Merge tag 'v4.9.209'

This is the 4.9.209 stable release

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 208
+SUBLEVEL = 209
 EXTRAVERSION =
 NAME = Roaring Lionus
 

arch/arm/boot/dts/am437x-gp-evm.dts

@@ -79,7 +79,7 @@
 		};
 
 	lcd0: display {
-		compatible = "osddisplays,osd057T0559-34ts", "panel-dpi";
+		compatible = "osddisplays,osd070t1718-19ts", "panel-dpi";
 		label = "lcd";
 
 		panel-timing {

arch/arm/boot/dts/am43x-epos-evm.dts

@@ -41,7 +41,7 @@
 	};
 
 	lcd0: display {
-		compatible = "osddisplays,osd057T0559-34ts", "panel-dpi";
+		compatible = "osddisplays,osd070t1718-19ts", "panel-dpi";
 		label = "lcd";
 
 		panel-timing {

arch/arm/mach-vexpress/spc.c

@@ -555,8 +555,9 @@ static struct clk *ve_spc_clk_register(struct device *cpu_dev)
 
 static int __init ve_spc_clk_init(void)
 {
-	int cpu;
+	int cpu, cluster;
 	struct clk *clk;
+	bool init_opp_table[MAX_CLUSTERS] = { false };
 
 	if (!info)
 		return 0; /* Continue only if SPC is initialised */
@@ -582,8 +583,17 @@ static int __init ve_spc_clk_init(void)
 			continue;
 		}
 
+		cluster = topology_physical_package_id(cpu_dev->id);
+		if (init_opp_table[cluster])
+			continue;
+
 		if (ve_init_opp_table(cpu_dev))
 			pr_warn("failed to initialise cpu%d opp table\n", cpu);
+		else if (dev_pm_opp_set_sharing_cpus(cpu_dev,
+			 topology_core_cpumask(cpu_dev->id)))
+			pr_warn("failed to mark OPPs shared for cpu%d\n", cpu);
+		else
+			init_opp_table[cluster] = true;
 	}
 
 	platform_device_register_simple("vexpress-spc-cpufreq", -1, NULL, 0);

arch/arm64/include/asm/pgtable-prot.h

@@ -77,13 +77,12 @@
 #define PAGE_COPY_EXEC		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
 #define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
-#define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_NG | PTE_PXN)
 
 #define __P000  PAGE_NONE
 #define __P001  PAGE_READONLY
 #define __P010  PAGE_COPY
 #define __P011  PAGE_COPY
-#define __P100  PAGE_EXECONLY
+#define __P100  PAGE_READONLY_EXEC
 #define __P101  PAGE_READONLY_EXEC
 #define __P110  PAGE_COPY_EXEC
 #define __P111  PAGE_COPY_EXEC
@@ -92,7 +91,7 @@
 #define __S001  PAGE_READONLY
 #define __S010  PAGE_SHARED
 #define __S011  PAGE_SHARED
-#define __S100  PAGE_EXECONLY
+#define __S100  PAGE_READONLY_EXEC
 #define __S101  PAGE_READONLY_EXEC
 #define __S110  PAGE_SHARED_EXEC
 #define __S111  PAGE_SHARED_EXEC

arch/arm64/include/asm/pgtable.h

@@ -84,12 +84,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
 #define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
-/*
- * Execute-only user mappings do not have the PTE_USER bit set. All valid
- * kernel mappings have the PTE_UXN bit set.
- */
 #define pte_valid_not_user(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN))
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 #define pte_valid_young(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
 #define pte_valid_user(pte) \
@@ -105,8 +101,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
 /*
  * p??_access_permitted() is true for valid user mappings (subject to the
- * write permission check) other than user execute-only which do not have the
- * PTE_USER bit set. PROT_NONE mappings do not have the PTE_VALID bit set.
+ * write permission check). PROT_NONE mappings do not have the PTE_VALID bit
+ * set.
  */
 #define pte_access_permitted(pte, write) \
 	(pte_valid_user(pte) && (!(write) || pte_write(pte)))

arch/arm64/mm/fault.c

@@ -327,7 +327,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	int fault, sig, code;
-	unsigned long vm_flags = VM_READ | VM_WRITE;
+	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 	struct vm_area_struct *vma = NULL;
 

arch/mips/include/asm/thread_info.h

@@ -52,8 +52,26 @@ struct thread_info {
 #define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)
 
-/* How to get the thread information struct from C.  */
+/*
+ * A pointer to the struct thread_info for the currently executing thread is
+ * held in register $28/$gp.
+ *
+ * We declare __current_thread_info as a global register variable rather than a
+ * local register variable within current_thread_info() because clang doesn't
+ * support explicit local register variables.
+ *
+ * When building the VDSO we take care not to declare the global register
+ * variable because this causes GCC to not preserve the value of $28/$gp in
+ * functions that change its value (which is common in the PIC VDSO when
+ * accessing the GOT). Since the VDSO shouldn't be accessing
+ * __current_thread_info anyway we declare it extern in order to cause a link
+ * failure if it's referenced.
+ */
+#ifdef __VDSO__
+extern struct thread_info *__current_thread_info;
+#else
 register struct thread_info *__current_thread_info __asm__("$28");
+#endif
 
 static inline struct thread_info *current_thread_info(void)
 {

arch/parisc/include/asm/cmpxchg.h

@@ -43,8 +43,14 @@ __xchg(unsigned long x, __volatile__ void *ptr, int size)
 **		if (((unsigned long)p & 0xf) == 0)
 **			return __ldcw(p);
 */
-#define xchg(ptr, x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
+#define xchg(ptr, x)							\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	__ret = (__typeof__(*(ptr)))					\
+		__xchg((unsigned long)_x_, (ptr), sizeof(*(ptr)));	\
+	__ret;								\
+})
 
 /* bug catcher for when unsupported size is used - won't link */
 extern void __cmpxchg_called_with_bad_pointer(void);

arch/powerpc/mm/mem.c

@@ -345,6 +345,14 @@ void __init mem_init(void)
 	BUILD_BUG_ON(MMU_PAGE_COUNT > 16);
 
 #ifdef CONFIG_SWIOTLB
+	/*
+	 * Some platforms (e.g. 85xx) limit DMA-able memory way below
+	 * 4G. We force memblock to bottom-up mode to ensure that the
+	 * memory allocated in swiotlb_init() is DMA-able.
+	 * As it's the last memblock allocation, no need to reset it
+	 * back to to-down.
+	 */
+	memblock_set_bottom_up(true);
 	swiotlb_init(0);
 #endif
 

arch/powerpc/platforms/pseries/hvconsole.c

@@ -62,7 +62,7 @@ EXPORT_SYMBOL(hvc_get_chars);
  * @vtermno: The vtermno or unit_address of the adapter from which the data
  *	originated.
  * @buf: The character buffer that contains the character data to send to
- *	firmware.
+ *	firmware. Must be at least 16 bytes, even if count is less than 16.
  * @count: Send this number of characters.
  */
 int hvc_put_chars(uint32_t vtermno, const char *buf, int count)

arch/s390/kernel/perf_cpum_sf.c

@@ -1295,18 +1295,28 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 		 */
 		if (flush_all && done)
 			break;
-
-		/* If an event overflow happened, discard samples by
-		 * processing any remaining sample-data-blocks.
-		 */
-		if (event_overflow)
-			flush_all = 1;
 	}
 
 	/* Account sample overflows in the event hardware structure */
 	if (sampl_overflow)
 		OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) +
 						 sampl_overflow, 1 + num_sdb);
+
+	/* Perf_event_overflow() and perf_event_account_interrupt() limit
+	 * the interrupt rate to an upper limit. Roughly 1000 samples per
+	 * task tick.
+	 * Hitting this limit results in a large number
+	 * of throttled REF_REPORT_THROTTLE entries and the samples
+	 * are dropped.
+	 * Slightly increase the interval to avoid hitting this limit.
+	 */
+	if (event_overflow) {
+		SAMPL_RATE(hwc) += DIV_ROUND_UP(SAMPL_RATE(hwc), 10);
+		debug_sprintf_event(sfdbg, 1, "%s: rate adjustment %ld\n",
+				    __func__,
+				    DIV_ROUND_UP(SAMPL_RATE(hwc), 10));
+	}
+
 	if (sampl_overflow || event_overflow)
 		debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: "
 				    "overflow stats: sample=%llu event=%llu\n",

arch/s390/kernel/smp.c

@@ -691,39 +691,67 @@ static struct sclp_core_info *smp_get_core_info(void)
 
 static int smp_add_present_cpu(int cpu);
 
-static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add)
+static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail,
+			bool configured, bool early)
 {
 	struct pcpu *pcpu;
-	cpumask_t avail;
-	int cpu, nr, i, j;
+	int cpu, nr, i;
 	u16 address;
 
 	nr = 0;
-	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
-	cpu = cpumask_first(&avail);
-	for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) {
-		if (sclp.has_core_type && info->core[i].type != boot_core_type)
+	if (sclp.has_core_type && core->type != boot_core_type)
+		return nr;
+	cpu = cpumask_first(avail);
+	address = core->core_id << smp_cpu_mt_shift;
+	for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) {
+		if (pcpu_find_address(cpu_present_mask, address + i))
 			continue;
-		address = info->core[i].core_id << smp_cpu_mt_shift;
-		for (j = 0; j <= smp_cpu_mtid; j++) {
-			if (pcpu_find_address(cpu_present_mask, address + j))
-				continue;
-			pcpu = pcpu_devices + cpu;
-			pcpu->address = address + j;
-			pcpu->state =
-				(cpu >= info->configured*(smp_cpu_mtid + 1)) ?
-				CPU_STATE_STANDBY : CPU_STATE_CONFIGURED;
-			smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
-			set_cpu_present(cpu, true);
-			if (sysfs_add && smp_add_present_cpu(cpu) != 0)
-				set_cpu_present(cpu, false);
-			else
-				nr++;
-			cpu = cpumask_next(cpu, &avail);
-			if (cpu >= nr_cpu_ids)
+		pcpu = pcpu_devices + cpu;
+		pcpu->address = address + i;
+		if (configured)
+			pcpu->state = CPU_STATE_CONFIGURED;
+		else
+			pcpu->state = CPU_STATE_STANDBY;
+		smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+		set_cpu_present(cpu, true);
+		if (!early && smp_add_present_cpu(cpu) != 0)
+			set_cpu_present(cpu, false);
+		else
+			nr++;
+		cpumask_clear_cpu(cpu, avail);
+		cpu = cpumask_next(cpu, avail);
+	}
+	return nr;
+}
+
+static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
+{
+	struct sclp_core_entry *core;
+	cpumask_t avail;
+	bool configured;
+	u16 core_id;
+	int nr, i;
+
+	nr = 0;
+	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
+	/*
+	 * Add IPL core first (which got logical CPU number 0) to make sure
+	 * that all SMT threads get subsequent logical CPU numbers.
+	 */
+	if (early) {
+		core_id = pcpu_devices[0].address >> smp_cpu_mt_shift;
+		for (i = 0; i < info->configured; i++) {
+			core = &info->core[i];
+			if (core->core_id == core_id) {
+				nr += smp_add_core(core, &avail, true, early);
 				break;
+			}
 		}
 	}
+	for (i = 0; i < info->combined; i++) {
+		configured = i < info->configured;
+		nr += smp_add_core(&info->core[i], &avail, configured, early);
+	}
 	return nr;
 }
 
@@ -771,7 +799,7 @@ static void __init smp_detect_cpus(void)
 
 	/* Add CPUs present at boot */
 	get_online_cpus();
-	__smp_rescan_cpus(info, 0);
+	__smp_rescan_cpus(info, true);
 	put_online_cpus();
 	kfree(info);
 }
@@ -1127,7 +1155,7 @@ int __ref smp_rescan_cpus(void)
 		return -ENOMEM;
 	get_online_cpus();
 	mutex_lock(&smp_cpu_state_mutex);
-	nr = __smp_rescan_cpus(info, 1);
+	nr = __smp_rescan_cpus(info, false);
 	mutex_unlock(&smp_cpu_state_mutex);
 	put_online_cpus();
 	kfree(info);

arch/tile/lib/atomic_asm_32.S

@@ -24,8 +24,7 @@
  * has an opportunity to return -EFAULT to the user if needed.
  * The 64-bit routines just return a "long long" with the value,
  * since they are only used from kernel space and don't expect to fault.
- * Support for 16-bit ops is included in the framework but we don't provide
- * any (x86_64 has an atomic_inc_short(), so we might want to some day).
+ * Support for 16-bit ops is included in the framework but we don't provide any.
  *
  * Note that the caller is advised to issue a suitable L1 or L2
  * prefetch on the address being manipulated to avoid extra stalls.

arch/x86/events/core.c

@@ -374,7 +374,7 @@ int x86_add_exclusive(unsigned int what)
 	 * LBR and BTS are still mutually exclusive.
 	 */
 	if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt)
-		return 0;
+		goto out;
 
 	if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) {
 		mutex_lock(&pmc_reserve_mutex);
@@ -386,6 +386,7 @@ int x86_add_exclusive(unsigned int what)
 		mutex_unlock(&pmc_reserve_mutex);
 	}
 
+out:
 	atomic_inc(&active_events);
 	return 0;
 
@@ -396,11 +397,15 @@ int x86_add_exclusive(unsigned int what)
 
 void x86_del_exclusive(unsigned int what)
 {
+	atomic_dec(&active_events);
+
+	/*
+	 * See the comment in x86_add_exclusive().
+	 */
 	if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt)
 		return;
 
 	atomic_dec(&x86_pmu.lbr_exclusive[what]);
-	atomic_dec(&active_events);
 }
 
 int x86_setup_perfctr(struct perf_event *event)

arch/x86/include/asm/atomic.h

@@ -249,19 +249,6 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
-/**
- * atomic_inc_short - increment of a short integer
- * @v: pointer to type int
- *
- * Atomically adds 1 to @v
- * Returns the new value of @u
- */
-static __always_inline short int atomic_inc_short(short int *v)
-{
-	asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
-	return *v;
-}
-
 #ifdef CONFIG_X86_32
 # include <asm/atomic64_32.h>
 #else

block/blk-map.c

@@ -142,7 +142,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	return 0;
 
 unmap_rq:
-	__blk_rq_unmap_user(bio);
+	blk_rq_unmap_user(bio);
 fail:
 	rq->bio = NULL;
 	return ret;