Merge branch 'perf/urgent' into perf/core, to pick up fixes before applying new changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/gpio/board.txt

@@ -21,8 +21,8 @@ exact way to do it depends on the GPIO controller providing the GPIOs, see the
 device tree bindings for your controller.
 
 GPIOs mappings are defined in the consumer device's node, in a property named
-<function>-gpios, where <function> is the function the driver will request
-through gpiod_get(). For example:
+either <function>-gpios or <function>-gpio, where <function> is the function
+the driver will request through gpiod_get(). For example:
 
 	foo_device {
 		compatible = "acme,foo";
@@ -31,7 +31,7 @@ through gpiod_get(). For example:
 			    <&gpio 16 GPIO_ACTIVE_HIGH>, /* green */
 			    <&gpio 17 GPIO_ACTIVE_HIGH>; /* blue */
 
-		power-gpios = <&gpio 1 GPIO_ACTIVE_LOW>;
+		power-gpio = <&gpio 1 GPIO_ACTIVE_LOW>;
 	};
 
 This property will make GPIOs 15, 16 and 17 available to the driver under the
@@ -39,15 +39,24 @@ This property will make GPIOs 15, 16 and 17 available to the driver under the
 
 	struct gpio_desc *red, *green, *blue, *power;
 
-	red = gpiod_get_index(dev, "led", 0);
-	green = gpiod_get_index(dev, "led", 1);
-	blue = gpiod_get_index(dev, "led", 2);
+	red = gpiod_get_index(dev, "led", 0, GPIOD_OUT_HIGH);
+	green = gpiod_get_index(dev, "led", 1, GPIOD_OUT_HIGH);
+	blue = gpiod_get_index(dev, "led", 2, GPIOD_OUT_HIGH);
 
-	power = gpiod_get(dev, "power");
+	power = gpiod_get(dev, "power", GPIOD_OUT_HIGH);
 
 The led GPIOs will be active-high, while the power GPIO will be active-low (i.e.
 gpiod_is_active_low(power) will be true).
 
+The second parameter of the gpiod_get() functions, the con_id string, has to be
+the <function>-prefix of the GPIO suffixes ("gpios" or "gpio", automatically
+looked up by the gpiod functions internally) used in the device tree. With above
+"led-gpios" example, use the prefix without the "-" as con_id parameter: "led".
+
+Internally, the GPIO subsystem prefixes the GPIO suffix ("gpios" or "gpio")
+with the string passed in con_id to get the resulting string
+(snprintf(... "%s-%s", con_id, gpio_suffixes[]).
+
 ACPI
 ----
 ACPI also supports function names for GPIOs in a similar fashion to DT.
@@ -142,13 +151,14 @@ The driver controlling "foo.0" will then be able to obtain its GPIOs as follows:
 
 	struct gpio_desc *red, *green, *blue, *power;
 
-	red = gpiod_get_index(dev, "led", 0);
-	green = gpiod_get_index(dev, "led", 1);
-	blue = gpiod_get_index(dev, "led", 2);
+	red = gpiod_get_index(dev, "led", 0, GPIOD_OUT_HIGH);
+	green = gpiod_get_index(dev, "led", 1, GPIOD_OUT_HIGH);
+	blue = gpiod_get_index(dev, "led", 2, GPIOD_OUT_HIGH);
 
-	power = gpiod_get(dev, "power");
-	gpiod_direction_output(power, 1);
+	power = gpiod_get(dev, "power", GPIOD_OUT_HIGH);
 
-Since the "power" GPIO is mapped as active-low, its actual signal will be 0
-after this code. Contrary to the legacy integer GPIO interface, the active-low
-property is handled during mapping and is thus transparent to GPIO consumers.
+Since the "led" GPIOs are mapped as active-high, this example will switch their
+signals to 1, i.e. enabling the LEDs. And for the "power" GPIO, which is mapped
+as active-low, its actual signal will be 0 after this code. Contrary to the legacy
+integer GPIO interface, the active-low property is handled during mapping and is
+thus transparent to GPIO consumers.

Documentation/gpio/consumer.txt

@@ -39,6 +39,9 @@ device that displays digits), an additional index argument can be specified:
 					  const char *con_id, unsigned int idx,
 					  enum gpiod_flags flags)
 
+For a more detailed description of the con_id parameter in the DeviceTree case
+see Documentation/gpio/board.txt
+
 The flags parameter is used to optionally specify a direction and initial value
 for the GPIO. Values can be:
 

Documentation/hwmon/nct6775

@@ -32,6 +32,10 @@ Supported chips:
     Prefix: 'nct6792'
     Addresses scanned: ISA address retrieved from Super I/O registers
     Datasheet: Available from Nuvoton upon request
+  * Nuvoton NCT6793D
+    Prefix: 'nct6793'
+    Addresses scanned: ISA address retrieved from Super I/O registers
+    Datasheet: Available from Nuvoton upon request
 
 Authors:
         Guenter Roeck <linux@roeck-us.net>

Documentation/static-keys.txt

@@ -15,8 +15,8 @@ The updated API replacements are:
 
 DEFINE_STATIC_KEY_TRUE(key);
 DEFINE_STATIC_KEY_FALSE(key);
-static_key_likely()
-statick_key_unlikely()
+static_branch_likely()
+static_branch_unlikely()
 
 0) Abstract
 

MAINTAINERS

@@ -6452,11 +6452,11 @@ F:	drivers/hwmon/ltc4261.c
 LTP (Linux Test Project)
 M:	Mike Frysinger <vapier@gentoo.org>
 M:	Cyril Hrubis <chrubis@suse.cz>
-M:	Wanlong Gao <gaowanlong@cn.fujitsu.com>
+M:	Wanlong Gao <wanlong.gao@gmail.com>
 M:	Jan Stancek <jstancek@redhat.com>
 M:	Stanislav Kholmanskikh <stanislav.kholmanskikh@oracle.com>
 M:	Alexey Kodanev <alexey.kodanev@oracle.com>
-L:	ltp-list@lists.sourceforge.net (subscribers-only)
+L:	ltp@lists.linux.it (subscribers-only)
 W:	http://linux-test-project.github.io/
 T:	git git://github.com/linux-test-project/ltp.git
 S:	Maintained

arch/alpha/include/asm/io.h

@@ -297,7 +297,9 @@ static inline void __iomem * ioremap_nocache(unsigned long offset,
 					     unsigned long size)
 {
 	return ioremap(offset, size);
-} 
+}
+
+#define ioremap_uc ioremap_nocache
 
 static inline void iounmap(volatile void __iomem *addr)
 {

arch/alpha/lib/udelay.c

@@ -30,6 +30,7 @@ __delay(int loops)
 		"	bgt %0,1b"
 		: "=&r" (tmp), "=r" (loops) : "1"(loops));
 }
+EXPORT_SYMBOL(__delay);
 
 #ifdef CONFIG_SMP
 #define LPJ	 cpu_data[smp_processor_id()].loops_per_jiffy

arch/arm/Makefile

@@ -54,6 +54,14 @@ AS		+= -EL
 LD		+= -EL
 endif
 
+#
+# The Scalar Replacement of Aggregates (SRA) optimization pass in GCC 4.9 and
+# later may result in code being generated that handles signed short and signed
+# char struct members incorrectly. So disable it.
+# (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65932)
+#
+KBUILD_CFLAGS	+= $(call cc-option,-fno-ipa-sra)
+
 # This selects which instruction set is used.
 # Note that GCC does not numerically define an architecture version
 # macro, but instead defines a whole series of macros which makes

arch/arm/include/asm/assembler.h

@@ -491,11 +491,6 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
-	.macro	uaccess_save_and_disable, tmp
-	uaccess_save \tmp
-	uaccess_disable \tmp
-	.endm
-
 	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
 	.macro	ret\c, reg
 #if __LINUX_ARM_ARCH__ < 6

arch/arm/include/asm/bug.h

@@ -40,6 +40,7 @@ do {								\
 		"2:\t.asciz " #__file "\n" 			\
 		".popsection\n" 				\
 		".pushsection __bug_table,\"a\"\n"		\
+		".align 2\n"					\
 		"3:\t.word 1b, 2b\n"				\
 		"\t.hword " #__line ", 0\n"			\
 		".popsection");					\

arch/arm/include/asm/domain.h

@@ -12,6 +12,7 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/barrier.h>
+#include <asm/thread_info.h>
 #endif
 
 /*
@@ -89,7 +90,8 @@ static inline unsigned int get_domain(void)
 
 	asm(
 	"mrc	p15, 0, %0, c3, c0	@ get domain"
-	 : "=r" (domain));
+	 : "=r" (domain)
+	 : "m" (current_thread_info()->cpu_domain));
 
 	return domain;
 }
@@ -98,7 +100,7 @@ static inline void set_domain(unsigned val)
 {
 	asm volatile(
 	"mcr	p15, 0, %0, c3, c0	@ set domain"
-	  : : "r" (val));
+	  : : "r" (val) : "memory");
 	isb();
 }
 

arch/arm/include/asm/thread_info.h

@@ -25,7 +25,6 @@
 struct task_struct;
 
 #include <asm/types.h>
-#include <asm/domain.h>
 
 typedef unsigned long mm_segment_t;
 

arch/arm/kernel/process.c

@@ -226,6 +226,7 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
 
+#ifdef CONFIG_CPU_USE_DOMAINS
 	/*
 	 * Copy the initial value of the domain access control register
 	 * from the current thread: thread->addr_limit will have been
@@ -233,6 +234,7 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	 * kernel/fork.c
 	 */
 	thread->cpu_domain = get_domain();
+#endif
 
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();

arch/arm/nwfpe/entry.S

@@ -95,9 +95,10 @@ emulate:
 	reteq	r4			@ no, return failure
 
 next:
+	uaccess_enable r3
 .Lx1:	ldrt	r6, [r5], #4		@ get the next instruction and
 					@ increment PC
-
+	uaccess_disable r3
 	and	r2, r6, #0x0F000000	@ test for FP insns
 	teq	r2, #0x0C000000
 	teqne	r2, #0x0D000000

arch/arm/xen/hypercall.S

@@ -98,8 +98,23 @@ ENTRY(privcmd_call)
 	mov r1, r2
 	mov r2, r3
 	ldr r3, [sp, #8]
+	/*
+	 * Privcmd calls are issued by the userspace. We need to allow the
+	 * kernel to access the userspace memory before issuing the hypercall.
+	 */
+	uaccess_enable r4
+
+	/* r4 is loaded now as we use it as scratch register before */
 	ldr r4, [sp, #4]
 	__HVC(XEN_IMM)
+
+	/*
+	 * Disable userspace access from kernel. This is fine to do it
+	 * unconditionally as no set_fs(KERNEL_DS)/set_fs(get_ds()) is
+	 * called before.
+	 */
+	uaccess_disable r4
+
 	ldm sp!, {r4}
 	ret lr
 ENDPROC(privcmd_call);

arch/arm64/Kconfig

@@ -32,6 +32,7 @@ config ARM64
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
+	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
@@ -331,6 +332,22 @@ config ARM64_ERRATUM_845719
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_843419
+	bool "Cortex-A53: 843419: A load or store might access an incorrect address"
+	depends on MODULES
+	default y
+	help
+	  This option builds kernel modules using the large memory model in
+	  order to avoid the use of the ADRP instruction, which can cause
+	  a subsequent memory access to use an incorrect address on Cortex-A53
+	  parts up to r0p4.
+
+	  Note that the kernel itself must be linked with a version of ld
+	  which fixes potentially affected ADRP instructions through the
+	  use of veneers.
+
+	  If unsure, say Y.
+
 endmenu
 
 

arch/arm64/Makefile

@@ -41,6 +41,10 @@ endif
 
 CHECKFLAGS	+= -D__aarch64__
 
+ifeq ($(CONFIG_ARM64_ERRATUM_843419), y)
+CFLAGS_MODULE	+= -mcmodel=large
+endif
+
 # Default value
 head-y		:= arch/arm64/kernel/head.o
 

arch/arm64/include/asm/pgtable.h

@@ -26,13 +26,9 @@
  * Software defined PTE bits definition.
  */
 #define PTE_VALID		(_AT(pteval_t, 1) << 0)
+#define PTE_WRITE		(PTE_DBM)		 /* same as DBM (51) */
 #define PTE_DIRTY		(_AT(pteval_t, 1) << 55)
 #define PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
-#ifdef CONFIG_ARM64_HW_AFDBM
-#define PTE_WRITE		(PTE_DBM)		 /* same as DBM */
-#else
-#define PTE_WRITE		(_AT(pteval_t, 1) << 57)
-#endif
 #define PTE_PROT_NONE		(_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */
 
 /*
@@ -146,7 +142,7 @@ extern struct page *empty_zero_page;
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 
 #ifdef CONFIG_ARM64_HW_AFDBM
-#define pte_hw_dirty(pte)	(!(pte_val(pte) & PTE_RDONLY))
+#define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
 #else
 #define pte_hw_dirty(pte)	(0)
 #endif
@@ -238,7 +234,7 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
  * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via
  * the page fault mechanism. Checking the dirty status of a pte becomes:
  *
- *   PTE_DIRTY || !PTE_RDONLY
+ *   PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY)
  */
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
@@ -503,7 +499,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 			      PTE_PROT_NONE | PTE_WRITE | PTE_TYPE_MASK;
 	/* preserve the hardware dirty information */
 	if (pte_hw_dirty(pte))
-		newprot |= PTE_DIRTY;
+		pte = pte_mkdirty(pte);
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }

arch/arm64/kernel/debug-monitors.c

@@ -134,7 +134,7 @@ static int os_lock_notify(struct notifier_block *self,
 				    unsigned long action, void *data)
 {
 	int cpu = (unsigned long)data;
-	if (action == CPU_ONLINE)
+	if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE)
 		smp_call_function_single(cpu, clear_os_lock, NULL, 1);
 	return NOTIFY_OK;
 }

arch/arm64/kernel/head.S

@@ -523,6 +523,11 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	msr	hstr_el2, xzr			// Disable CP15 traps to EL2
 #endif
 
+	/* EL2 debug */
+	mrs	x0, pmcr_el0			// Disable debug access traps
+	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
+	msr	mdcr_el2, x0			// all PMU counters from EL1
+
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr