Merge 4.10-rc4 into driver-core-next

We want the sysfs file revert and other fixes in here as well for
testing.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

.mailmap

@@ -137,6 +137,7 @@ Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
 Rudolf Marek <R.Marek@sh.cvut.cz>
 Rui Saraiva <rmps@joel.ist.utl.pt>
 Sachin P Sant <ssant@in.ibm.com>
+Sarangdhar Joshi <spjoshi@codeaurora.org>
 Sam Ravnborg <sam@mars.ravnborg.org>
 Santosh Shilimkar <ssantosh@kernel.org>
 Santosh Shilimkar <santosh.shilimkar@oracle.org>
@@ -150,10 +151,13 @@ Shuah Khan <shuah@kernel.org> <shuah.kh@samsung.com>
 Simon Kelley <simon@thekelleys.org.uk>
 Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
 Stephen Hemminger <shemminger@osdl.org>
+Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
+Subhash Jadavani <subhashj@codeaurora.org>
 Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
 Sumit Semwal <sumit.semwal@ti.com>
 Tejun Heo <htejun@gmail.com>
 Thomas Graf <tgraf@suug.ch>
+Thomas Pedersen <twp@codeaurora.org>
 Tony Luck <tony.luck@intel.com>
 Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
 Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>

Documentation/ABI/testing/sysfs-devices-deferred_probe

@@ -1,12 +0,0 @@
-What:		/sys/devices/.../deferred_probe
-Date:		August 2016
-Contact:	Ben Hutchings <ben.hutchings@codethink.co.uk>
-Description:
-		The /sys/devices/.../deferred_probe attribute is
-		present for all devices.  If a driver detects during
-		probing a device that a related device is not yet
-		ready, it may defer probing of the first device.  The
-		kernel will retry probing the first device after any
-		other device is successfully probed.  This attribute
-		reads as 1 if probing of this device is currently
-		deferred, or 0 otherwise.

Documentation/devicetree/bindings/i2c/i2c.txt

@@ -62,6 +62,9 @@ wants to support one of the below features, it should adapt the bindings below.
 	"irq" and "wakeup" names are recognized by I2C core, other names are
 	left to individual drivers.
 
+- host-notify
+	device uses SMBus host notify protocol instead of interrupt line.
+
 - multi-master
 	states that there is another master active on this bus. The OS can use
 	this information to adapt power management to keep the arbitration awake
@@ -81,6 +84,11 @@ Binding may contain optional "interrupts" property, describing interrupts
 used by the device. I2C core will assign "irq" interrupt (or the very first
 interrupt if not using interrupt names) as primary interrupt for the slave.
 
+Alternatively, devices supporting SMbus Host Notify, and connected to
+adapters that support this feature, may use "host-notify" property. I2C
+core will create a virtual interrupt for Host Notify and assign it as
+primary interrupt for the slave.
+
 Also, if device is marked as a wakeup source, I2C core will set up "wakeup"
 interrupt for the device. If "wakeup" interrupt name is not present in the
 binding, then primary interrupt will be used as wakeup interrupt.

Documentation/vm/page_frags

@@ -0,0 +1,42 @@
+Page fragments
+--------------
+
+A page fragment is an arbitrary-length arbitrary-offset area of memory
+which resides within a 0 or higher order compound page.  Multiple
+fragments within that page are individually refcounted, in the page's
+reference counter.
+
+The page_frag functions, page_frag_alloc and page_frag_free, provide a
+simple allocation framework for page fragments.  This is used by the
+network stack and network device drivers to provide a backing region of
+memory for use as either an sk_buff->head, or to be used in the "frags"
+portion of skb_shared_info.
+
+In order to make use of the page fragment APIs a backing page fragment
+cache is needed.  This provides a central point for the fragment allocation
+and tracks allows multiple calls to make use of a cached page.  The
+advantage to doing this is that multiple calls to get_page can be avoided
+which can be expensive at allocation time.  However due to the nature of
+this caching it is required that any calls to the cache be protected by
+either a per-cpu limitation, or a per-cpu limitation and forcing interrupts
+to be disabled when executing the fragment allocation.
+
+The network stack uses two separate caches per CPU to handle fragment
+allocation.  The netdev_alloc_cache is used by callers making use of the
+__netdev_alloc_frag and __netdev_alloc_skb calls.  The napi_alloc_cache is
+used by callers of the __napi_alloc_frag and __napi_alloc_skb calls.  The
+main difference between these two calls is the context in which they may be
+called.  The "netdev" prefixed functions are usable in any context as these
+functions will disable interrupts, while the "napi" prefixed functions are
+only usable within the softirq context.
+
+Many network device drivers use a similar methodology for allocating page
+fragments, but the page fragments are cached at the ring or descriptor
+level.  In order to enable these cases it is necessary to provide a generic
+way of tearing down a page cache.  For this reason __page_frag_cache_drain
+was implemented.  It allows for freeing multiple references from a single
+page via a single call.  The advantage to doing this is that it allows for
+cleaning up the multiple references that were added to a page in order to
+avoid calling get_page per allocation.
+
+Alexander Duyck, Nov 29, 2016.

MAINTAINERS

@@ -81,7 +81,6 @@ Descriptions of section entries:
 	Q: Patchwork web based patch tracking system site
 	T: SCM tree type and location.
 	   Type is one of: git, hg, quilt, stgit, topgit
-	B: Bug tracking system location.
 	S: Status, one of the following:
 	   Supported:	Someone is actually paid to look after this.
 	   Maintained:	Someone actually looks after it.
@@ -2194,14 +2193,6 @@ L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Supported
 F:	sound/soc/atmel
 
-ATMEL DMA DRIVER
-M:	Nicolas Ferre <nicolas.ferre@atmel.com>
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
-F:	drivers/dma/at_hdmac.c
-F:	drivers/dma/at_hdmac_regs.h
-F:	include/linux/platform_data/dma-atmel.h
-
 ATMEL XDMA DRIVER
 M:	Ludovic Desroches <ludovic.desroches@atmel.com>
 L:	linux-arm-kernel@lists.infradead.org
@@ -4117,7 +4108,7 @@ F:	drivers/gpu/drm/cirrus/
 RADEON and AMDGPU DRM DRIVERS
 M:	Alex Deucher <alexander.deucher@amd.com>
 M:	Christian König <christian.koenig@amd.com>
-L:	dri-devel@lists.freedesktop.org
+L:	amd-gfx@lists.freedesktop.org
 T:	git git://people.freedesktop.org/~agd5f/linux
 S:	Supported
 F:	drivers/gpu/drm/radeon/
@@ -8179,6 +8170,15 @@ S:	Maintained
 F:	drivers/tty/serial/atmel_serial.c
 F:	include/linux/atmel_serial.h
 
+MICROCHIP / ATMEL DMA DRIVER
+M:	Ludovic Desroches <ludovic.desroches@microchip.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	dmaengine@vger.kernel.org
+S:	Supported
+F:	drivers/dma/at_hdmac.c
+F:	drivers/dma/at_hdmac_regs.h
+F:	include/linux/platform_data/dma-atmel.h
+
 MICROCHIP / ATMEL ISC DRIVER
 M:	Songjun Wu <songjun.wu@microchip.com>
 L:	linux-media@vger.kernel.org

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Roaring Lionus
 
 # *DOCUMENTATION*

arch/arm64/include/asm/assembler.h

@@ -164,22 +164,25 @@ lr	.req	x30		// link register
 
 /*
  * Pseudo-ops for PC-relative adr/ldr/str <reg>, <symbol> where
- * <symbol> is within the range +/- 4 GB of the PC.
+ * <symbol> is within the range +/- 4 GB of the PC when running
+ * in core kernel context. In module context, a movz/movk sequence
+ * is used, since modules may be loaded far away from the kernel
+ * when KASLR is in effect.
  */
 	/*
 	 * @dst: destination register (64 bit wide)
 	 * @sym: name of the symbol
-	 * @tmp: optional scratch register to be used if <dst> == sp, which
-	 *       is not allowed in an adrp instruction
 	 */
-	.macro	adr_l, dst, sym, tmp=
-	.ifb	\tmp
+	.macro	adr_l, dst, sym
+#ifndef MODULE
 	adrp	\dst, \sym
 	add	\dst, \dst, :lo12:\sym
-	.else
-	adrp	\tmp, \sym
-	add	\dst, \tmp, :lo12:\sym
-	.endif
+#else
+	movz	\dst, #:abs_g3:\sym
+	movk	\dst, #:abs_g2_nc:\sym
+	movk	\dst, #:abs_g1_nc:\sym
+	movk	\dst, #:abs_g0_nc:\sym
+#endif
 	.endm
 
 	/*
@@ -190,6 +193,7 @@ lr	.req	x30		// link register
 	 *       the address
 	 */
 	.macro	ldr_l, dst, sym, tmp=
+#ifndef MODULE
 	.ifb	\tmp
 	adrp	\dst, \sym
 	ldr	\dst, [\dst, :lo12:\sym]
@@ -197,6 +201,15 @@ lr	.req	x30		// link register
 	adrp	\tmp, \sym
 	ldr	\dst, [\tmp, :lo12:\sym]
 	.endif
+#else
+	.ifb	\tmp
+	adr_l	\dst, \sym
+	ldr	\dst, [\dst]
+	.else
+	adr_l	\tmp, \sym
+	ldr	\dst, [\tmp]
+	.endif
+#endif
 	.endm
 
 	/*
@@ -206,8 +219,13 @@ lr	.req	x30		// link register
 	 *       while <src> needs to be preserved.
 	 */
 	.macro	str_l, src, sym, tmp
+#ifndef MODULE
 	adrp	\tmp, \sym
 	str	\src, [\tmp, :lo12:\sym]
+#else
+	adr_l	\tmp, \sym
+	str	\src, [\tmp]
+#endif
 	.endm
 
 	/*

arch/arm64/mm/hugetlbpage.c

@@ -239,7 +239,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 		ncontig = find_num_contig(vma->vm_mm, addr, cpte,
 					  *cpte, &pgsize);
 		for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize) {
-			changed = ptep_set_access_flags(vma, addr, cpte,
+			changed |= ptep_set_access_flags(vma, addr, cpte,
 							pfn_pte(pfn,
 								hugeprot),
 							dirty);

arch/x86/boot/string.c

@@ -14,6 +14,7 @@
 
 #include <linux/types.h>
 #include "ctype.h"
+#include "string.h"
 
 int memcmp(const void *s1, const void *s2, size_t len)
 {

arch/x86/boot/string.h

@@ -18,4 +18,13 @@ int memcmp(const void *s1, const void *s2, size_t len);
 #define memset(d,c,l) __builtin_memset(d,c,l)
 #define memcmp	__builtin_memcmp
 
+extern int strcmp(const char *str1, const char *str2);
+extern int strncmp(const char *cs, const char *ct, size_t count);
+extern size_t strlen(const char *s);
+extern char *strstr(const char *s1, const char *s2);
+extern size_t strnlen(const char *s, size_t maxlen);
+extern unsigned int atou(const char *s);
+extern unsigned long long simple_strtoull(const char *cp, char **endp,
+					  unsigned int base);
+
 #endif /* BOOT_STRING_H */

arch/x86/crypto/aesni-intel_glue.c

@@ -1020,7 +1020,8 @@ struct {
 	const char *basename;
 	struct simd_skcipher_alg *simd;
 } aesni_simd_skciphers2[] = {
-#if IS_ENABLED(CONFIG_CRYPTO_PCBC)
+#if (defined(MODULE) && IS_ENABLED(CONFIG_CRYPTO_PCBC)) || \
+    IS_BUILTIN(CONFIG_CRYPTO_PCBC)
 	{
 		.algname	= "pcbc(aes)",
 		.drvname	= "pcbc-aes-aesni",

arch/x86/entry/entry_32.S

@@ -254,23 +254,6 @@ ENTRY(__switch_to_asm)
 	jmp	__switch_to
 END(__switch_to_asm)
 
-/*
- * The unwinder expects the last frame on the stack to always be at the same
- * offset from the end of the page, which allows it to validate the stack.
- * Calling schedule_tail() directly would break that convention because its an
- * asmlinkage function so its argument has to be pushed on the stack.  This
- * wrapper creates a proper "end of stack" frame header before the call.
- */
-ENTRY(schedule_tail_wrapper)
-	FRAME_BEGIN
-
-	pushl	%eax
-	call	schedule_tail
-	popl	%eax
-
-	FRAME_END
-	ret
-ENDPROC(schedule_tail_wrapper)
 /*
  * A newly forked process directly context switches into this address.
  *
@@ -279,15 +262,24 @@ ENDPROC(schedule_tail_wrapper)
  * edi: kernel thread arg
  */
 ENTRY(ret_from_fork)
-	call	schedule_tail_wrapper
+	FRAME_BEGIN		/* help unwinder find end of stack */
+
+	/*
+	 * schedule_tail() is asmlinkage so we have to put its 'prev' argument
+	 * on the stack.
+	 */
+	pushl	%eax
+	call	schedule_tail
+	popl	%eax
 
 	testl	%ebx, %ebx
 	jnz	1f		/* kernel threads are uncommon */
 
 2:
 	/* When we fork, we trace the syscall return in the child, too. */
-	movl    %esp, %eax
+	leal	FRAME_OFFSET(%esp), %eax
 	call    syscall_return_slowpath
+	FRAME_END
 	jmp     restore_all
 
 	/* kernel thread */

arch/x86/entry/entry_64.S

@@ -36,6 +36,7 @@
 #include <asm/smap.h>
 #include <asm/pgtable_types.h>
 #include <asm/export.h>
+#include <asm/frame.h>
 #include <linux/err.h>
 
 .code64
@@ -408,17 +409,19 @@ END(__switch_to_asm)
  * r12: kernel thread arg
  */
 ENTRY(ret_from_fork)
+	FRAME_BEGIN			/* help unwinder find end of stack */
 	movq	%rax, %rdi
-	call	schedule_tail			/* rdi: 'prev' task parameter */
+	call	schedule_tail		/* rdi: 'prev' task parameter */
 
-	testq	%rbx, %rbx			/* from kernel_thread? */
-	jnz	1f				/* kernel threads are uncommon */
+	testq	%rbx, %rbx		/* from kernel_thread? */
+	jnz	1f			/* kernel threads are uncommon */
 
 2:
-	movq	%rsp, %rdi
+	leaq	FRAME_OFFSET(%rsp),%rdi	/* pt_regs pointer */
 	call	syscall_return_slowpath	/* returns with IRQs disabled */
 	TRACE_IRQS_ON			/* user mode is traced as IRQS on */
 	SWAPGS
+	FRAME_END
 	jmp	restore_regs_and_iret
 
 1:

arch/x86/events/core.c

@@ -505,6 +505,10 @@ int x86_pmu_hw_config(struct perf_event *event)
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
+
+		/* There's no sense in having PEBS for non sampling events: */
+		if (!is_sampling_event(event))
+			return -EINVAL;
 	}
 	/*
 	 * check that PEBS LBR correction does not conflict with

arch/x86/events/intel/core.c

@@ -3987,7 +3987,7 @@ __init int intel_pmu_init(void)
 		     x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC);
 		x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC;
 	}
-	x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+	x86_pmu.intel_ctrl = (1ULL << x86_pmu.num_counters) - 1;
 
 	if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) {
 		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",

arch/x86/events/intel/cstate.c

@@ -434,6 +434,7 @@ static struct pmu cstate_core_pmu = {
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
 	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
+	.module		= THIS_MODULE,
 };
 
 static struct pmu cstate_pkg_pmu = {
@@ -447,6 +448,7 @@ static struct pmu cstate_pkg_pmu = {
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
 	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
+	.module		= THIS_MODULE,
 };
 
 static const struct cstate_model nhm_cstates __initconst = {

arch/x86/events/intel/ds.c

@@ -1389,9 +1389,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 			continue;
 
 		/* log dropped samples number */
-		if (error[bit])
+		if (error[bit]) {
 			perf_log_lost_samples(event, error[bit]);
 
+			if (perf_event_account_interrupt(event))
+				x86_pmu_stop(event, 0);
+		}
+
 		if (counts[bit]) {
 			__intel_pmu_pebs_event(event, iregs, base,
 					       top, bit, counts[bit]);

arch/x86/events/intel/rapl.c

@@ -697,6 +697,7 @@ static int __init init_rapl_pmus(void)
 	rapl_pmus->pmu.start		= rapl_pmu_event_start;
 	rapl_pmus->pmu.stop		= rapl_pmu_event_stop;
 	rapl_pmus->pmu.read		= rapl_pmu_event_read;
+	rapl_pmus->pmu.module		= THIS_MODULE;
 	return 0;
 }
 

arch/x86/events/intel/uncore.c

@@ -733,6 +733,7 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 			.start		= uncore_pmu_event_start,
 			.stop		= uncore_pmu_event_stop,
 			.read		= uncore_pmu_event_read,
+			.module		= THIS_MODULE,
 		};
 	} else {
 		pmu->pmu = *pmu->type->pmu;

arch/x86/events/intel/uncore_snbep.c

@@ -2686,7 +2686,7 @@ static struct intel_uncore_type *hswep_msr_uncores[] = {
 
 void hswep_uncore_cpu_init(void)
 {
-	int pkg = topology_phys_to_logical_pkg(0);
+	int pkg = boot_cpu_data.logical_proc_id;
 
 	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;