Merge tag 'v3.2.17' into v3.2-rt

This is the 3.2.17 stable release

16 files changed, 107 insertions, 49 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0e53586543f5..202b76500f29 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1156,6 +1156,15 @@ if !MMU
 source "arch/arm/Kconfig-nommu"
 endif
 
+config ARM_ERRATA_326103
+	bool "ARM errata: FSR write bit incorrect on a SWP to read-only memory"
+	depends on CPU_V6
+	help
+	  Executing a SWP instruction to read-only memory does not set bit 11
+	  of the FSR on the ARM 1136 prior to r1p0. This causes the kernel to
+	  treat the access as a read, preventing a COW from occurring and
+	  causing the faulting task to livelock.
+
 config ARM_ERRATA_411920
 	bool "ARM errata: Invalidation of the Instruction Cache operation can fail"
 	depends on CPU_V6 || CPU_V6K
diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h
index 60843eb0f61c..73409e6c0251 100644
--- a/arch/arm/include/asm/tls.h
+++ b/arch/arm/include/asm/tls.h
@@ -7,6 +7,8 @@
 
 	.macro set_tls_v6k, tp, tmp1, tmp2
 	mcr	p15, 0, \tp, c13, c0, 3		@ set TLS register
+	mov	\tmp1, #0
+	mcr	p15, 0, \tmp1, c13, c0, 2	@ clear user r/w TLS register
 	.endm
 
 	.macro set_tls_v6, tp, tmp1, tmp2
@@ -15,6 +17,8 @@
 	mov	\tmp2, #0xffff0fff
 	tst	\tmp1, #HWCAP_TLS		@ hardware TLS available?
 	mcrne	p15, 0, \tp, c13, c0, 3		@ yes, set TLS register
+	movne	\tmp1, #0
+	mcrne	p15, 0, \tmp1, c13, c0, 2	@ clear user r/w TLS register
 	streq	\tp, [\tmp2, #-15]		@ set TLS value at 0xffff0ff0
 	.endm
 
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 3efd82cc95f0..87c8be59a25a 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -156,10 +156,10 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	}
 
 	c = irq_data_get_irq_chip(d);
-	if (c->irq_set_affinity)
-		c->irq_set_affinity(d, affinity, true);
-	else
+	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
+	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+		cpumask_copy(d->affinity, affinity);
 
 	return ret;
 }
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index ef5640b9e218..e10e59a4dc15 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -297,8 +297,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	struct mm_struct *mm = &init_mm;
 	unsigned int cpu = smp_processor_id();
 
-	printk("CPU%u: Booted secondary processor\n", cpu);
-
 	/*
 	 * All kernel threads share the same mm context; grab a
 	 * reference and switch to it.
@@ -310,6 +308,8 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	enter_lazy_tlb(mm, current);
 	local_flush_tlb_all();
 
+	printk("CPU%u: Booted secondary processor\n", cpu);
+
 	cpu_init();
 	preempt_disable();
 	trace_hardirqs_off();
diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c
index d2b177905cdb..76cbb055dd05 100644
--- a/arch/arm/kernel/sys_arm.c
+++ b/arch/arm/kernel/sys_arm.c
@@ -115,7 +115,7 @@ int kernel_execve(const char *filename,
 		  "Ir" (THREAD_START_SP - sizeof(regs)),
 		  "r" (&regs),
 		  "Ir" (sizeof(regs))
-		: "r0", "r1", "r2", "r3", "ip", "lr", "memory");
+		: "r0", "r1", "r2", "r3", "r8", "r9", "ip", "lr", "memory");
 
  out:
 	return ret;
diff --git a/arch/arm/mach-omap1/timer.c b/arch/arm/mach-omap1/timer.c
index 6e90665a7c47..fb202af01d0d 100644
--- a/arch/arm/mach-omap1/timer.c
+++ b/arch/arm/mach-omap1/timer.c
@@ -47,9 +47,9 @@ static int omap1_dm_timer_set_src(struct platform_device *pdev,
 	int n = (pdev->id - 1) << 1;
 	u32 l;
 
-	l = __raw_readl(MOD_CONF_CTRL_1) & ~(0x03 << n);
+	l = omap_readl(MOD_CONF_CTRL_1) & ~(0x03 << n);
 	l |= source << n;
-	__raw_writel(l, MOD_CONF_CTRL_1);
+	omap_writel(l, MOD_CONF_CTRL_1);
 
 	return 0;
 }
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index ff1f7cc11f87..80741992a9fc 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -26,18 +26,23 @@ ENTRY(v6_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 /*
- * Faulty SWP instruction on 1136 doesn't set bit 11 in DFSR (erratum 326103).
- * The test below covers all the write situations, including Java bytecodes
+ * Faulty SWP instruction on 1136 doesn't set bit 11 in DFSR.
  */
-	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
+#ifdef CONFIG_ARM_ERRATA_326103
+	ldr	ip, =0x4107b36
+	mrc	p15, 0, r3, c0, c0, 0		@ get processor id
+	teq	ip, r3, lsr #4			@ r0 ARM1136?
+	bne	do_DataAbort
 	tst	r5, #PSR_J_BIT			@ Java?
+	tsteq	r5, #PSR_T_BIT			@ Thumb?
 	bne	do_DataAbort
-	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
-	ldreq	r3, [r4]			@ read aborted ARM instruction
+	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
+	ldr	r3, [r4]			@ read aborted ARM instruction
 #ifdef CONFIG_CPU_ENDIAN_BE8
-	reveq	r3, r3
+	rev	r3, r3
 #endif
 	do_ldrd_abort tmp=ip, insn=r3
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
+#endif
 	b	do_DataAbort
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index b1e192ba8c24..db7bcc078006 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -32,6 +32,7 @@ static void __iomem *l2x0_base;
 static DEFINE_RAW_SPINLOCK(l2x0_lock);
 static uint32_t l2x0_way_mask;	/* Bitmask of active ways */
 static uint32_t l2x0_size;
+static unsigned long sync_reg_offset = L2X0_CACHE_SYNC;
 
 struct l2x0_regs l2x0_saved_regs;
 
@@ -61,12 +62,7 @@ static inline void cache_sync(void)
 {
 	void __iomem *base = l2x0_base;
 
-#ifdef CONFIG_PL310_ERRATA_753970
-	/* write to an unmmapped register */
-	writel_relaxed(0, base + L2X0_DUMMY_REG);
-#else
-	writel_relaxed(0, base + L2X0_CACHE_SYNC);
-#endif
+	writel_relaxed(0, base + sync_reg_offset);
 	cache_wait(base + L2X0_CACHE_SYNC, 1);
 }
 
@@ -85,10 +81,13 @@ static inline void l2x0_inv_line(unsigned long addr)
 }
 
 #if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915)
+static inline void debug_writel(unsigned long val)
+{
+	if (outer_cache.set_debug)
+		outer_cache.set_debug(val);
+}
 
-#define debug_writel(val)	outer_cache.set_debug(val)
-
-static void l2x0_set_debug(unsigned long val)
+static void pl310_set_debug(unsigned long val)
 {
 	writel_relaxed(val, l2x0_base + L2X0_DEBUG_CTRL);
 }
@@ -98,7 +97,7 @@ static inline void debug_writel(unsigned long val)
 {
 }
 
-#define l2x0_set_debug	NULL
+#define pl310_set_debug	NULL
 #endif
 
 #ifdef CONFIG_PL310_ERRATA_588369
@@ -331,6 +330,11 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 		else
 			ways = 8;
 		type = "L310";
+#ifdef CONFIG_PL310_ERRATA_753970
+		/* Unmapped register. */
+		sync_reg_offset = L2X0_DUMMY_REG;
+#endif
+		outer_cache.set_debug = pl310_set_debug;
 		break;
 	case L2X0_CACHE_ID_PART_L210:
 		ways = (aux >> 13) & 0xf;
@@ -379,7 +383,6 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 	outer_cache.flush_all = l2x0_flush_all;
 	outer_cache.inv_all = l2x0_inv_all;
 	outer_cache.disable = l2x0_disable;
-	outer_cache.set_debug = l2x0_set_debug;
 
 	printk(KERN_INFO "%s cache controller enabled\n", type);
 	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c
index 89bbf4e4d05d..e77f4e43809b 100644
--- a/arch/x86/boot/compressed/relocs.c
+++ b/arch/x86/boot/compressed/relocs.c
@@ -402,13 +402,11 @@ static void print_absolute_symbols(void)
 	for (i = 0; i < ehdr.e_shnum; i++) {
 		struct section *sec = &secs[i];
 		char *sym_strtab;
-		Elf32_Sym *sh_symtab;
 		int j;
 
 		if (sec->shdr.sh_type != SHT_SYMTAB) {
 			continue;
 		}
-		sh_symtab = sec->symtab;
 		sym_strtab = sec->link->strtab;
 		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) {
 			Elf32_Sym *sym;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2cd2d93643dc..c2beffe8fb3f 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1577,9 +1577,11 @@ static int __init apic_verify(void)
 	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
 
 	/* The BIOS may have set up the APIC at some other address */
-	rdmsr(MSR_IA32_APICBASE, l, h);
-	if (l & MSR_IA32_APICBASE_ENABLE)
-		mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
+	if (boot_cpu_data.x86 >= 6) {
+		rdmsr(MSR_IA32_APICBASE, l, h);
+		if (l & MSR_IA32_APICBASE_ENABLE)
+			mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
+	}
 
 	pr_info("Found and enabled local APIC!\n");
 	return 0;
@@ -1597,13 +1599,15 @@ int __init apic_force_enable(unsigned long addr)
 	 * MSR. This can only be done in software for Intel P6 or later
 	 * and AMD K7 (Model > 1) or later.
 	 */
-	rdmsr(MSR_IA32_APICBASE, l, h);
-	if (!(l & MSR_IA32_APICBASE_ENABLE)) {
-		pr_info("Local APIC disabled by BIOS -- reenabling.\n");
-		l &= ~MSR_IA32_APICBASE_BASE;
-		l |= MSR_IA32_APICBASE_ENABLE | addr;
-		wrmsr(MSR_IA32_APICBASE, l, h);
-		enabled_via_apicbase = 1;
+	if (boot_cpu_data.x86 >= 6) {
+		rdmsr(MSR_IA32_APICBASE, l, h);
+		if (!(l & MSR_IA32_APICBASE_ENABLE)) {
+			pr_info("Local APIC disabled by BIOS -- reenabling.\n");
+			l &= ~MSR_IA32_APICBASE_BASE;
+			l |= MSR_IA32_APICBASE_ENABLE | addr;
+			wrmsr(MSR_IA32_APICBASE, l, h);
+			enabled_via_apicbase = 1;
+		}
 	}
 	return apic_verify();
 }
@@ -2149,10 +2153,12 @@ static void lapic_resume(void)
 		 * FIXME! This will be wrong if we ever support suspend on
 		 * SMP! We'll need to do this as part of the CPU restore!
 		 */
-		rdmsr(MSR_IA32_APICBASE, l, h);
-		l &= ~MSR_IA32_APICBASE_BASE;
-		l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
-		wrmsr(MSR_IA32_APICBASE, l, h);
+		if (boot_cpu_data.x86 >= 6) {
+			rdmsr(MSR_IA32_APICBASE, l, h);
+			l &= ~MSR_IA32_APICBASE_BASE;
+			l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
+			wrmsr(MSR_IA32_APICBASE, l, h);
+		}
 	}
 
 	maxlvt = lapic_get_maxlvt();
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 9d46f5e43b51..563a09dcbcfc 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -418,10 +418,8 @@ static int mc_sysdev_add(struct sys_device *sys_dev)
 	if (err)
 		return err;
 
-	if (microcode_init_cpu(cpu) == UCODE_ERROR) {
-		sysfs_remove_group(&sys_dev->kobj, &mc_attr_group);
+	if (microcode_init_cpu(cpu) == UCODE_ERROR)
 		return -EINVAL;
-	}
 
 	return err;
 }
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 71f4727da373..5a98aa272184 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -185,10 +185,22 @@ void __init setup_per_cpu_areas(void)
 #endif
 	rc = -EINVAL;
 	if (pcpu_chosen_fc != PCPU_FC_PAGE) {
-		const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
 		const size_t dyn_size = PERCPU_MODULE_RESERVE +
 			PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
+		size_t atom_size;
 
+		/*
+		 * On 64bit, use PMD_SIZE for atom_size so that embedded
+		 * percpu areas are aligned to PMD.  This, in the future,
+		 * can also allow using PMD mappings in vmalloc area.  Use
+		 * PAGE_SIZE on 32bit as vmalloc space is highly contended
+		 * and large vmalloc area allocs can easily fail.
+		 */
+#ifdef CONFIG_X86_64
+		atom_size = PMD_SIZE;
+#else
+		atom_size = PAGE_SIZE;
+#endif
 		rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
 					    dyn_size, atom_size,
 					    pcpu_cpu_distance,
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 1f928659c338..e7c920bfbc9d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -62,6 +62,7 @@
 #include <asm/reboot.h>
 #include <asm/stackprotector.h>
 #include <asm/hypervisor.h>
+#include <asm/pci_x86.h>
 
 #include "xen-ops.h"
 #include "mmu.h"
@@ -1278,8 +1279,10 @@ asmlinkage void __init xen_start_kernel(void)
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 	}
-		
-
+#ifdef CONFIG_PCI
+	/* PCI BIOS service won't work from a PV guest. */
+	pci_probe &= ~PCI_PROBE_BIOS;
+#endif
 	xen_raw_console_write("about to get started...\n");
 
 	xen_setup_runstate_info(0);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 87f6673b1207..ec3d603b2d3b 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -353,8 +353,13 @@ static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
 	if (val & _PAGE_PRESENT) {
 		unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+		unsigned long pfn = mfn_to_pfn(mfn);
+
 		pteval_t flags = val & PTE_FLAGS_MASK;
-		val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+		if (unlikely(pfn == ~0))
+			val = flags & ~_PAGE_PRESENT;
+		else
+			val = ((pteval_t)pfn << PAGE_SHIFT) | flags;
 	}
 
 	return val;
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 041d4fe9dfe4..9a23fff68201 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -172,6 +172,7 @@ static void __init xen_fill_possible_map(void)
 static void __init xen_filter_cpu_maps(void)
 {
 	int i, rc;
+	unsigned int subtract = 0;
 
 	if (!xen_initial_domain())
 		return;
@@ -186,8 +187,22 @@ static void __init xen_filter_cpu_maps(void)
 		} else {
 			set_cpu_possible(i, false);
 			set_cpu_present(i, false);
+			subtract++;
 		}
 	}
+#ifdef CONFIG_HOTPLUG_CPU
+	/* This is akin to using 'nr_cpus' on the Linux command line.
+	 * Which is OK as when we use 'dom0_max_vcpus=X' we can only
+	 * have up to X, while nr_cpu_ids is greater than X. This
+	 * normally is not a problem, except when CPU hotplugging
+	 * is involved and then there might be more than X CPUs
+	 * in the guest - which will not work as there is no
+	 * hypercall to expand the max number of VCPUs an already
+	 * running guest has. So cap it up to X. */
+	if (subtract)
+		nr_cpu_ids = nr_cpu_ids - subtract;
+#endif
+
 }
 
 static void __init xen_smp_prepare_boot_cpu(void)
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 79d7362ad6d1..3e45aa000718 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -96,7 +96,7 @@ ENTRY(xen_restore_fl_direct)
 
 	/* check for unmasked and pending */
 	cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
-	jz 1f
+	jnz 1f
 2:	call check_events
 1:
 ENDPATCH(xen_restore_fl_direct)