Merge branch '2.6.33.4' into rt/2.6.33

Conflicts:
	Makefile

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

20 files changed, 139 insertions, 73 deletions

diff --git a/arch/arm/mach-pxa/include/mach/colibri.h b/arch/arm/mach-pxa/include/mach/colibri.h
index 811743c56147..5f2ba8d9015c 100644
--- a/arch/arm/mach-pxa/include/mach/colibri.h
+++ b/arch/arm/mach-pxa/include/mach/colibri.h
@@ -2,6 +2,7 @@
 #define _COLIBRI_H_
 
 #include <net/ax88796.h>
+#include <mach/mfp.h>
 
 /*
  * common settings for all modules
diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h
index 7950ef4f032c..743385d7b5f2 100644
--- a/arch/mips/include/asm/mach-sibyte/war.h
+++ b/arch/mips/include/asm/mach-sibyte/war.h
@@ -16,7 +16,11 @@
 #if defined(CONFIG_SB1_PASS_1_WORKAROUNDS) || \
     defined(CONFIG_SB1_PASS_2_WORKAROUNDS)
 
-#define BCM1250_M3_WAR	1
+#ifndef __ASSEMBLY__
+extern int sb1250_m3_workaround_needed(void);
+#endif
+
+#define BCM1250_M3_WAR	sb1250_m3_workaround_needed()
 #define SIBYTE_1956_WAR	1
 
 #else
diff --git a/arch/mips/sibyte/sb1250/setup.c b/arch/mips/sibyte/sb1250/setup.c
index 0444da1e23c2..92da3155ce07 100644
--- a/arch/mips/sibyte/sb1250/setup.c
+++ b/arch/mips/sibyte/sb1250/setup.c
@@ -87,6 +87,21 @@ static int __init setup_bcm1250(void)
 	return ret;
 }
 
+int sb1250_m3_workaround_needed(void)
+{
+	switch (soc_type) {
+	case K_SYS_SOC_TYPE_BCM1250:
+	case K_SYS_SOC_TYPE_BCM1250_ALT:
+	case K_SYS_SOC_TYPE_BCM1250_ALT2:
+	case K_SYS_SOC_TYPE_BCM1125:
+	case K_SYS_SOC_TYPE_BCM1125H:
+		return soc_pass < K_SYS_REVISION_BCM1250_C0;
+
+	default:
+		return 0;
+	}
+}
+
 static int __init setup_bcm112x(void)
 {
 	int ret = 0;
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 925807488022..567cd57ad7b6 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -615,6 +615,17 @@ _GLOBAL(start_secondary_prolog)
 	std	r3,0(r1)		/* Zero the stack frame pointer	*/
 	bl	.start_secondary
 	b	.
+/*
+ * Reset stack pointer and call start_secondary
+ * to continue with online operation when woken up
+ * from cede in cpu offline.
+ */
+_GLOBAL(start_secondary_resume)
+	ld	r1,PACAKSAVE(r13)	/* Reload kernel stack pointer */
+	li	r3,0
+	std	r3,0(r1)		/* Zero the stack frame pointer	*/
+	bl	.start_secondary
+	b	.
 #endif
 
 /*
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index c5394728bf2e..1ce9dd51a2f6 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -155,15 +155,10 @@ static void settlbcam(int index, unsigned long virt, phys_addr_t phys,
 	if (cur_cpu_spec->cpu_features & MMU_FTR_BIG_PHYS)
 		TLBCAM[index].MAS7 = (u64)phys >> 32;
 
-#ifndef CONFIG_KGDB /* want user access for breakpoints */
 	if (flags & _PAGE_USER) {
 	   TLBCAM[index].MAS3 |= MAS3_UX | MAS3_UR;
 	   TLBCAM[index].MAS3 |= ((flags & _PAGE_RW) ? MAS3_UW : 0);
 	}
-#else
-	TLBCAM[index].MAS3 |= MAS3_UX | MAS3_UR;
-	TLBCAM[index].MAS3 |= ((flags & _PAGE_RW) ? MAS3_UW : 0);
-#endif
 
 	tlbcam_addrs[index].start = virt;
 	tlbcam_addrs[index].limit = virt + size - 1;
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 6ea4698d9176..b84237884737 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -122,44 +122,32 @@ static void pseries_mach_cpu_die(void)
 		if (!get_lppaca()->shared_proc)
 			get_lppaca()->donate_dedicated_cpu = 1;
 
-		printk(KERN_INFO
-			"cpu %u (hwid %u) ceding for offline with hint %d\n",
-			cpu, hwcpu, cede_latency_hint);
 		while (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
 			extended_cede_processor(cede_latency_hint);
-			printk(KERN_INFO "cpu %u (hwid %u) returned from cede.\n",
-				cpu, hwcpu);
-			printk(KERN_INFO
-			"Decrementer value = %x Timebase value = %llx\n",
-			get_dec(), get_tb());
 		}
 
-		printk(KERN_INFO "cpu %u (hwid %u) got prodded to go online\n",
-			cpu, hwcpu);
-
 		if (!get_lppaca()->shared_proc)
 			get_lppaca()->donate_dedicated_cpu = 0;
 		get_lppaca()->idle = 0;
-	}
 
-	if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) {
-		unregister_slb_shadow(hwcpu, __pa(get_slb_shadow()));
+		if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) {
+			unregister_slb_shadow(hwcpu, __pa(get_slb_shadow()));
 
-		/*
-		 * NOTE: Calling start_secondary() here for now to
-		 * start new context.
-		 * However, need to do it cleanly by resetting the
-		 * stack pointer.
-		 */
-		start_secondary();
+			/*
+			 * Call to start_secondary_resume() will not return.
+			 * Kernel stack will be reset and start_secondary()
+			 * will be called to continue the online operation.
+			 */
+			start_secondary_resume();
+		}
+	}
 
-	} else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) {
+	/* Requested state is CPU_STATE_OFFLINE at this point */
+	WARN_ON(get_preferred_offline_state(cpu) != CPU_STATE_OFFLINE);
 
-		set_cpu_current_state(cpu, CPU_STATE_OFFLINE);
-		unregister_slb_shadow(hard_smp_processor_id(),
-					__pa(get_slb_shadow()));
-		rtas_stop_self();
-	}
+	set_cpu_current_state(cpu, CPU_STATE_OFFLINE);
+	unregister_slb_shadow(hwcpu, __pa(get_slb_shadow()));
+	rtas_stop_self();
 
 	/* Should never get here... */
 	BUG();
diff --git a/arch/powerpc/platforms/pseries/offline_states.h b/arch/powerpc/platforms/pseries/offline_states.h
index 202d8692c6a2..75a6f480d931 100644
--- a/arch/powerpc/platforms/pseries/offline_states.h
+++ b/arch/powerpc/platforms/pseries/offline_states.h
@@ -35,4 +35,5 @@ static inline void set_default_offline_state(int cpu)
 
 extern enum cpu_state_vals get_preferred_offline_state(int cpu);
 extern int start_secondary(void);
+extern void start_secondary_resume(void);
 #endif
diff --git a/arch/sparc/include/asm/irqflags_64.h b/arch/sparc/include/asm/irqflags_64.h
index 8b49bf920df3..bfa1ea45b4cd 100644
--- a/arch/sparc/include/asm/irqflags_64.h
+++ b/arch/sparc/include/asm/irqflags_64.h
@@ -76,9 +76,26 @@ static inline int raw_irqs_disabled(void)
  */
 static inline unsigned long __raw_local_irq_save(void)
 {
-	unsigned long flags = __raw_local_save_flags();
-
-	raw_local_irq_disable();
+	unsigned long flags, tmp;
+
+	/* Disable interrupts to PIL_NORMAL_MAX unless we already
+	 * are using PIL_NMI, in which case PIL_NMI is retained.
+	 *
+	 * The only values we ever program into the %pil are 0,
+	 * PIL_NORMAL_MAX and PIL_NMI.
+	 *
+	 * Since PIL_NMI is the largest %pil value and all bits are
+	 * set in it (0xf), it doesn't matter what PIL_NORMAL_MAX
+	 * actually is.
+	 */
+	__asm__ __volatile__(
+		"rdpr	%%pil, %0\n\t"
+		"or	%0, %2, %1\n\t"
+		"wrpr	%1, 0x0, %%pil"
+		: "=r" (flags), "=r" (tmp)
+		: "i" (PIL_NORMAL_MAX)
+		: "memory"
+	);
 
 	return flags;
 }
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 39be9f256e5a..3df02de1984e 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -121,7 +121,7 @@ struct thread_info {
 #define THREAD_SHIFT PAGE_SHIFT
 #endif /* PAGE_SHIFT == 13 */
 
-#define PREEMPT_ACTIVE		0x4000000
+#define PREEMPT_ACTIVE		0x10000000
 
 /*
  * macros/functions for gaining access to the thread information structure
diff --git a/arch/sparc/kernel/pci_common.c b/arch/sparc/kernel/pci_common.c
index b775658a927d..8a000583b5cf 100644
--- a/arch/sparc/kernel/pci_common.c
+++ b/arch/sparc/kernel/pci_common.c
@@ -371,14 +371,19 @@ static void pci_register_iommu_region(struct pci_pbm_info *pbm)
 		struct resource *rp = kzalloc(sizeof(*rp), GFP_KERNEL);
 
 		if (!rp) {
-			prom_printf("Cannot allocate IOMMU resource.\n");
-			prom_halt();
+			pr_info("%s: Cannot allocate IOMMU resource.\n",
+				pbm->name);
+			return;
 		}
 		rp->name = "IOMMU";
 		rp->start = pbm->mem_space.start + (unsigned long) vdma[0];
 		rp->end = rp->start + (unsigned long) vdma[1] - 1UL;
 		rp->flags = IORESOURCE_BUSY;
-		request_resource(&pbm->mem_space, rp);
+		if (request_resource(&pbm->mem_space, rp)) {
+			pr_info("%s: Unable to request IOMMU resource.\n",
+				pbm->name);
+			kfree(rp);
+		}
 	}
 }
 
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index fd3cee4d117c..c720f0ccea1b 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -172,7 +172,17 @@ rtrap_xcall:
 		 nop
 		call			trace_hardirqs_on
 		 nop
-		wrpr			%l4, %pil
+		/* Do not actually set the %pil here.  We will do that
+		 * below after we clear PSTATE_IE in the %pstate register.
+		 * If we re-enable interrupts here, we can recurse down
+		 * the hardirq stack potentially endlessly, causing a
+		 * stack overflow.
+		 *
+		 * It is tempting to put this test and trace_hardirqs_on
+		 * call at the 'rt_continue' label, but that will not work
+		 * as that path hits unconditionally and we do not want to
+		 * execute this in NMI return paths, for example.
+		 */
 #endif
 rtrap_no_irq_enable:
 		andcc			%l1, TSTATE_PRIV, %l3
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 10f7bb9fc140..22cd4751ef8a 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2202,27 +2202,6 @@ void dump_stack(void)
 
 EXPORT_SYMBOL(dump_stack);
 
-static inline int is_kernel_stack(struct task_struct *task,
-				  struct reg_window *rw)
-{
-	unsigned long rw_addr = (unsigned long) rw;
-	unsigned long thread_base, thread_end;
-
-	if (rw_addr < PAGE_OFFSET) {
-		if (task != &init_task)
-			return 0;
-	}
-
-	thread_base = (unsigned long) task_stack_page(task);
-	thread_end = thread_base + sizeof(union thread_union);
-	if (rw_addr >= thread_base &&
-	    rw_addr < thread_end &&
-	    !(rw_addr & 0x7UL))
-		return 1;
-
-	return 0;
-}
-
 static inline struct reg_window *kernel_stack_up(struct reg_window *rw)
 {
 	unsigned long fp = rw->ins[6];
@@ -2251,6 +2230,7 @@ void die_if_kernel(char *str, struct pt_regs *regs)
 	show_regs(regs);
 	add_taint(TAINT_DIE);
 	if (regs->tstate & TSTATE_PRIV) {
+		struct thread_info *tp = current_thread_info();
 		struct reg_window *rw = (struct reg_window *)
 			(regs->u_regs[UREG_FP] + STACK_BIAS);
 
@@ -2258,8 +2238,8 @@ void die_if_kernel(char *str, struct pt_regs *regs)
 		 * find some badly aligned kernel stack.
 		 */
 		while (rw &&
-		       count++ < 30&&
-		       is_kernel_stack(current, rw)) {
+		       count++ < 30 &&
+		       kstack_valid(tp, (unsigned long) rw)) {
 			printk("Caller[%016lx]: %pS\n", rw->ins[7],
 			       (void *) rw->ins[7]);
 
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index 378ca82b9ccc..95a8e9a5125d 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -49,7 +49,7 @@ static inline enum direction decode_direction(unsigned int insn)
 }
 
 /* 16 = double-word, 8 = extra-word, 4 = word, 2 = half-word */
-static inline int decode_access_size(unsigned int insn)
+static inline int decode_access_size(struct pt_regs *regs, unsigned int insn)
 {
 	unsigned int tmp;
 
@@ -65,7 +65,7 @@ static inline int decode_access_size(unsigned int insn)
 		return 2;
 	else {
 		printk("Impossible unaligned trap. insn=%08x\n", insn);
-		die_if_kernel("Byte sized unaligned access?!?!", current_thread_info()->kregs);
+		die_if_kernel("Byte sized unaligned access?!?!", regs);
 
 		/* GCC should never warn that control reaches the end
 		 * of this function without returning a value because
@@ -289,7 +289,7 @@ static void log_unaligned(struct pt_regs *regs)
 asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 {
 	enum direction dir = decode_direction(insn);
-	int size = decode_access_size(insn);
+	int size = decode_access_size(regs, insn);
 	int orig_asi, asi;
 
 	current_thread_info()->kern_una_regs = regs;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ec9733936c96..b6cc9c9dc919 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -636,7 +636,7 @@ config GART_IOMMU
 	bool "GART IOMMU support" if EMBEDDED
 	default y
 	select SWIOTLB
-	depends on X86_64 && PCI
+	depends on X86_64 && PCI && K8_NB
 	---help---
 	  Support for full DMA access of devices with 32bit memory access only
 	  on systems with more than 3GB. This is usually needed for USB,
@@ -2036,7 +2036,7 @@ endif # X86_32
 
 config K8_NB
 	def_bool y
-	depends on AGP_AMD64 || (X86_64 && (GART_IOMMU || (PCI && NUMA)))
+	depends on CPU_SUP_AMD && PCI
 
 source "drivers/pcmcia/Kconfig"
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c2ac98f62d05..adcb4bfbaae4 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2539,6 +2539,9 @@ void irq_force_complete_move(int irq)
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg = desc->chip_data;
 
+	if (!cfg)
+		return;
+
 	__irq_complete_move(&desc, cfg->vector);
 }
 #else
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 6e44519960c8..3b5ea3831c26 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -929,7 +929,8 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
 		powernow_table[i].index = index;
 
 		/* Frequency may be rounded for these */
-		if (boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x11) {
+		if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
+				 || boot_cpu_data.x86 == 0x11) {
 			powernow_table[i].frequency =
 				freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
 		} else
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 7e1cca13af35..1366c7cfd483 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -47,6 +47,27 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 		(c->x86 == 0x6 && c->x86_model >= 0x0e))
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 
+	/*
+	 * Atom erratum AAE44/AAF40/AAG38/AAH41:
+	 *
+	 * A race condition between speculative fetches and invalidating
+	 * a large page.  This is worked around in microcode, but we
+	 * need the microcode to have already been loaded... so if it is
+	 * not, recommend a BIOS update and disable large pages.
+	 */
+	if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2) {
+		u32 ucode, junk;
+
+		wrmsr(MSR_IA32_UCODE_REV, 0, 0);
+		sync_core();
+		rdmsr(MSR_IA32_UCODE_REV, junk, ucode);
+
+		if (ucode < 0x20e) {
+			printk(KERN_WARNING "Atom PSE erratum detected, BIOS microcode update recommended\n");
+			clear_cpu_cap(c, X86_FEATURE_PSE);
+		}
+	}
+
 #ifdef CONFIG_X86_64
 	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
 #else
diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/k8.c
index cbc4332a77b2..9b895464dd03 100644
--- a/arch/x86/kernel/k8.c
+++ b/arch/x86/kernel/k8.c
@@ -121,3 +121,17 @@ void k8_flush_garts(void)
 }
 EXPORT_SYMBOL_GPL(k8_flush_garts);
 
+static __init int init_k8_nbs(void)
+{
+	int err = 0;
+
+	err = cache_k8_northbridges();
+
+	if (err < 0)
+		printk(KERN_NOTICE "K8 NB: Cannot enumerate AMD northbridges.\n");
+
+	return err;
+}
+
+/* This has to go after the PCI subsystem */
+fs_initcall(init_k8_nbs);
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 4f41b29fde98..0ae24d9b44b3 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -738,7 +738,7 @@ int __init gart_iommu_init(void)
 	unsigned long scratch;
 	long i;
 
-	if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0)
+	if (num_k8_northbridges == 0)
 		return 0;
 
 #ifndef CONFIG_AGP_AMD64
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index bb62edf74e72..259f8ce8c0fe 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -284,12 +284,12 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	set_tsk_thread_flag(p, TIF_FORK);
 
-	p->thread.fs = me->thread.fs;
-	p->thread.gs = me->thread.gs;
 	p->thread.io_bitmap_ptr = NULL;
 
 	savesegment(gs, p->thread.gsindex);
+	p->thread.gs = p->thread.gsindex ? 0 : me->thread.gs;
 	savesegment(fs, p->thread.fsindex);
+	p->thread.fs = p->thread.fsindex ? 0 : me->thread.fs;
 	savesegment(es, p->thread.es);
 	savesegment(ds, p->thread.ds);