by the drm_global_mutex, which protects
+ * struct drm_file::magic and struct drm_magic_entry::priv.
  */
 int drm_authmagic(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)

drivers/gpu/drm/drm_fops.c

@@ -487,6 +487,11 @@ int drm_release(struct inode *inode, struct file *filp)
 		  (long)old_encode_dev(file_priv->minor->device),
 		  dev->open_count);
 
+	/* Release any auth tokens that might point to this file_priv,
+	   (do that under the drm_global_mutex) */
+	if (file_priv->magic)
+		(void) drm_remove_magic(file_priv->master, file_priv->magic);
+
 	/* if the master has gone away we can't do anything with the lock */
 	if (file_priv->minor->master)
 		drm_master_release(dev, filp);

drivers/gpu/drm/i915/i915_debugfs.c

@@ -1314,9 +1314,13 @@ static int i915_gen6_forcewake_count_info(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned forcewake_count;
 
-	seq_printf(m, "forcewake count = %d\n",
-		   atomic_read(&dev_priv->forcewake_count));
+	spin_lock_irq(&dev_priv->gt_lock);
+	forcewake_count = dev_priv->forcewake_count;
+	spin_unlock_irq(&dev_priv->gt_lock);
+
+	seq_printf(m, "forcewake count = %u\n", forcewake_count);
 
 	return 0;
 }

drivers/gpu/drm/i915/i915_dma.c

@@ -2042,6 +2042,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	if (!IS_I945G(dev) && !IS_I945GM(dev))
 		pci_enable_msi(dev->pdev);
 
+	spin_lock_init(&dev_priv->gt_lock);
 	spin_lock_init(&dev_priv->irq_lock);
 	spin_lock_init(&dev_priv->error_lock);
 	spin_lock_init(&dev_priv->rps_lock);

drivers/gpu/drm/i915/i915_drv.c

@@ -368,11 +368,12 @@ void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
  */
 void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 {
-	WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
+	unsigned long irqflags;
 
-	/* Forcewake is atomic in case we get in here without the lock */
-	if (atomic_add_return(1, &dev_priv->forcewake_count) == 1)
+	spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
+	if (dev_priv->forcewake_count++ == 0)
 		dev_priv->display.force_wake_get(dev_priv);
+	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
 }
 
 void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
@@ -392,10 +393,12 @@ void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
  */
 void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 {
-	WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
+	unsigned long irqflags;
 
-	if (atomic_dec_and_test(&dev_priv->forcewake_count))
+	spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
+	if (--dev_priv->forcewake_count == 0)
 		dev_priv->display.force_wake_put(dev_priv);
+	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
 }
 
 void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
@@ -626,6 +629,7 @@ int i915_reset(struct drm_device *dev, u8 flags)
 	 * need to
 	 */
 	bool need_display = true;
+	unsigned long irqflags;
 	int ret;
 
 	if (!i915_try_reset)
@@ -644,8 +648,10 @@ int i915_reset(struct drm_device *dev, u8 flags)
 	case 6:
 		ret = gen6_do_reset(dev, flags);
 		/* If reset with a user forcewake, try to restore */
-		if (atomic_read(&dev_priv->forcewake_count))
-			__gen6_gt_force_wake_get(dev_priv);
+		spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
+		if (dev_priv->forcewake_count)
+			dev_priv->display.force_wake_get(dev_priv);
+		spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
 		break;
 	case 5:
 		ret = ironlake_do_reset(dev, flags);

drivers/gpu/drm/i915/i915_drv.h

@@ -286,7 +286,13 @@ typedef struct drm_i915_private {
 	int relative_constants_mode;
 
 	void __iomem *regs;
-	u32 gt_fifo_count;
+	/** gt_fifo_count and the subsequent register write are synchronized
+	 * with dev->struct_mutex. */
+	unsigned gt_fifo_count;
+	/** forcewake_count is protected by gt_lock */
+	unsigned forcewake_count;
+	/** gt_lock is also taken in irq contexts. */
+	struct spinlock gt_lock;
 
 	struct intel_gmbus {
 		struct i2c_adapter adapter;
@@ -337,6 +343,8 @@ typedef struct drm_i915_private {
 	struct timer_list hangcheck_timer;
 	int hangcheck_count;
 	uint32_t last_acthd;
+	uint32_t last_acthd_bsd;
+	uint32_t last_acthd_blt;
 	uint32_t last_instdone;
 	uint32_t last_instdone1;
 
@@ -736,8 +744,6 @@ typedef struct drm_i915_private {
 
 	struct drm_property *broadcast_rgb_property;
 	struct drm_property *force_audio_property;
-
-	atomic_t forcewake_count;
 } drm_i915_private_t;
 
 enum i915_cache_level {

drivers/gpu/drm/i915/i915_irq.c

@@ -1669,7 +1669,7 @@ void i915_hangcheck_elapsed(unsigned long data)
 {
 	struct drm_device *dev = (struct drm_device *)data;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	uint32_t acthd, instdone, instdone1;
+	uint32_t acthd, instdone, instdone1, acthd_bsd, acthd_blt;
 	bool err = false;
 
 	if (!i915_enable_hangcheck)
@@ -1686,16 +1686,21 @@ void i915_hangcheck_elapsed(unsigned long data)
 	}
 
 	if (INTEL_INFO(dev)->gen < 4) {
-		acthd = I915_READ(ACTHD);
 		instdone = I915_READ(INSTDONE);
 		instdone1 = 0;
 	} else {
-		acthd = I915_READ(ACTHD_I965);
 		instdone = I915_READ(INSTDONE_I965);
 		instdone1 = I915_READ(INSTDONE1);
 	}
+	acthd = intel_ring_get_active_head(&dev_priv->ring[RCS]);
+	acthd_bsd = HAS_BSD(dev) ?
+		intel_ring_get_active_head(&dev_priv->ring[VCS]) : 0;
+	acthd_blt = HAS_BLT(dev) ?
+		intel_ring_get_active_head(&dev_priv->ring[BCS]) : 0;
 
 	if (dev_priv->last_acthd == acthd &&
+	    dev_priv->last_acthd_bsd == acthd_bsd &&
+	    dev_priv->last_acthd_blt == acthd_blt &&
 	    dev_priv->last_instdone == instdone &&
 	    dev_priv->last_instdone1 == instdone1) {
 		if (dev_priv->hangcheck_count++ > 1) {
@@ -1727,6 +1732,8 @@ void i915_hangcheck_elapsed(unsigned long data)
 		dev_priv->hangcheck_count = 0;
 
 		dev_priv->last_acthd = acthd;
+		dev_priv->last_acthd_bsd = acthd_bsd;
+		dev_priv->last_acthd_blt = acthd_blt;
 		dev_priv->last_instdone = instdone;
 		dev_priv->last_instdone1 = instdone1;
 	}

drivers/gpu/drm/i915/i915_suspend.c

@@ -34,6 +34,10 @@ static bool i915_pipe_enabled(struct drm_device *dev, enum pipe pipe)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32	dpll_reg;
 
+	/* On IVB, 3rd pipe shares PLL with another one */
+	if (pipe > 1)
+		return false;
+
 	if (HAS_PCH_SPLIT(dev))
 		dpll_reg = (pipe == PIPE_A) ? _PCH_DPLL_A : _PCH_DPLL_B;
 	else
@@ -822,7 +826,7 @@ int i915_save_state(struct drm_device *dev)
 
 	if (IS_IRONLAKE_M(dev))
 		ironlake_disable_drps(dev);
-	if (IS_GEN6(dev))
+	if (INTEL_INFO(dev)->gen >= 6)
 		gen6_disable_rps(dev);
 
 	/* Cache mode state */
@@ -881,7 +885,7 @@ int i915_restore_state(struct drm_device *dev)
 		intel_init_emon(dev);
 	}
 
-	if (IS_GEN6(dev)) {
+	if (INTEL_INFO(dev)->gen >= 6) {
 		gen6_enable_rps(dev_priv);
 		gen6_update_ring_freq(dev_priv);
 	}

drivers/gpu/drm/i915/intel_dp.c

@@ -208,17 +208,8 @@ intel_dp_link_clock(uint8_t link_bw)
  */
 
 static int
-intel_dp_link_required(struct intel_dp *intel_dp, int pixel_clock, int check_bpp)
+intel_dp_link_required(int pixel_clock, int bpp)
 {
-	struct drm_crtc *crtc = intel_dp->base.base.crtc;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int bpp = 24;
-
-	if (check_bpp)
-		bpp = check_bpp;
-	else if (intel_crtc)
-		bpp = intel_crtc->bpp;
-
 	return (pixel_clock * bpp + 9) / 10;
 }
 
@@ -245,12 +236,11 @@ intel_dp_mode_valid(struct drm_connector *connector,
 			return MODE_PANEL;
 	}
 
-	mode_rate = intel_dp_link_required(intel_dp, mode->clock, 0);
+	mode_rate = intel_dp_link_required(mode->clock, 24);
 	max_rate = intel_dp_max_data_rate(max_link_clock, max_lanes);
 
 	if (mode_rate > max_rate) {
-			mode_rate = intel_dp_link_required(intel_dp,
-							   mode->clock, 18);
+			mode_rate = intel_dp_link_required(mode->clock, 18);
 			if (mode_rate > max_rate)
 				return MODE_CLOCK_HIGH;
 			else
@@ -683,7 +673,7 @@ intel_dp_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode,
 	int lane_count, clock;
 	int max_lane_count = intel_dp_max_lane_count(intel_dp);
 	int max_clock = intel_dp_max_link_bw(intel_dp) == DP_LINK_BW_2_7 ? 1 : 0;
-	int bpp = mode->private_flags & INTEL_MODE_DP_FORCE_6BPC ? 18 : 0;
+	int bpp = mode->private_flags & INTEL_MODE_DP_FORCE_6BPC ? 18 : 24;
 	static int bws[2] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7 };
 
 	if (is_edp(intel_dp) && intel_dp->panel_fixed_mode) {
@@ -701,7 +691,7 @@ intel_dp_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode,
 		for (clock = 0; clock <= max_clock; clock++) {
 			int link_avail = intel_dp_max_data_rate(intel_dp_link_clock(bws[clock]), lane_count);
 
-			if (intel_dp_link_required(intel_dp, mode->clock, bpp)
+			if (intel_dp_link_required(mode->clock, bpp)
 					<= link_avail) {
 				intel_dp->link_bw = bws[clock];
 				intel_dp->lane_count = lane_count;
@@ -1926,6 +1916,7 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 			intel_wait_for_vblank(dev, to_intel_crtc(crtc)->pipe);
 	}
 
+	DP &= ~DP_AUDIO_OUTPUT_ENABLE;
 	I915_WRITE(intel_dp->output_reg, DP & ~DP_PORT_EN);
 	POSTING_READ(intel_dp->output_reg);
 	msleep(intel_dp->panel_power_down_delay);

drivers/gpu/drm/i915/intel_hdmi.c

@@ -269,6 +269,10 @@ static void intel_hdmi_dpms(struct drm_encoder *encoder, int mode)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	u32 temp;
+	u32 enable_bits = SDVO_ENABLE;
+
+	if (intel_hdmi->has_audio)
+		enable_bits |= SDVO_AUDIO_ENABLE;
 
 	temp = I915_READ(intel_hdmi->sdvox_reg);
 
@@ -281,9 +285,9 @@ static void intel_hdmi_dpms(struct drm_encoder *encoder, int mode)
 	}
 
 	if (mode != DRM_MODE_DPMS_ON) {
-		temp &= ~SDVO_ENABLE;
+		temp &= ~enable_bits;
 	} else {
-		temp |= SDVO_ENABLE;
+		temp |= enable_bits;
 	}
 
 	I915_WRITE(intel_hdmi->sdvox_reg, temp);

drivers/gpu/drm/i915/intel_lvds.c

@@ -692,6 +692,14 @@ static const struct dmi_system_id intel_no_lvds[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "i915GMm-HFS"),
 		},
 	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+                .ident = "AOpen i45GMx-I",
+                .matches = {
+                        DMI_MATCH(DMI_BOARD_VENDOR, "AOpen"),
+                        DMI_MATCH(DMI_BOARD_NAME, "i45GMx-I"),
+                },
+        },
 	{
 		.callback = intel_no_lvds_dmi_callback,
 		.ident = "Aopen i945GTt-VFA",

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -630,6 +630,19 @@ render_ring_add_request(struct intel_ring_buffer *ring,
 	return 0;
 }
 
+static u32
+gen6_ring_get_seqno(struct intel_ring_buffer *ring)
+{
+	struct drm_device *dev = ring->dev;
+
+	/* Workaround to force correct ordering between irq and seqno writes on
+	 * ivb (and maybe also on snb) by reading from a CS register (like
+	 * ACTHD) before reading the status page. */
+	if (IS_GEN7(dev))
+		intel_ring_get_active_head(ring);
+	return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
+}
+
 static u32
 ring_get_seqno(struct intel_ring_buffer *ring)
 {
@@ -795,6 +808,12 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring, u32 gflag, u32 rflag)
 	if (!dev->irq_enabled)
 	       return false;
 
+	/* It looks like we need to prevent the gt from suspending while waiting
+	 * for an notifiy irq, otherwise irqs seem to get lost on at least the
+	 * blt/bsd rings on ivb. */
+	if (IS_GEN7(dev))
+		gen6_gt_force_wake_get(dev_priv);
+
 	spin_lock(&ring->irq_lock);
 	if (ring->irq_refcount++ == 0) {
 		ring->irq_mask &= ~rflag;
@@ -819,6 +838,9 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring, u32 gflag, u32 rflag)
 		ironlake_disable_irq(dev_priv, gflag);
 	}
 	spin_unlock(&ring->irq_lock);
+
+	if (IS_GEN7(dev))
+		gen6_gt_force_wake_put(dev_priv);
 }
 
 static bool
@@ -1316,7 +1338,7 @@ static const struct intel_ring_buffer gen6_bsd_ring = {
 	.write_tail		= gen6_bsd_ring_write_tail,
 	.flush			= gen6_ring_flush,
 	.add_request		= gen6_add_request,
-	.get_seqno		= ring_get_seqno,
+	.get_seqno		= gen6_ring_get_seqno,
 	.irq_get		= gen6_bsd_ring_get_irq,
 	.irq_put		= gen6_bsd_ring_put_irq,
 	.dispatch_execbuffer	= gen6_ring_dispatch_execbuffer,
@@ -1451,7 +1473,7 @@ static const struct intel_ring_buffer gen6_blt_ring = {
 	.write_tail		= ring_write_tail,
 	.flush			= blt_ring_flush,
 	.add_request		= gen6_add_request,
-	.get_seqno		= ring_get_seqno,
+	.get_seqno		= gen6_ring_get_seqno,
 	.irq_get		= blt_ring_get_irq,
 	.irq_put		= blt_ring_put_irq,
 	.dispatch_execbuffer	= gen6_ring_dispatch_execbuffer,
@@ -1474,6 +1496,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->flush = gen6_render_ring_flush;
 		ring->irq_get = gen6_render_ring_get_irq;
 		ring->irq_put = gen6_render_ring_put_irq;
+		ring->get_seqno = gen6_ring_get_seqno;
 	} else if (IS_GEN5(dev)) {
 		ring->add_request = pc_render_add_request;
 		ring->get_seqno = pc_render_get_seqno;

drivers/gpu/drm/i915/intel_sdvo.c

@@ -1066,15 +1066,13 @@ static void intel_sdvo_mode_set(struct drm_encoder *encoder,
 
 	/* Set the SDVO control regs. */
 	if (INTEL_INFO(dev)->gen >= 4) {
-		sdvox = 0;
+		/* The real mode polarity is set by the SDVO commands, using
+		 * struct intel_sdvo_dtd. */
+		sdvox = SDVO_VSYNC_ACTIVE_HIGH | SDVO_HSYNC_ACTIVE_HIGH;
 		if (intel_sdvo->is_hdmi)
 			sdvox |= intel_sdvo->color_range;
 		if (INTEL_INFO(dev)->gen < 5)
 			sdvox |= SDVO_BORDER_ENABLE;
-		if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
-			sdvox |= SDVO_VSYNC_ACTIVE_HIGH;
-		if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
-			sdvox |= SDVO_HSYNC_ACTIVE_HIGH;
 	} else {
 		sdvox = I915_READ(intel_sdvo->sdvo_reg);
 		switch (intel_sdvo->sdvo_reg) {

drivers/gpu/drm/i915/intel_tv.c

@@ -417,7 +417,7 @@ static const struct tv_mode tv_modes[] = {
 	{
 		.name		= "NTSC-M",
 		.clock		= 108000,
-		.refresh	= 29970,
+		.refresh	= 59940,
 		.oversample	= TV_OVERSAMPLE_8X,
 		.component_only = 0,
 		/* 525 Lines, 60 Fields, 15.734KHz line, Sub-Carrier 3.580MHz */
@@ -460,7 +460,7 @@ static const struct tv_mode tv_modes[] = {
 	{
 		.name		= "NTSC-443",
 		.clock		= 108000,
-		.refresh	= 29970,
+		.refresh	= 59940,
 		.oversample	= TV_OVERSAMPLE_8X,
 		.component_only = 0,
 		/* 525 Lines, 60 Fields, 15.734KHz line, Sub-Carrier 4.43MHz */
@@ -502,7 +502,7 @@ static const struct tv_mode tv_modes[] = {
 	{
 		.name		= "NTSC-J",
 		.clock		= 108000,
-		.refresh	= 29970,
+		.refresh	= 59940,
 		.oversample	= TV_OVERSAMPLE_8X,
 		.component_only = 0,
 
@@ -545,7 +545,7 @@ static const struct tv_mode tv_modes[] = {
 	{
 		.name		= "PAL-M",
 		.clock		= 108000,
-		.refresh	= 29970,
+		.refresh	= 59940,
 		.oversample	= TV_OVERSAMPLE_8X,
 		.component_only = 0,
 
@@ -589,7 +589,7 @@ static const struct tv_mode tv_modes[] = {
 		/* 625 Lines, 50 Fields, 15.625KHz line, Sub-Carrier 4.434MHz */
 		.name	    = "PAL-N",
 		.clock		= 108000,
-		.refresh	= 25000,
+		.refresh	= 50000,
 		.oversample	= TV_OVERSAMPLE_8X,
 		.component_only = 0,
 
@@ -634,7 +634,7 @@ static const struct tv_mode tv_modes[] = {
 		/* 625 Lines, 50 Fields, 15.625KHz line, Sub-Carrier 4.434MHz */
 		.name	    = "PAL",
 		.clock		= 108000,
-		.refresh	= 25000,
+		.refresh	= 50000,
 		.oversample	= TV_OVERSAMPLE_8X,
 		.component_only = 0,
 
@@ -821,7 +821,7 @@ static const struct tv_mode tv_modes[] = {
 	{
 		.name       = "1080i@50Hz",
 		.clock		= 148800,
-		.refresh	= 25000,
+		.refresh	= 50000,
 		.oversample     = TV_OVERSAMPLE_2X,
 		.component_only = 1,
 
@@ -847,7 +847,7 @@ static const struct tv_mode tv_modes[] = {
 	{
 		.name       = "1080i@60Hz",
 		.clock		= 148800,
-		.refresh	= 30000,
+		.refresh	= 60000,
 		.oversample     = TV_OVERSAMPLE_2X,
 		.component_only = 1,
 

drivers/gpu/drm/nouveau/nouveau_gem.c

@@ -379,6 +379,25 @@ retry:
 	return 0;
 }
 
+static int
+validate_sync(struct nouveau_channel *chan, struct nouveau_bo *nvbo)
+{
+	struct nouveau_fence *fence = NULL;
+	int ret = 0;
+
+	spin_lock(&nvbo->bo.bdev->fence_lock);
+	if (nvbo->bo.sync_obj)
+		fence = nouveau_fence_ref(nvbo->bo.sync_obj);
+	spin_unlock(&nvbo->bo.bdev->fence_lock);
+
+	if (fence) {
+		ret = nouveau_fence_sync(fence, chan);
+		nouveau_fence_unref(&fence);
+	}
+
+	return ret;
+}
+
 static int
 validate_list(struct nouveau_channel *chan, struct list_head *list,
 	      struct drm_nouveau_gem_pushbuf_bo *pbbo, uint64_t user_pbbo_ptr)
@@ -393,7 +412,7 @@ validate_list(struct nouveau_channel *chan, struct list_head *list,
 	list_for_each_entry(nvbo, list, entry) {
 		struct drm_nouveau_gem_pushbuf_bo *b = &pbbo[nvbo->pbbo_index];
 
-		ret = nouveau_fence_sync(nvbo->bo.sync_obj, chan);
+		ret = validate_sync(chan, nvbo);
 		if (unlikely(ret)) {
 			NV_ERROR(dev, "fail pre-validate sync\n");
 			return ret;
@@ -416,7 +435,7 @@ validate_list(struct nouveau_channel *chan, struct list_head *list,
 			return ret;
 		}
 
-		ret = nouveau_fence_sync(nvbo->bo.sync_obj, chan);
+		ret = validate_sync(chan, nvbo);
 		if (unlikely(ret)) {
 			NV_ERROR(dev, "fail post-validate sync\n");
 			return ret;

drivers/gpu/drm/radeon/atombios_crtc.c

@@ -1189,7 +1189,7 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(EVERGREEN_GRPH_ENABLE + radeon_crtc->crtc_offset, 1);
 
 	WREG32(EVERGREEN_DESKTOP_HEIGHT + radeon_crtc->crtc_offset,
-	       crtc->mode.vdisplay);
+	       target_fb->height);
 	x &= ~3;
 	y &= ~1;
 	WREG32(EVERGREEN_VIEWPORT_START + radeon_crtc->crtc_offset,
@@ -1358,7 +1358,7 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(AVIVO_D1GRPH_ENABLE + radeon_crtc->crtc_offset, 1);
 
 	WREG32(AVIVO_D1MODE_DESKTOP_HEIGHT + radeon_crtc->crtc_offset,
-	       crtc->mode.vdisplay);
+	       target_fb->height);
 	x &= ~3;
 	y &= ~1;
 	WREG32(AVIVO_D1MODE_VIEWPORT_START + radeon_crtc->crtc_offset,

drivers/gpu/drm/radeon/atombios_dp.c

@@ -549,8 +549,8 @@ bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector)
 	return false;
 }
 
-static void radeon_dp_set_panel_mode(struct drm_encoder *encoder,
-				     struct drm_connector *connector)
+int radeon_dp_get_panel_mode(struct drm_encoder *encoder,
+			     struct drm_connector *connector)
 {
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
@@ -558,28 +558,33 @@ static void radeon_dp_set_panel_mode(struct drm_encoder *encoder,
 	int panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE;
 
 	if (!ASIC_IS_DCE4(rdev))
-		return;
+		return panel_mode;
 
 	if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) ==
 	    ENCODER_OBJECT_ID_NUTMEG)
 		panel_mode = DP_PANEL_MODE_INTERNAL_DP1_MODE;
 	else if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) ==
-		 ENCODER_OBJECT_ID_TRAVIS)
-		panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
-	else if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
+		 ENCODER_OBJECT_ID_TRAVIS) {
+		u8 id[6];
+		int i;
+		for (i = 0; i < 6; i++)
+			id[i] = radeon_read_dpcd_reg(radeon_connector, 0x503 + i);
+		if (id[0] == 0x73 &&
+		    id[1] == 0x69 &&
+		    id[2] == 0x76 &&
+		    id[3] == 0x61 &&
+		    id[4] == 0x72 &&
+		    id[5] == 0x54)
+			panel_mode = DP_PANEL_MODE_INTERNAL_DP1_MODE;
+		else
+			panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
+	} else if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
 		u8 tmp = radeon_read_dpcd_reg(radeon_connector, DP_EDP_CONFIGURATION_CAP);
 		if (tmp & 1)
 			panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
 	}
 
-	atombios_dig_encoder_setup(encoder,
-				   ATOM_ENCODER_CMD_SETUP_PANEL_MODE,
-				   panel_mode);
-
-	if ((connector->connector_type == DRM_MODE_CONNECTOR_eDP) &&
-	    (panel_mode == DP_PANEL_MODE_INTERNAL_DP2_MODE)) {
-		radeon_write_dpcd_reg(radeon_connector, DP_EDP_CONFIGURATION_SET, 1);
-	}
+	return panel_mode;
 }
 
 void radeon_dp_set_link_config(struct drm_connector *connector,
@@ -717,6 +722,8 @@ static void radeon_dp_set_tp(struct radeon_dp_link_train_info *dp_info, int tp)
 
 static int radeon_dp_link_train_init(struct radeon_dp_link_train_info *dp_info)
 {
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(dp_info->encoder);
+	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 	u8 tmp;
 
 	/* power up the sink */
@@ -732,7 +739,10 @@ static int radeon_dp_link_train_init(struct radeon_dp_link_train_info *dp_info)
 		radeon_write_dpcd_reg(dp_info->radeon_connector,
 				      DP_DOWNSPREAD_CTRL, 0);
 
-	radeon_dp_set_panel_mode(dp_info->encoder, dp_info->connector);
+	if ((dp_info->connector->connector_type == DRM_MODE_CONNECTOR_eDP) &&
+	    (dig->panel_mode == DP_PANEL_MODE_INTERNAL_DP2_MODE)) {
+		radeon_write_dpcd_reg(dp_info->radeon_connector, DP_EDP_CONFIGURATION_SET, 1);
+	}
 
 	/* set the lane count on the sink */
 	tmp = dp_info->dp_lane_count;

drivers/gpu/drm/radeon/atombios_encoders.c

@@ -1352,7 +1352,8 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
 		/* some early dce3.2 boards have a bug in their transmitter control table */
-		if ((rdev->family == CHIP_RV710) || (rdev->family == CHIP_RV730))
+		if ((rdev->family == CHIP_RV710) || (rdev->family == CHIP_RV730) ||
+		    ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev))
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
 		else
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
@@ -1362,8 +1363,6 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 							     ATOM_TRANSMITTER_ACTION_POWER_ON);
 				radeon_dig_connector->edp_on = true;
 			}
-			if (ASIC_IS_DCE4(rdev))
-				atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_OFF, 0);
 			radeon_dp_link_train(encoder, connector);
 			if (ASIC_IS_DCE4(rdev))
 				atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_ON, 0);
@@ -1374,7 +1373,10 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 	case DRM_MODE_DPMS_OFF:
-		atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE_OUTPUT, 0, 0);
+		if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev))
+			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
+		else
+			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE_OUTPUT, 0, 0);
 		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) {
 			if (ASIC_IS_DCE4(rdev))
 				atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_OFF, 0);
@@ -1821,7 +1823,21 @@ radeon_atom_encoder_mode_set(struct drm_encoder *encoder,
 	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
 	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
 	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
-		if (ASIC_IS_DCE4(rdev)) {
+		if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) {
+			struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+			struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+
+			if (!connector)
+				dig->panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE;
+			else
+				dig->panel_mode = radeon_dp_get_panel_mode(encoder, connector);
+
+			/* setup and enable the encoder */
+			atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0);
+			atombios_dig_encoder_setup(encoder,
+						   ATOM_ENCODER_CMD_SETUP_PANEL_MODE,
+						   dig->panel_mode);
+		} else if (ASIC_IS_DCE4(rdev)) {
 			/* disable the transmitter */
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
 			/* setup and enable the encoder */

drivers/gpu/drm/radeon/r100.c

@@ -789,9 +789,7 @@ int r100_irq_process(struct radeon_device *rdev)
 			WREG32(RADEON_AIC_CNTL, msi_rearm | RS400_MSI_REARM);
 			break;
 		default:
-			msi_rearm = RREG32(RADEON_MSI_REARM_EN) & ~RV370_MSI_REARM_EN;
-			WREG32(RADEON_MSI_REARM_EN, msi_rearm);
-			WREG32(RADEON_MSI_REARM_EN, msi_rearm | RV370_MSI_REARM_EN);
+			WREG32(RADEON_MSI_REARM_EN, RV370_MSI_REARM_EN);
 			break;
 		}
 	}
@@ -2177,6 +2175,7 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev)
 void r100_bm_disable(struct radeon_device *rdev)
 {
 	u32 tmp;
+	u16 tmp16;
 
 	/* disable bus mastering */
 	tmp = RREG32(R_000030_BUS_CNTL);
@@ -2187,8 +2186,8 @@ void r100_bm_disable(struct radeon_device *rdev)
 	WREG32(R_000030_BUS_CNTL, (tmp & 0xFFFFFFFF) | 0x00000040);
 	tmp = RREG32(RADEON_BUS_CNTL);
 	mdelay(1);
-	pci_read_config_word(rdev->pdev, 0x4, (u16*)&tmp);
-	pci_write_config_word(rdev->pdev, 0x4, tmp & 0xFFFB);
+	pci_read_config_word(rdev->pdev, 0x4, &tmp16);
+	pci_write_config_word(rdev->pdev, 0x4, tmp16 & 0xFFFB);
 	mdelay(1);
 }
 

drivers/gpu/drm/radeon/r600_hdmi.c

@@ -196,6 +196,13 @@ static void r600_hdmi_videoinfoframe(
 	frame[0xD] = (right_bar >> 8);
 
 	r600_hdmi_infoframe_checksum(0x82, 0x02, 0x0D, frame);
+	/* Our header values (type, version, length) should be alright, Intel
+	 * is using the same. Checksum function also seems to be OK, it works
+	 * fine for audio infoframe. However calculated value is always lower
+	 * by 2 in comparison to fglrx. It breaks displaying anything in case
+	 * of TVs that strictly check the checksum. Hack it manually here to
+	 * workaround this issue. */
+	frame[0x0] += 2;
 
 	WREG32(offset+R600_HDMI_VIDEOINFOFRAME_0,
 		frame[0x0] | (frame[0x1] << 8) | (frame[0x2] << 16) | (frame[0x3] << 24));

drivers/gpu/drm/radeon/radeon_device.c

@@ -224,8 +224,11 @@ int radeon_wb_init(struct radeon_device *rdev)
 	if (radeon_no_wb == 1)
 		rdev->wb.enabled = false;
 	else {
-		/* often unreliable on AGP */
 		if (rdev->flags & RADEON_IS_AGP) {
+			/* often unreliable on AGP */
+			rdev->wb.enabled = false;
+		} else if (rdev->family < CHIP_R300) {
+			/* often unreliable on pre-r300 */
 			rdev->wb.enabled = false;
 		} else {
 			rdev->wb.enabled = true;
@@ -861,6 +864,8 @@ int radeon_suspend_kms(struct drm_device *dev, pm_message_t state)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
+	drm_kms_helper_poll_disable(dev);
+
 	/* turn off display hw */
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
@@ -947,6 +952,8 @@ int radeon_resume_kms(struct drm_device *dev)
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
 	}
+
+	drm_kms_helper_poll_enable(dev);
 	return 0;
 }