Merge branch 'linux-linaro-lsk-v3.14' into linux-linaro-lsk-v3.14-rt

17 files changed, 200 insertions, 116 deletions

diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 767f0e376f4d..f60aeee2fc9e 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -458,7 +458,7 @@
 		};
 
 		wdt2: wdt@4ae14000 {
-			compatible = "ti,omap4-wdt";
+			compatible = "ti,omap3-wdt";
 			reg = <0x4ae14000 0x80>;
 			interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "wd_timer2";
diff --git a/arch/arm/boot/dts/s3c6410-mini6410.dts b/arch/arm/boot/dts/s3c6410-mini6410.dts
index 57e00f9bce99..a25debb50401 100644
--- a/arch/arm/boot/dts/s3c6410-mini6410.dts
+++ b/arch/arm/boot/dts/s3c6410-mini6410.dts
@@ -198,10 +198,6 @@
 	status = "okay";
 };
 
-&pwm {
-	status = "okay";
-};
-
 &pinctrl0 {
 	gpio_leds: gpio-leds {
 		samsung,pins = "gpk-4", "gpk-5", "gpk-6", "gpk-7";
diff --git a/arch/arm/boot/dts/s3c64xx.dtsi b/arch/arm/boot/dts/s3c64xx.dtsi
index 4e3be4d3493d..4f1eff3420f6 100644
--- a/arch/arm/boot/dts/s3c64xx.dtsi
+++ b/arch/arm/boot/dts/s3c64xx.dtsi
@@ -168,7 +168,6 @@
 			clocks = <&clocks PCLK_PWM>;
 			samsung,pwm-outputs = <0>, <1>;
 			#pwm-cells = <3>;
-			status = "disabled";
 		};
 
 		pinctrl0: pinctrl@7f008000 {
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index ee6982976d66..cf4823bc111d 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -235,6 +235,7 @@ CONFIG_SND_SOC_TEGRA_MAX98090=y
 CONFIG_USB=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_EXYNOS=y
 CONFIG_USB_EHCI_TEGRA=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_ISP1760_HCD=y
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 4a5e9430f16b..a4ef472c0d5e 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -1034,6 +1034,15 @@ static int c_show(struct seq_file *m, void *v)
 		seq_printf(m, "model name\t: %s rev %d (%s)\n",
 			   cpu_name, cpuid & 15, elf_platform);
 
+#if defined(CONFIG_SMP)
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   per_cpu(cpu_data, i).loops_per_jiffy / (500000UL/HZ),
+			   (per_cpu(cpu_data, i).loops_per_jiffy / (5000UL/HZ)) % 100);
+#else
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   loops_per_jiffy / (500000/HZ),
+			   (loops_per_jiffy / (5000/HZ)) % 100);
+#endif
 		/* dump out the processor features */
 		seq_puts(m, "Features\t: ");
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 7a41b96b4d20..686f1d1eb32e 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -388,8 +388,17 @@ asmlinkage void secondary_start_kernel(void)
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	printk(KERN_INFO "SMP: Total of %d processors activated.\n",
-	       num_online_cpus());
+	int cpu;
+	unsigned long bogosum = 0;
+
+	for_each_online_cpu(cpu)
+		bogosum += per_cpu(cpu_data, cpu).loops_per_jiffy;
+
+	printk(KERN_INFO "SMP: Total of %d processors activated "
+	       "(%lu.%02lu BogoMIPS).\n",
+	       num_online_cpus(),
+	       bogosum / (500000/HZ),
+	       (bogosum / (5000/HZ)) % 100);
 
 	hyp_mode_check();
 }
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 4e9d58148ca7..c295c10f9217 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -125,6 +125,29 @@ int __init coherency_init(void)
 {
 	struct device_node *np;
 
+	/*
+	 * The coherency fabric is needed:
+	 * - For coherency between processors on Armada XP, so only
+	 *   when SMP is enabled.
+	 * - For coherency between the processor and I/O devices, but
+	 *   this coherency requires many pre-requisites (write
+	 *   allocate cache policy, shareable pages, SMP bit set) that
+	 *   are only meant in SMP situations.
+	 *
+	 * Note that this means that on Armada 370, there is currently
+	 * no way to use hardware I/O coherency, because even when
+	 * CONFIG_SMP is enabled, is_smp() returns false due to the
+	 * Armada 370 being a single-core processor. To lift this
+	 * limitation, we would have to find a way to make the cache
+	 * policy set to write-allocate (on all Armada SoCs), and to
+	 * set the shareable attribute in page tables (on all Armada
+	 * SoCs except the Armada 370). Unfortunately, such decisions
+	 * are taken very early in the kernel boot process, at a point
+	 * where we don't know yet on which SoC we are running.
+	 */
+	if (!is_smp())
+		return 0;
+
 	np = of_find_matching_node(NULL, of_coherency_table);
 	if (np) {
 		struct resource res;
@@ -151,6 +174,9 @@ static int __init coherency_late_init(void)
 {
 	struct device_node *np;
 
+	if (!is_smp())
+		return 0;
+
 	np = of_find_matching_node(NULL, of_coherency_table);
 	if (np) {
 		bus_register_notifier(&platform_bus_type,
diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c
index eefb30cfcabd..2b9cff960af2 100644
--- a/arch/arm/mach-omap2/pm44xx.c
+++ b/arch/arm/mach-omap2/pm44xx.c
@@ -148,26 +148,6 @@ static inline int omap4_init_static_deps(void)
 	struct clockdomain *ducati_clkdm, *l3_2_clkdm;
 	int ret = 0;
 
-	if (omap_rev() == OMAP4430_REV_ES1_0) {
-		WARN(1, "Power Management not supported on OMAP4430 ES1.0\n");
-		return -ENODEV;
-	}
-
-	pr_err("Power Management for TI OMAP4.\n");
-	/*
-	 * OMAP4 chip PM currently works only with certain (newer)
-	 * versions of bootloaders. This is due to missing code in the
-	 * kernel to properly reset and initialize some devices.
-	 * http://www.spinics.net/lists/arm-kernel/msg218641.html
-	 */
-	pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n");
-
-	ret = pwrdm_for_each(pwrdms_setup, NULL);
-	if (ret) {
-		pr_err("Failed to setup powerdomains\n");
-		return ret;
-	}
-
 	/*
 	 * The dynamic dependency between MPUSS -> MEMIF and
 	 * MPUSS -> L4_PER/L3_* and DUCATI -> L3_* doesn't work as
@@ -231,6 +211,15 @@ int __init omap4_pm_init(void)
 
 	pr_info("Power Management for TI OMAP4+ devices.\n");
 
+	/*
+	 * OMAP4 chip PM currently works only with certain (newer)
+	 * versions of bootloaders. This is due to missing code in the
+	 * kernel to properly reset and initialize some devices.
+	 * http://www.spinics.net/lists/arm-kernel/msg218641.html
+	 */
+	if (cpu_is_omap44xx())
+		pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n");
+
 	ret = pwrdm_for_each(pwrdms_setup, NULL);
 	if (ret) {
 		pr_err("Failed to setup powerdomains.\n");
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
index e9c149c042e0..456d67c1f0fa 100644
--- a/arch/arm64/include/asm/suspend.h
+++ b/arch/arm64/include/asm/suspend.h
@@ -21,6 +21,7 @@ struct sleep_save_sp {
 	phys_addr_t save_ptr_stash_phys;
 };
 
+extern int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long));
 extern void cpu_resume(void);
 extern int cpu_suspend(unsigned long);
 
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index b1925729c692..ede186cdd452 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -49,28 +49,39 @@
 	orr	\dst, \dst, \mask		// dst|=(aff3>>rs3)
 	.endm
 /*
- * Save CPU state for a suspend.  This saves callee registers, and allocates
- * space on the kernel stack to save the CPU specific registers + some
- * other data for resume.
+ * Save CPU state for a suspend and execute the suspend finisher.
+ * On success it will return 0 through cpu_resume - ie through a CPU
+ * soft/hard reboot from the reset vector.
+ * On failure it returns the suspend finisher return value or force
+ * -EOPNOTSUPP if the finisher erroneously returns 0 (the suspend finisher
+ * is not allowed to return, if it does this must be considered failure).
+ * It saves callee registers, and allocates space on the kernel stack
+ * to save the CPU specific registers + some other data for resume.
  *
  *  x0 = suspend finisher argument
+ *  x1 = suspend finisher function pointer
  */
-ENTRY(__cpu_suspend)
+ENTRY(__cpu_suspend_enter)
 	stp	x29, lr, [sp, #-96]!
 	stp	x19, x20, [sp,#16]
 	stp	x21, x22, [sp,#32]
 	stp	x23, x24, [sp,#48]
 	stp	x25, x26, [sp,#64]
 	stp	x27, x28, [sp,#80]
+	/*
+	 * Stash suspend finisher and its argument in x20 and x19
+	 */
+	mov	x19, x0
+	mov	x20, x1
 	mov	x2, sp
 	sub	sp, sp, #CPU_SUSPEND_SZ	// allocate cpu_suspend_ctx
-	mov	x1, sp
+	mov	x0, sp
 	/*
-	 * x1 now points to struct cpu_suspend_ctx allocated on the stack
+	 * x0 now points to struct cpu_suspend_ctx allocated on the stack
 	 */
-	str	x2, [x1, #CPU_CTX_SP]
-	ldr	x2, =sleep_save_sp
-	ldr	x2, [x2, #SLEEP_SAVE_SP_VIRT]
+	str	x2, [x0, #CPU_CTX_SP]
+	ldr	x1, =sleep_save_sp
+	ldr	x1, [x1, #SLEEP_SAVE_SP_VIRT]
 #ifdef CONFIG_SMP
 	mrs	x7, mpidr_el1
 	ldr	x9, =mpidr_hash
@@ -82,11 +93,21 @@ ENTRY(__cpu_suspend)
 	ldp	w3, w4, [x9, #MPIDR_HASH_SHIFTS]
 	ldp	w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)]
 	compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10
-	add	x2, x2, x8, lsl #3
+	add	x1, x1, x8, lsl #3
 #endif
-	bl	__cpu_suspend_finisher
+	bl	__cpu_suspend_save
+	/*
+	 * Grab suspend finisher in x20 and its argument in x19
+	 */
+	mov	x0, x19
+	mov	x1, x20
+	/*
+	 * We are ready for power down, fire off the suspend finisher
+	 * in x1, with argument in x0
+	 */
+	blr	x1
         /*
-	 * Never gets here, unless suspend fails.
+	 * Never gets here, unless suspend finisher fails.
 	 * Successful cpu_suspend should return from cpu_resume, returning
 	 * through this code path is considered an error
 	 * If the return value is set to 0 force x0 = -EOPNOTSUPP
@@ -103,7 +124,7 @@ ENTRY(__cpu_suspend)
 	ldp	x27, x28, [sp, #80]
 	ldp	x29, lr, [sp], #96
 	ret
-ENDPROC(__cpu_suspend)
+ENDPROC(__cpu_suspend_enter)
 	.ltorg
 
 /*
@@ -126,14 +147,12 @@ cpu_resume_after_mmu:
 	ret
 ENDPROC(cpu_resume_after_mmu)
 
-	.data
 ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
 #ifdef CONFIG_SMP
 	mrs	x1, mpidr_el1
-	adr	x4, mpidr_hash_ptr
-	ldr	x5, [x4]
-	add	x8, x4, x5		// x8 = struct mpidr_hash phys address
+	adrp	x8, mpidr_hash
+	add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address
         /* retrieve mpidr_hash members to compute the hash */
 	ldr	x2, [x8, #MPIDR_HASH_MASK]
 	ldp	w3, w4, [x8, #MPIDR_HASH_SHIFTS]
@@ -143,14 +162,15 @@ ENTRY(cpu_resume)
 #else
 	mov	x7, xzr
 #endif
-	adr	x0, sleep_save_sp
+	adrp	x0, sleep_save_sp
+	add	x0, x0, #:lo12:sleep_save_sp
 	ldr	x0, [x0, #SLEEP_SAVE_SP_PHYS]
 	ldr	x0, [x0, x7, lsl #3]
 	/* load sp from context */
 	ldr	x2, [x0, #CPU_CTX_SP]
-	adr	x1, sleep_idmap_phys
+	adrp	x1, sleep_idmap_phys
 	/* load physical address of identity map page table in x1 */
-	ldr	x1, [x1]
+	ldr	x1, [x1, #:lo12:sleep_idmap_phys]
 	mov	sp, x2
 	/*
 	 * cpu_do_resume expects x0 to contain context physical address
@@ -159,26 +179,3 @@ ENTRY(cpu_resume)
 	bl	cpu_do_resume		// PC relative jump, MMU off
 	b	cpu_resume_mmu		// Resume MMU, never returns
 ENDPROC(cpu_resume)
-
-	.align 3
-mpidr_hash_ptr:
-	/*
-	 * offset of mpidr_hash symbol from current location
-	 * used to obtain run-time mpidr_hash address with MMU off
-         */
-	.quad	mpidr_hash - .
-/*
- * physical address of identity mapped page tables
- */
-	.type	sleep_idmap_phys, #object
-ENTRY(sleep_idmap_phys)
-	.quad	0
-/*
- * struct sleep_save_sp {
- *	phys_addr_t *save_ptr_stash;
- *	phys_addr_t save_ptr_stash_phys;
- * };
- */
-	.type	sleep_save_sp, #object
-ENTRY(sleep_save_sp)
-	.space	SLEEP_SAVE_SP_SZ	// struct sleep_save_sp
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 1fa9ce4afd8f..2d6b6065fe7f 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -5,26 +5,24 @@
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
+#include <asm/mmu_context.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
 
-extern int __cpu_suspend(unsigned long);
+extern int __cpu_suspend_enter(unsigned long arg, int (*fn)(unsigned long));
 /*
- * This is called by __cpu_suspend() to save the state, and do whatever
+ * This is called by __cpu_suspend_enter() to save the state, and do whatever
  * flushing is required to ensure that when the CPU goes to sleep we have
  * the necessary data available when the caches are not searched.
  *
- * @arg: Argument to pass to suspend operations
- * @ptr: CPU context virtual address
- * @save_ptr: address of the location where the context physical address
- *            must be saved
+ * ptr: CPU context virtual address
+ * save_ptr: address of the location where the context physical address
+ *           must be saved
  */
-int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr,
-			   phys_addr_t *save_ptr)
+void notrace __cpu_suspend_save(struct cpu_suspend_ctx *ptr,
+				phys_addr_t *save_ptr)
 {
-	int cpu = smp_processor_id();
-
 	*save_ptr = virt_to_phys(ptr);
 
 	cpu_do_suspend(ptr);
@@ -35,8 +33,6 @@ int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr,
 	 */
 	__flush_dcache_area(ptr, sizeof(*ptr));
 	__flush_dcache_area(save_ptr, sizeof(*save_ptr));
-
-	return cpu_ops[cpu]->cpu_suspend(arg);
 }
 
 /*
@@ -56,15 +52,15 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
 }
 
 /**
- * cpu_suspend
+ * cpu_suspend() - function to enter a low-power state
+ * @arg: argument to pass to CPU suspend operations
  *
- * @arg: argument to pass to the finisher function
+ * Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU
+ * operations back-end error code otherwise.
  */
 int cpu_suspend(unsigned long arg)
 {
-	struct mm_struct *mm = current->active_mm;
-	int ret, cpu = smp_processor_id();
-	unsigned long flags;
+	int cpu = smp_processor_id();
 
 	/*
 	 * If cpu_ops have not been registered or suspend
@@ -72,6 +68,21 @@ int cpu_suspend(unsigned long arg)
 	 */
 	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend)
 		return -EOPNOTSUPP;
+	return cpu_ops[cpu]->cpu_suspend(arg);
+}
+
+/*
+ * __cpu_suspend
+ *
+ * arg: argument to pass to the finisher function
+ * fn: finisher function pointer
+ *
+ */
+int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+{
+	struct mm_struct *mm = current->active_mm;
+	int ret;
+	unsigned long flags;
 
 	/*
 	 * From this point debug exceptions are disabled to prevent
@@ -86,16 +97,27 @@ int cpu_suspend(unsigned long arg)
 	 * page tables, so that the thread address space is properly
 	 * set-up on function return.
 	 */
-	ret = __cpu_suspend(arg);
+	ret = __cpu_suspend_enter(arg, fn);
 	if (ret == 0) {
-		cpu_switch_mm(mm->pgd, mm);
+		/*
+		 * We are resuming from reset with TTBR0_EL1 set to the
+		 * idmap to enable the MMU; restore the active_mm mappings in
+		 * TTBR0_EL1 unless the active_mm == &init_mm, in which case
+		 * the thread entered __cpu_suspend with TTBR0_EL1 set to
+		 * reserved TTBR0 page tables and should be restored as such.
+		 */
+		if (mm == &init_mm)
+			cpu_set_reserved_ttbr0();
+		else
+			cpu_switch_mm(mm->pgd, mm);
+
 		flush_tlb_all();
 
 		/*
 		 * Restore per-cpu offset before any kernel
 		 * subsystem relying on it has a chance to run.
 		 */
-		set_my_cpu_offset(per_cpu_offset(cpu));
+		set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 
 		/*
 		 * Restore HW breakpoint registers to sane values
@@ -116,10 +138,10 @@ int cpu_suspend(unsigned long arg)
 	return ret;
 }
 
-extern struct sleep_save_sp sleep_save_sp;
-extern phys_addr_t sleep_idmap_phys;
+struct sleep_save_sp sleep_save_sp;
+phys_addr_t sleep_idmap_phys;
 
-static int cpu_suspend_init(void)
+static int __init cpu_suspend_init(void)
 {
 	void *ctx_ptr;
 
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 27c93f41166f..fc0927a162ff 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -78,7 +78,7 @@ static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
 	}
 	if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
 		/* reset error bits */
 		dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB;
 	}
@@ -109,7 +109,7 @@ static long mce_handle_common_ierror(uint64_t srr1)
 		break;
 	case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
 			handled = 1;
 		}
 		break;
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 75702e207b29..f7089fcfaa5d 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -69,8 +69,12 @@ static void udbg_uart_putc(char c)
 
 static int udbg_uart_getc_poll(void)
 {
-	if (!udbg_uart_in || !(udbg_uart_in(UART_LSR) & LSR_DR))
+	if (!udbg_uart_in)
+		return -1;
+
+	if (!(udbg_uart_in(UART_LSR) & LSR_DR))
 		return udbg_uart_in(UART_RBR);
+
 	return -1;
 }
 
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 2a46ca720afc..2874be9aef0a 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -34,7 +34,7 @@ static inline unsigned int __getcpu(void)
 		native_read_tscp(&p);
 	} else {
 		/* Load per CPU data from GDT */
-		asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+		asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
 	}
 
 	return p;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 047f540cf3f7..2f9858894d5a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2886,6 +2886,17 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
 	return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
 }
 
+/*
+ * Using uncore_pmu_event_init pmu event_init callback
+ * as a detection point for uncore events.
+ */
+static int uncore_pmu_event_init(struct perf_event *event);
+
+static bool is_uncore_event(struct perf_event *event)
+{
+	return event->pmu->event_init == uncore_pmu_event_init;
+}
+
 static int
 uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
 {
@@ -2900,13 +2911,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b
 		return -EINVAL;
 
 	n = box->n_events;
-	box->event_list[n] = leader;
-	n++;
+
+	if (is_uncore_event(leader)) {
+		box->event_list[n] = leader;
+		n++;
+	}
+
 	if (!dogrp)
 		return n;
 
 	list_for_each_entry(event, &leader->sibling_list, group_entry) {
-		if (event->state <= PERF_EVENT_STATE_OFF)
+		if (!is_uncore_event(event) ||
+		    event->state <= PERF_EVENT_STATE_OFF)
 			continue;
 
 		if (n >= max_count)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 25aea1e9111f..32e5329ab0b6 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4379,7 +4379,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
 	 * zap all shadow pages.
 	 */
 	if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
-		printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n");
+		printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n");
 		kvm_mmu_invalidate_zap_all_pages(kvm);
 	}
 }
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 431e87544411..ab6ba35a9357 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -117,30 +117,45 @@ subsys_initcall(init_vdso);
 
 struct linux_binprm;
 
-/* Put the vdso above the (randomized) stack with another randomized offset.
-   This way there is no hole in the middle of address space.
-   To save memory make sure it is still in the same PTE as the stack top.
-   This doesn't give that many random bits */
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset.  This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top.  This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
 static unsigned long vdso_addr(unsigned long start, unsigned len)
 {
 	unsigned long addr, end;
 	unsigned offset;
-	end = (start + PMD_SIZE - 1) & PMD_MASK;
+
+	/*
+	 * Round up the start address.  It can start out unaligned as a result
+	 * of stack start randomization.
+	 */
+	start = PAGE_ALIGN(start);
+
+	/* Round the lowest possible end address up to a PMD boundary. */
+	end = (start + len + PMD_SIZE - 1) & PMD_MASK;
 	if (end >= TASK_SIZE_MAX)
 		end = TASK_SIZE_MAX;
 	end -= len;
-	/* This loses some more bits than a modulo, but is cheaper */
-	offset = get_random_int() & (PTRS_PER_PTE - 1);
-	addr = start + (offset << PAGE_SHIFT);
-	if (addr >= end)
-		addr = end;
+
+	if (end > start) {
+		offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+		addr = start + (offset << PAGE_SHIFT);
+	} else {
+		addr = start;
+	}
 
 	/*
-	 * page-align it here so that get_unmapped_area doesn't
-	 * align it wrongfully again to the next page. addr can come in 4K
-	 * unaligned here as a result of stack start randomization.
+	 * Forcibly align the final address in case we have a hardware
+	 * issue that requires alignment for performance reasons.
 	 */
-	addr = PAGE_ALIGN(addr);
 	addr = align_vdso_addr(addr);
 
 	return addr;