Merge branch 'for-4.11/libnvdimm' into for-4.12/dax

17 files changed, 186 insertions, 62 deletions

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 349d4d17aa7f..2aa1ad194db2 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2101,8 +2101,8 @@ static int x86_pmu_event_init(struct perf_event *event)
 
 static void refresh_pce(void *ignored)
 {
-	if (current->mm)
-		load_mm_cr4(current->mm);
+	if (current->active_mm)
+		load_mm_cr4(current->active_mm);
 }
 
 static void x86_pmu_event_mapped(struct perf_event *event)
@@ -2110,6 +2110,18 @@ static void x86_pmu_event_mapped(struct perf_event *event)
 	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
 		return;
 
+	/*
+	 * This function relies on not being called concurrently in two
+	 * tasks in the same mm.  Otherwise one task could observe
+	 * perf_rdpmc_allowed > 1 and return all the way back to
+	 * userspace with CR4.PCE clear while another task is still
+	 * doing on_each_cpu_mask() to propagate CR4.PCE.
+	 *
+	 * For now, this can't happen because all callers hold mmap_sem
+	 * for write.  If this changes, we'll need a different solution.
+	 */
+	lockdep_assert_held_exclusive(&current->mm->mmap_sem);
+
 	if (atomic_inc_return(&current->mm->context.perf_rdpmc_allowed) == 1)
 		on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
 }
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 72277b1028a5..50d35e3185f5 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -121,12 +121,9 @@ static inline void native_pmd_clear(pmd_t *pmd)
 	*(tmp + 1) = 0;
 }
 
-#if !defined(CONFIG_SMP) || (defined(CONFIG_HIGHMEM64G) && \
-		defined(CONFIG_PARAVIRT))
 static inline void native_pud_clear(pud_t *pudp)
 {
 }
-#endif
 
 static inline void pud_clear(pud_t *pudp)
 {
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1cfb36b8c024..585ee0d42d18 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -62,7 +62,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
 # define set_pud(pudp, pud)		native_set_pud(pudp, pud)
 #endif
 
-#ifndef __PAGETABLE_PMD_FOLDED
+#ifndef __PAGETABLE_PUD_FOLDED
 #define pud_clear(pud)			native_pud_clear(pud)
 #endif
 
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index 2c1ebeb4d737..529bb4a6487a 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -55,7 +55,8 @@ static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n)
  * @size:	number of bytes to write back
  *
  * Write back a cache range using the CLWB (cache line write back)
- * instruction.
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
  */
 static inline void arch_wb_cache_pmem(void *addr, size_t size)
 {
@@ -69,15 +70,6 @@ static inline void arch_wb_cache_pmem(void *addr, size_t size)
 		clwb(p);
 }
 
-/*
- * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
- * iterators, so for other types (bvec & kvec) we must do a cache write-back.
- */
-static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
-{
-	return iter_is_iovec(i) == false;
-}
-
 /**
  * arch_copy_from_iter_pmem - copy data from an iterator to PMEM
  * @addr:	PMEM destination address
@@ -94,7 +86,35 @@ static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
 	/* TODO: skip the write-back by always using non-temporal stores */
 	len = copy_from_iter_nocache(addr, bytes, i);
 
-	if (__iter_needs_pmem_wb(i))
+	/*
+	 * In the iovec case on x86_64 copy_from_iter_nocache() uses
+	 * non-temporal stores for the bulk of the transfer, but we need
+	 * to manually flush if the transfer is unaligned. A cached
+	 * memory copy is used when destination or size is not naturally
+	 * aligned. That is:
+	 *   - Require 8-byte alignment when size is 8 bytes or larger.
+	 *   - Require 4-byte alignment when size is 4 bytes.
+	 *
+	 * In the non-iovec case the entire destination needs to be
+	 * flushed.
+	 */
+	if (iter_is_iovec(i)) {
+		unsigned long flushed, dest = (unsigned long) addr;
+
+		if (bytes < 8) {
+			if (!IS_ALIGNED(dest, 4) || (bytes != 4))
+				arch_wb_cache_pmem(addr, 1);
+		} else {
+			if (!IS_ALIGNED(dest, 8)) {
+				dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+				arch_wb_cache_pmem(addr, 1);
+			}
+
+			flushed = dest - (unsigned long) addr;
+			if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
+				arch_wb_cache_pmem(addr + bytes - 1, 1);
+		}
+	} else
 		arch_wb_cache_pmem(addr, bytes);
 
 	return len;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index ae32838cac5f..b2879cc23db4 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -179,10 +179,15 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
 		return -EINVAL;
 	}
 
+	if (!enabled) {
+		++disabled_cpus;
+		return -EINVAL;
+	}
+
 	if (boot_cpu_physical_apicid != -1U)
 		ver = boot_cpu_apic_version;
 
-	cpu = __generic_processor_info(id, ver, enabled);
+	cpu = generic_processor_info(id, ver);
 	if (cpu >= 0)
 		early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid;
 
@@ -710,7 +715,7 @@ static void __init acpi_set_irq_model_ioapic(void)
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 #include <acpi/processor.h>
 
-int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 {
 #ifdef CONFIG_ACPI_NUMA
 	int nid;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index aee7deddabd0..8ccb7ef512e0 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2063,7 +2063,7 @@ static int allocate_logical_cpuid(int apicid)
 	return nr_logical_cpuids++;
 }
 
-int __generic_processor_info(int apicid, int version, bool enabled)
+int generic_processor_info(int apicid, int version)
 {
 	int cpu, max = nr_cpu_ids;
 	bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid,
@@ -2121,11 +2121,9 @@ int __generic_processor_info(int apicid, int version, bool enabled)
 	if (num_processors >= nr_cpu_ids) {
 		int thiscpu = max + disabled_cpus;
 
-		if (enabled) {
-			pr_warning("APIC: NR_CPUS/possible_cpus limit of %i "
-				   "reached. Processor %d/0x%x ignored.\n",
-				   max, thiscpu, apicid);
-		}
+		pr_warning("APIC: NR_CPUS/possible_cpus limit of %i "
+			   "reached. Processor %d/0x%x ignored.\n",
+			   max, thiscpu, apicid);
 
 		disabled_cpus++;
 		return -EINVAL;
@@ -2177,23 +2175,13 @@ int __generic_processor_info(int apicid, int version, bool enabled)
 		apic->x86_32_early_logical_apicid(cpu);
 #endif
 	set_cpu_possible(cpu, true);
-
-	if (enabled) {
-		num_processors++;
-		physid_set(apicid, phys_cpu_present_map);
-		set_cpu_present(cpu, true);
-	} else {
-		disabled_cpus++;
-	}
+	physid_set(apicid, phys_cpu_present_map);
+	set_cpu_present(cpu, true);
+	num_processors++;
 
 	return cpu;
 }
 
-int generic_processor_info(int apicid, int version)
-{
-	return __generic_processor_info(apicid, version, true);
-}
-
 int hard_smp_processor_id(void)
 {
 	return read_apic_id();
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index c05509d38b1f..9ac2a5cdd9c2 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -727,7 +727,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
 	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
 	    (rdtgrp->flags & RDT_DELETED)) {
 		kernfs_unbreak_active_protection(kn);
-		kernfs_put(kn);
+		kernfs_put(rdtgrp->kn);
 		kfree(rdtgrp);
 	} else {
 		kernfs_unbreak_active_protection(kn);
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 54a2372f5dbb..b5785c197e53 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -4,6 +4,7 @@
  *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
  */
 
+#define DISABLE_BRANCH_PROFILING
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/types.h>
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index f088ea4c66e7..a723ae9440ab 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -166,11 +166,9 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
 	spin_lock_irqsave(&desc->lock, flags);
 
 	/*
-	 * most handlers of type NMI_UNKNOWN never return because
-	 * they just assume the NMI is theirs.  Just a sanity check
-	 * to manage expectations
+	 * Indicate if there are multiple registrations on the
+	 * internal NMI handler call chains (SERR and IO_CHECK).
 	 */
-	WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head));
 	WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head));
 	WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head));
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 4f7a9833d8e5..c73a7f9e881a 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1333,6 +1333,8 @@ static int __init init_tsc_clocksource(void)
 	 * the refined calibration and directly register it as a clocksource.
 	 */
 	if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) {
+		if (boot_cpu_has(X86_FEATURE_ART))
+			art_related_clocksource = &clocksource_tsc;
 		clocksource_register_khz(&clocksource_tsc, tsc_khz);
 		return 0;
 	}
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 478d15dbaee4..08339262b666 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -82,19 +82,43 @@ static size_t regs_size(struct pt_regs *regs)
 	return sizeof(*regs);
 }
 
+#ifdef CONFIG_X86_32
+#define GCC_REALIGN_WORDS 3
+#else
+#define GCC_REALIGN_WORDS 1
+#endif
+
 static bool is_last_task_frame(struct unwind_state *state)
 {
-	unsigned long bp = (unsigned long)state->bp;
-	unsigned long regs = (unsigned long)task_pt_regs(state->task);
+	unsigned long *last_bp = (unsigned long *)task_pt_regs(state->task) - 2;
+	unsigned long *aligned_bp = last_bp - GCC_REALIGN_WORDS;
 
 	/*
 	 * We have to check for the last task frame at two different locations
 	 * because gcc can occasionally decide to realign the stack pointer and
-	 * change the offset of the stack frame by a word in the prologue of a
-	 * function called by head/entry code.
+	 * change the offset of the stack frame in the prologue of a function
+	 * called by head/entry code.  Examples:
+	 *
+	 * <start_secondary>:
+	 *      push   %edi
+	 *      lea    0x8(%esp),%edi
+	 *      and    $0xfffffff8,%esp
+	 *      pushl  -0x4(%edi)
+	 *      push   %ebp
+	 *      mov    %esp,%ebp
+	 *
+	 * <x86_64_start_kernel>:
+	 *      lea    0x8(%rsp),%r10
+	 *      and    $0xfffffffffffffff0,%rsp
+	 *      pushq  -0x8(%r10)
+	 *      push   %rbp
+	 *      mov    %rsp,%rbp
+	 *
+	 * Note that after aligning the stack, it pushes a duplicate copy of
+	 * the return address before pushing the frame pointer.
 	 */
-	return bp == regs - FRAME_HEADER_SIZE ||
-	       bp == regs - FRAME_HEADER_SIZE - sizeof(long);
+	return (state->bp == last_bp ||
+		(state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1)));
 }
 
 /*
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 8d63d7a104c3..4c90cfdc128b 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define DISABLE_BRANCH_PROFILING
 #define pr_fmt(fmt) "kasan: " fmt
 #include <linux/bootmem.h>
 #include <linux/kasan.h>
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 5126dfd52b18..cd44ae727df7 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -590,7 +590,7 @@ static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
  * we might run off the end of the bounds table if we are on
  * a 64-bit kernel and try to get 8 bytes.
  */
-int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
+static int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
 		long __user *bd_entry_ptr)
 {
 	u32 bd_entry_32;
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index a7dbec4dce27..3dbde04febdc 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -26,5 +26,6 @@ obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o
 obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o
 # MISC Devices
 obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
+obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_mrfld_power_btn.o
 obj-$(subst m,y,$(CONFIG_RTC_DRV_CMOS)) += platform_mrfld_rtc.o
 obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c
new file mode 100644
index 000000000000..a6c3705a28ad
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c
@@ -0,0 +1,82 @@
+/*
+ * Intel Merrifield power button support
+ *
+ * (C) Copyright 2017 Intel Corporation
+ *
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/platform_device.h>
+#include <linux/sfi.h>
+
+#include <asm/intel-mid.h>
+#include <asm/intel_scu_ipc.h>
+
+static struct resource mrfld_power_btn_resources[] = {
+	{
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mrfld_power_btn_dev = {
+	.name		= "msic_power_btn",
+	.id		= PLATFORM_DEVID_NONE,
+	.num_resources	= ARRAY_SIZE(mrfld_power_btn_resources),
+	.resource	= mrfld_power_btn_resources,
+};
+
+static int mrfld_power_btn_scu_status_change(struct notifier_block *nb,
+					     unsigned long code, void *data)
+{
+	if (code == SCU_DOWN) {
+		platform_device_unregister(&mrfld_power_btn_dev);
+		return 0;
+	}
+
+	return platform_device_register(&mrfld_power_btn_dev);
+}
+
+static struct notifier_block mrfld_power_btn_scu_notifier = {
+	.notifier_call	= mrfld_power_btn_scu_status_change,
+};
+
+static int __init register_mrfld_power_btn(void)
+{
+	if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+		return -ENODEV;
+
+	/*
+	 * We need to be sure that the SCU IPC is ready before
+	 * PMIC power button device can be registered:
+	 */
+	intel_scu_notifier_add(&mrfld_power_btn_scu_notifier);
+
+	return 0;
+}
+arch_initcall(register_mrfld_power_btn);
+
+static void __init *mrfld_power_btn_platform_data(void *info)
+{
+	struct resource *res = mrfld_power_btn_resources;
+	struct sfi_device_table_entry *pentry = info;
+
+	res->start = res->end = pentry->irq;
+	return NULL;
+}
+
+static const struct devs_id mrfld_power_btn_dev_id __initconst = {
+	.name			= "bcove_power_btn",
+	.type			= SFI_DEV_TYPE_IPC,
+	.delay			= 1,
+	.msic			= 1,
+	.get_platform_data	= &mrfld_power_btn_platform_data,
+};
+
+sfi_device(mrfld_power_btn_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
index 86edd1e941eb..9e304e2ea4f5 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
@@ -19,7 +19,7 @@
 #include <asm/intel_scu_ipc.h>
 #include <asm/io_apic.h>
 
-#define TANGIER_EXT_TIMER0_MSI 15
+#define TANGIER_EXT_TIMER0_MSI 12
 
 static struct platform_device wdt_dev = {
 	.name = "intel_mid_wdt",
diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c
index e793fe509971..e42978d4deaf 100644
--- a/arch/x86/platform/intel-mid/mfld.c
+++ b/arch/x86/platform/intel-mid/mfld.c
@@ -17,16 +17,6 @@
 
 #include "intel_mid_weak_decls.h"
 
-static void penwell_arch_setup(void);
-/* penwell arch ops */
-static struct intel_mid_ops penwell_ops = {
-	.arch_setup = penwell_arch_setup,
-};
-
-static void mfld_power_off(void)
-{
-}
-
 static unsigned long __init mfld_calibrate_tsc(void)
 {
 	unsigned long fast_calibrate;
@@ -63,9 +53,12 @@ static unsigned long __init mfld_calibrate_tsc(void)
 static void __init penwell_arch_setup(void)
 {
 	x86_platform.calibrate_tsc = mfld_calibrate_tsc;
-	pm_power_off = mfld_power_off;
 }
 
+static struct intel_mid_ops penwell_ops = {
+	.arch_setup = penwell_arch_setup,
+};
+
 void *get_penwell_ops(void)
 {
 	return &penwell_ops;