Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

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/devicetree/bindings/mtd/tango-nand.txt

@@ -5,7 +5,7 @@ Required properties:
 - compatible: "sigma,smp8758-nand"
 - reg: address/size of nfc_reg, nfc_mem, and pbus_reg
 - dmas: reference to the DMA channel used by the controller
-- dma-names: "nfc_sbox"
+- dma-names: "rxtx"
 - clocks: reference to the system clock
 - #address-cells: <1>
 - #size-cells: <0>
@@ -17,9 +17,9 @@ Example:
 
 	nandc: nand-controller@2c000 {
 		compatible = "sigma,smp8758-nand";
-		reg = <0x2c000 0x30 0x2d000 0x800 0x20000 0x1000>;
+		reg = <0x2c000 0x30>, <0x2d000 0x800>, <0x20000 0x1000>;
 		dmas = <&dma0 3>;
-		dma-names = "nfc_sbox";
+		dma-names = "rxtx";
 		clocks = <&clkgen SYS_CLK>;
 		#address-cells = <1>;
 		#size-cells = <0>;

Documentation/devicetree/bindings/net/ti,dp83867.txt

@@ -3,9 +3,11 @@
 Required properties:
 	- reg - The ID number for the phy, usually a small integer
 	- ti,rx-internal-delay - RGMII Receive Clock Delay - see dt-bindings/net/ti-dp83867.h
-		for applicable values
+		for applicable values. Required only if interface type is
+		PHY_INTERFACE_MODE_RGMII_ID or PHY_INTERFACE_MODE_RGMII_RXID
 	- ti,tx-internal-delay - RGMII Transmit Clock Delay - see dt-bindings/net/ti-dp83867.h
-		for applicable values
+		for applicable values. Required only if interface type is
+		PHY_INTERFACE_MODE_RGMII_ID or PHY_INTERFACE_MODE_RGMII_TXID
 	- ti,fifo-depth - Transmitt FIFO depth- see dt-bindings/net/ti-dp83867.h
 		for applicable values
 

MAINTAINERS

@@ -2193,14 +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
@@ -8184,6 +8176,15 @@ 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/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;

arch/x86/include/asm/intel-family.h

@@ -57,7 +57,7 @@
 #define INTEL_FAM6_ATOM_SILVERMONT2	0x4D /* Avaton/Rangely */
 #define INTEL_FAM6_ATOM_AIRMONT		0x4C /* CherryTrail / Braswell */
 #define INTEL_FAM6_ATOM_MERRIFIELD	0x4A /* Tangier */
-#define INTEL_FAM6_ATOM_MOOREFIELD	0x5A /* Annidale */
+#define INTEL_FAM6_ATOM_MOOREFIELD	0x5A /* Anniedale */
 #define INTEL_FAM6_ATOM_GOLDMONT	0x5C
 #define INTEL_FAM6_ATOM_DENVERTON	0x5F /* Goldmont Microserver */
 

arch/x86/include/asm/microcode_intel.h

@@ -52,6 +52,21 @@ struct extended_sigtable {
 
 #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE)
 
+static inline u32 intel_get_microcode_revision(void)
+{
+	u32 rev, dummy;
+
+	native_wrmsrl(MSR_IA32_UCODE_REV, 0);
+
+	/* As documented in the SDM: Do a CPUID 1 here */
+	native_cpuid_eax(1);
+
+	/* get the current revision from MSR 0x8B */
+	native_rdmsr(MSR_IA32_UCODE_REV, dummy, rev);
+
+	return rev;
+}
+
 #ifdef CONFIG_MICROCODE_INTEL
 extern void __init load_ucode_intel_bsp(void);
 extern void load_ucode_intel_ap(void);

arch/x86/include/asm/processor.h

@@ -219,6 +219,24 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
 	    : "memory");
 }
 
+#define native_cpuid_reg(reg)					\
+static inline unsigned int native_cpuid_##reg(unsigned int op)	\
+{								\
+	unsigned int eax = op, ebx, ecx = 0, edx;		\
+								\
+	native_cpuid(&eax, &ebx, &ecx, &edx);			\
+								\
+	return reg;						\
+}
+
+/*
+ * Native CPUID functions returning a single datum.
+ */
+native_cpuid_reg(eax)
+native_cpuid_reg(ebx)
+native_cpuid_reg(ecx)
+native_cpuid_reg(edx)
+
 static inline void load_cr3(pgd_t *pgdir)
 {
 	write_cr3(__pa(pgdir));

arch/x86/include/asm/stacktrace.h

@@ -58,7 +58,7 @@ get_frame_pointer(struct task_struct *task, struct pt_regs *regs)
 	if (task == current)
 		return __builtin_frame_address(0);
 
-	return (unsigned long *)((struct inactive_task_frame *)task->thread.sp)->bp;
+	return &((struct inactive_task_frame *)task->thread.sp)->bp;
 }
 #else
 static inline unsigned long *

arch/x86/include/asm/switch_to.h

@@ -36,7 +36,10 @@ static inline void prepare_switch_to(struct task_struct *prev,
 
 asmlinkage void ret_from_fork(void);
 
-/* data that is pointed to by thread.sp */
+/*
+ * This is the structure pointed to by thread.sp for an inactive task.  The
+ * order of the fields must match the code in __switch_to_asm().
+ */
 struct inactive_task_frame {
 #ifdef CONFIG_X86_64
 	unsigned long r15;
@@ -48,6 +51,11 @@ struct inactive_task_frame {
 	unsigned long di;
 #endif
 	unsigned long bx;
+
+	/*
+	 * These two fields must be together.  They form a stack frame header,
+	 * needed by get_frame_pointer().
+	 */
 	unsigned long bp;
 	unsigned long ret_addr;
 };

arch/x86/kernel/cpu/amd.c

@@ -309,15 +309,8 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 	/* get information required for multi-node processors */
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
-		u32 eax, ebx, ecx, edx;
 
-		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
-		node_id = ecx & 7;
-
-		/* get compute unit information */
-		smp_num_siblings = ((ebx >> 8) & 3) + 1;
-		c->x86_max_cores /= smp_num_siblings;
-		c->cpu_core_id = ebx & 0xff;
+		node_id = cpuid_ecx(0x8000001e) & 7;
 
 		/*
 		 * We may have multiple LLCs if L3 caches exist, so check if we

arch/x86/kernel/cpu/common.c

@@ -1221,7 +1221,7 @@ static __init int setup_disablecpuid(char *arg)
 {
 	int bit;
 
-	if (get_option(&arg, &bit) && bit < NCAPINTS*32)
+	if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32)
 		setup_clear_cpu_cap(bit);
 	else
 		return 0;

arch/x86/kernel/cpu/intel.c

@@ -14,6 +14,7 @@
 #include <asm/bugs.h>
 #include <asm/cpu.h>
 #include <asm/intel-family.h>
+#include <asm/microcode_intel.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
@@ -78,14 +79,8 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		(c->x86 == 0x6 && c->x86_model >= 0x0e))
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 
-	if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) {
-		unsigned lower_word;
-
-		wrmsr(MSR_IA32_UCODE_REV, 0, 0);
-		/* Required by the SDM */
-		sync_core();
-		rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode);
-	}
+	if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64))
+		c->microcode = intel_get_microcode_revision();
 
 	/*
 	 * Atom erratum AAE44/AAF40/AAG38/AAH41:

arch/x86/kernel/cpu/microcode/intel.c

@@ -150,7 +150,7 @@ static struct ucode_patch *__alloc_microcode_buf(void *data, unsigned int size)
 {
 	struct ucode_patch *p;
 
-	p = kzalloc(size, GFP_KERNEL);
+	p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL);
 	if (!p)
 		return ERR_PTR(-ENOMEM);
 
@@ -368,26 +368,6 @@ next:
 	return patch;
 }
 
-static void cpuid_1(void)
-{
-	/*
-	 * According to the Intel SDM, Volume 3, 9.11.7:
-	 *
-	 *   CPUID returns a value in a model specific register in
-	 *   addition to its usual register return values. The
-	 *   semantics of CPUID cause it to deposit an update ID value
-	 *   in the 64-bit model-specific register at address 08BH
-	 *   (IA32_BIOS_SIGN_ID). If no update is present in the
-	 *   processor, the value in the MSR remains unmodified.
-	 *
-	 * Use native_cpuid -- this code runs very early and we don't
-	 * want to mess with paravirt.
-	 */
-	unsigned int eax = 1, ebx, ecx = 0, edx;
-
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-}
-
 static int collect_cpu_info_early(struct ucode_cpu_info *uci)
 {
 	unsigned int val[2];
@@ -410,15 +390,8 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci)
 		native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
 		csig.pf = 1 << ((val[1] >> 18) & 7);
 	}
-	native_wrmsrl(MSR_IA32_UCODE_REV, 0);
-
-	/* As documented in the SDM: Do a CPUID 1 here */
-	cpuid_1();
 
-	/* get the current revision from MSR 0x8B */
-	native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
-
-	csig.rev = val[1];
+	csig.rev = intel_get_microcode_revision();
 
 	uci->cpu_sig = csig;
 	uci->valid = 1;
@@ -602,7 +575,7 @@ static inline void print_ucode(struct ucode_cpu_info *uci)
 static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 {
 	struct microcode_intel *mc;
-	unsigned int val[2];
+	u32 rev;
 
 	mc = uci->mc;
 	if (!mc)
@@ -610,21 +583,16 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 
 	/* write microcode via MSR 0x79 */
 	native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
-	native_wrmsrl(MSR_IA32_UCODE_REV, 0);
 
-	/* As documented in the SDM: Do a CPUID 1 here */
-	cpuid_1();
-
-	/* get the current revision from MSR 0x8B */
-	native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
-	if (val[1] != mc->hdr.rev)
+	rev = intel_get_microcode_revision();
+	if (rev != mc->hdr.rev)
 		return -1;
 
 #ifdef CONFIG_X86_64
 	/* Flush global tlb. This is precaution. */
 	flush_tlb_early();
 #endif
-	uci->cpu_sig.rev = val[1];
+	uci->cpu_sig.rev = rev;
 
 	if (early)
 		print_ucode(uci);
@@ -804,8 +772,8 @@ static int apply_microcode_intel(int cpu)
 	struct microcode_intel *mc;
 	struct ucode_cpu_info *uci;
 	struct cpuinfo_x86 *c;
-	unsigned int val[2];
 	static int prev_rev;
+	u32 rev;
 
 	/* We should bind the task to the CPU */
 	if (WARN_ON(raw_smp_processor_id() != cpu))
@@ -822,33 +790,28 @@ static int apply_microcode_intel(int cpu)
 
 	/* write microcode via MSR 0x79 */
 	wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
-	wrmsrl(MSR_IA32_UCODE_REV, 0);
-
-	/* As documented in the SDM: Do a CPUID 1 here */
-	cpuid_1();
 
-	/* get the current revision from MSR 0x8B */
-	rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
+	rev = intel_get_microcode_revision();
 
-	if (val[1] != mc->hdr.rev) {
+	if (rev != mc->hdr.rev) {
 		pr_err("CPU%d update to revision 0x%x failed\n",
 		       cpu, mc->hdr.rev);
 		return -1;
 	}
 
-	if (val[1] != prev_rev) {
+	if (rev != prev_rev) {
 		pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n",
-			val[1],
+			rev,
 			mc->hdr.date & 0xffff,
 			mc->hdr.date >> 24,
 			(mc->hdr.date >> 16) & 0xff);
-		prev_rev = val[1];
+		prev_rev = rev;
 	}
 
 	c = &cpu_data(cpu);
 
-	uci->cpu_sig.rev = val[1];
-	c->microcode = val[1];
+	uci->cpu_sig.rev = rev;
+	c->microcode = rev;
 
 	return 0;
 }
@@ -860,7 +823,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 	u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL;
 	int new_rev = uci->cpu_sig.rev;
 	unsigned int leftover = size;
-	unsigned int curr_mc_size = 0;
+	unsigned int curr_mc_size = 0, new_mc_size = 0;
 	unsigned int csig, cpf;
 
 	while (leftover) {
@@ -901,6 +864,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 			vfree(new_mc);
 			new_rev = mc_header.rev;
 			new_mc  = mc;
+			new_mc_size = mc_size;
 			mc = NULL;	/* trigger new vmalloc */
 		}
 
@@ -926,7 +890,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 	 * permanent memory. So it will be loaded early when a CPU is hot added
 	 * or resumes.
 	 */
-	save_mc_for_early(new_mc, curr_mc_size);
+	save_mc_for_early(new_mc, new_mc_size);
 
 	pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
 		 cpu, new_rev, uci->cpu_sig.rev);

arch/x86/kernel/tsc.c

@@ -694,6 +694,7 @@ unsigned long native_calibrate_tsc(void)
 			crystal_khz = 24000;	/* 24.0 MHz */
 			break;
 		case INTEL_FAM6_SKYLAKE_X:
+		case INTEL_FAM6_ATOM_DENVERTON:
 			crystal_khz = 25000;	/* 25.0 MHz */
 			break;
 		case INTEL_FAM6_ATOM_GOLDMONT:

arch/x86/kernel/unwind_frame.c

@@ -6,6 +6,21 @@
 
 #define FRAME_HEADER_SIZE (sizeof(long) * 2)
 
+/*
+ * This disables KASAN checking when reading a value from another task's stack,
+ * since the other task could be running on another CPU and could have poisoned
+ * the stack in the meantime.
+ */
+#define READ_ONCE_TASK_STACK(task, x)			\
+({							\
+	unsigned long val;				\
+	if (task == current)				\
+		val = READ_ONCE(x);			\
+	else						\
+		val = READ_ONCE_NOCHECK(x);		\
+	val;						\
+})
+
 static void unwind_dump(struct unwind_state *state, unsigned long *sp)
 {
 	static bool dumped_before = false;
@@ -48,7 +63,8 @@ unsigned long unwind_get_return_address(struct unwind_state *state)
 	if (state->regs && user_mode(state->regs))
 		return 0;
 
-	addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p,
+	addr = READ_ONCE_TASK_STACK(state->task, *addr_p);
+	addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr,
 				     addr_p);
 
 	return __kernel_text_address(addr) ? addr : 0;
@@ -162,7 +178,7 @@ bool unwind_next_frame(struct unwind_state *state)
 	if (state->regs)
 		next_bp = (unsigned long *)state->regs->bp;
 	else
-		next_bp = (unsigned long *)*state->bp;
+		next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task,*state->bp);
 
 	/* is the next frame pointer an encoded pointer to pt_regs? */
 	regs = decode_frame_pointer(next_bp);
@@ -207,6 +223,16 @@ bool unwind_next_frame(struct unwind_state *state)
 	return true;
 
 bad_address:
+	/*
+	 * When unwinding a non-current task, the task might actually be
+	 * running on another CPU, in which case it could be modifying its
+	 * stack while we're reading it.  This is generally not a problem and
+	 * can be ignored as long as the caller understands that unwinding
+	 * another task will not always succeed.
+	 */
+	if (state->task != current)
+		goto the_end;
+
 	if (state->regs) {
 		printk_deferred_once(KERN_WARNING
 			"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",

arch/x86/kvm/emulate.c

@@ -818,6 +818,20 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
 	return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception);
 }
 
+static int segmented_write_std(struct x86_emulate_ctxt *ctxt,
+			       struct segmented_address addr,
+			       void *data,
+			       unsigned int size)
+{
+	int rc;
+	ulong linear;
+
+	rc = linearize(ctxt, addr, size, true, &linear);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+	return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception);
+}
+
 /*
  * Prefetch the remaining bytes of the instruction without crossing page
  * boundary if they are not in fetch_cache yet.
@@ -1571,7 +1585,6 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				    &ctxt->exception);
 }
 
-/* Does not support long mode */
 static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				     u16 selector, int seg, u8 cpl,
 				     enum x86_transfer_type transfer,
@@ -1608,20 +1621,34 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 
 	rpl = selector & 3;
 
-	/* NULL selector is not valid for TR, CS and SS (except for long mode) */
-	if ((seg == VCPU_SREG_CS
-	     || (seg == VCPU_SREG_SS
-		 && (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl))
-	     || seg == VCPU_SREG_TR)
-	    && null_selector)
-		goto exception;
-
 	/* TR should be in GDT only */
 	if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
 		goto exception;
 
-	if (null_selector) /* for NULL selector skip all following checks */
+	/* NULL selector is not valid for TR, CS and (except for long mode) SS */
+	if (null_selector) {
+		if (seg == VCPU_SREG_CS || seg == VCPU_SREG_TR)
+			goto exception;
+
+		if (seg == VCPU_SREG_SS) {
+			if (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl)
+				goto exception;
+
+			/*
+			 * ctxt->ops->set_segment expects the CPL to be in
+			 * SS.DPL, so fake an expand-up 32-bit data segment.
+			 */
+			seg_desc.type = 3;
+			seg_desc.p = 1;
+			seg_desc.s = 1;
+			seg_desc.dpl = cpl;
+			seg_desc.d = 1;
+			seg_desc.g = 1;
+		}
+
+		/* Skip all following checks */
 		goto load;
+	}
 
 	ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr);
 	if (ret != X86EMUL_CONTINUE)
@@ -1737,6 +1764,21 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				   u16 selector, int seg)
 {
 	u8 cpl = ctxt->ops->cpl(ctxt);
+
+	/*
+	 * None of MOV, POP and LSS can load a NULL selector in CPL=3, but
+	 * they can load it at CPL<3 (Intel's manual says only LSS can,
+	 * but it's wrong).
+	 *
+	 * However, the Intel manual says that putting IST=1/DPL=3 in
+	 * an interrupt gate will result in SS=3 (the AMD manual instead
+	 * says it doesn't), so allow SS=3 in __load_segment_descriptor
+	 * and only forbid it here.
+	 */
+	if (seg == VCPU_SREG_SS && selector == 3 &&
+	    ctxt->mode == X86EMUL_MODE_PROT64)
+		return emulate_exception(ctxt, GP_VECTOR, 0, true);
+
 	return __load_segment_descriptor(ctxt, selector, seg, cpl,
 					 X86_TRANSFER_NONE, NULL);
 }
@@ -3685,8 +3727,8 @@ static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt,
 	}
 	/* Disable writeback. */
 	ctxt->dst.type = OP_NONE;
-	return segmented_write(ctxt, ctxt->dst.addr.mem,
-			       &desc_ptr, 2 + ctxt->op_bytes);
+	return segmented_write_std(ctxt, ctxt->dst.addr.mem,
+				   &desc_ptr, 2 + ctxt->op_bytes);
 }
 
 static int em_sgdt(struct x86_emulate_ctxt *ctxt)
@@ -3932,7 +3974,7 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 	else
 		size = offsetof(struct fxregs_state, xmm_space[0]);
 
-	return segmented_write(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+	return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
 }
 
 static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt,
@@ -3974,7 +4016,7 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	rc = segmented_read(ctxt, ctxt->memop.addr.mem, &fx_state, 512);
+	rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 

arch/x86/kvm/lapic.c

@@ -2426,3 +2426,9 @@ void kvm_lapic_init(void)
 	jump_label_rate_limit(&apic_hw_disabled, HZ);
 	jump_label_rate_limit(&apic_sw_disabled, HZ);
 }
+
+void kvm_lapic_exit(void)
+{
+	static_key_deferred_flush(&apic_hw_disabled);
+	static_key_deferred_flush(&apic_sw_disabled);
+}

arch/x86/kvm/lapic.h

@@ -110,6 +110,7 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
 
 int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
 void kvm_lapic_init(void);
+void kvm_lapic_exit(void);
 
 #define VEC_POS(v) ((v) & (32 - 1))
 #define REG_POS(v) (((v) >> 5) << 4)

arch/x86/kvm/x86.c

@@ -3342,6 +3342,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 
 	switch (cap->cap) {
 	case KVM_CAP_HYPERV_SYNIC:
+		if (!irqchip_in_kernel(vcpu->kvm))
+			return -EINVAL;
 		return kvm_hv_activate_synic(vcpu);
 	default:
 		return -EINVAL;
@@ -6045,6 +6047,7 @@ out:
 
 void kvm_arch_exit(void)
 {
+	kvm_lapic_exit();
 	perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
 
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))

arch/x86/mm/mpx.c

@@ -293,7 +293,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 	 * We were not able to extract an address from the instruction,
 	 * probably because there was something invalid in it.
 	 */
-	if (info->si_addr == (void *)-1) {
+	if (info->si_addr == (void __user *)-1) {
 		err = -EINVAL;
 		goto err_out;
 	}

arch/x86/platform/efi/efi.c

@@ -210,6 +210,70 @@ int __init efi_memblock_x86_reserve_range(void)
 	return 0;
 }
 
+#define OVERFLOW_ADDR_SHIFT	(64 - EFI_PAGE_SHIFT)
+#define OVERFLOW_ADDR_MASK	(U64_MAX << OVERFLOW_ADDR_SHIFT)
+#define U64_HIGH_BIT		(~(U64_MAX >> 1))
+
+static bool __init efi_memmap_entry_valid(const efi_memory_desc_t *md, int i)
+{
+	u64 end = (md->num_pages << EFI_PAGE_SHIFT) + md->phys_addr - 1;
+	u64 end_hi = 0;
+	char buf[64];
+
+	if (md->num_pages == 0) {
+		end = 0;
+	} else if (md->num_pages > EFI_PAGES_MAX ||
+		   EFI_PAGES_MAX - md->num_pages <
+		   (md->phys_addr >> EFI_PAGE_SHIFT)) {
+		end_hi = (md->num_pages & OVERFLOW_ADDR_MASK)
+			>> OVERFLOW_ADDR_SHIFT;
+
+		if ((md->phys_addr & U64_HIGH_BIT) && !(end & U64_HIGH_BIT))
+			end_hi += 1;
+	} else {
+		return true;
+	}
+
+	pr_warn_once(FW_BUG "Invalid EFI memory map entries:\n");
+
+	if (end_hi) {
+		pr_warn("mem%02u: %s range=[0x%016llx-0x%llx%016llx] (invalid)\n",
+			i, efi_md_typeattr_format(buf, sizeof(buf), md),
+			md->phys_addr, end_hi, end);
+	} else {
+		pr_warn("mem%02u: %s range=[0x%016llx-0x%016llx] (invalid)\n",
+			i, efi_md_typeattr_format(buf, sizeof(buf), md),
+			md->phys_addr, end);
+	}
+	return false;
+}
+
+static void __init efi_clean_memmap(void)
+{
+	efi_memory_desc_t *out = efi.memmap.map;
+	const efi_memory_desc_t *in = out;
+	const efi_memory_desc_t *end = efi.memmap.map_end;
+	int i, n_removal;
+
+	for (i = n_removal = 0; in < end; i++) {
+		if (efi_memmap_entry_valid(in, i)) {
+			if (out != in)
+				memcpy(out, in, efi.memmap.desc_size);
+			out = (void *)out + efi.memmap.desc_size;
+		} else {
+			n_removal++;
+		}
+		in = (void *)in + efi.memmap.desc_size;
+	}
+
+	if (n_removal > 0) {
+		u64 size = efi.memmap.nr_map - n_removal;
+
+		pr_warn("Removing %d invalid memory map entries.\n", n_removal);
+		efi_memmap_install(efi.memmap.phys_map, size);
+	}
+}
+
 void __init efi_print_memmap(void)
 {
 	efi_memory_desc_t *md;
@@ -472,6 +536,8 @@ void __init efi_init(void)
 		}
 	}
 
+	efi_clean_memmap();
+
 	if (efi_enabled(EFI_DBG))
 		efi_print_memmap();
 }

arch/x86/platform/efi/quirks.c

@@ -214,7 +214,7 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
 
 	new_size = efi.memmap.desc_size * num_entries;
 
-	new_phys = memblock_alloc(new_size, 0);
+	new_phys = efi_memmap_alloc(num_entries);
 	if (!new_phys) {
 		pr_err("Could not allocate boot services memmap\n");
 		return;
@@ -355,7 +355,7 @@ void __init efi_free_boot_services(void)
 	}
 
 	new_size = efi.memmap.desc_size * num_entries;
-	new_phys = memblock_alloc(new_size, 0);
+	new_phys = efi_memmap_alloc(num_entries);
 	if (!new_phys) {
 		pr_err("Failed to allocate new EFI memmap\n");
 		return;

arch/x86/platform/intel-mid/device_libs/Makefile

@@ -15,7 +15,7 @@ obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_msic_power_btn.o
 obj-$(subst m,y,$(CONFIG_GPIO_INTEL_PMIC)) += platform_pmic_gpio.o
 obj-$(subst m,y,$(CONFIG_INTEL_MFLD_THERMAL)) += platform_msic_thermal.o
 # SPI Devices
-obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_spidev.o
+obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_mrfld_spidev.o
 # I2C Devices
 obj-$(subst m,y,$(CONFIG_SENSORS_EMC1403)) += platform_emc1403.o
 obj-$(subst m,y,$(CONFIG_SENSORS_LIS3LV02D)) += platform_lis331.o

arch/x86/platform/intel-mid/device_libs/platform_spidev.c → arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c

@@ -11,6 +11,7 @@
  * of the License.
  */
 
+#include <linux/err.h>
 #include <linux/init.h>
 #include <linux/sfi.h>
 #include <linux/spi/pxa2xx_spi.h>
@@ -34,6 +35,9 @@ static void __init *spidev_platform_data(void *info)
 {
 	struct spi_board_info *spi_info = info;
 
+	if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+		return ERR_PTR(-ENODEV);
+
 	spi_info->mode = SPI_MODE_0;
 	spi_info->controller_data = &spidev_spi_chip;
 

block/blk-lib.c

@@ -301,13 +301,6 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	if ((sector | nr_sects) & bs_mask)
 		return -EINVAL;
 
-	if (discard) {
-		ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask,
-				BLKDEV_DISCARD_ZERO, biop);
-		if (ret == 0 || (ret && ret != -EOPNOTSUPP))
-			goto out;
-	}
-
 	ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask,
 			biop);
 	if (ret == 0 || (ret && ret != -EOPNOTSUPP))
@@ -370,6 +363,12 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	struct bio *bio = NULL;
 	struct blk_plug plug;
 
+	if (discard) {
+		if (!blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask,
+				BLKDEV_DISCARD_ZERO))
+			return 0;
+	}
+
 	blk_start_plug(&plug);
 	ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask,
 			&bio, discard);

block/blk-zoned.c

@@ -16,7 +16,7 @@
 static inline sector_t blk_zone_start(struct request_queue *q,
 				      sector_t sector)
 {
-	sector_t zone_mask = blk_queue_zone_size(q) - 1;
+	sector_t zone_mask = blk_queue_zone_sectors(q) - 1;
 
 	return sector & ~zone_mask;
 }
@@ -222,7 +222,7 @@ int blkdev_reset_zones(struct block_device *bdev,
 		return -EINVAL;
 
 	/* Check alignment (handle eventual smaller last zone) */
-	zone_sectors = blk_queue_zone_size(q);
+	zone_sectors = blk_queue_zone_sectors(q);
 	if (sector & (zone_sectors - 1))
 		return -EINVAL;
 

block/partition-generic.c

@@ -434,7 +434,7 @@ static bool part_zone_aligned(struct gendisk *disk,
 			      struct block_device *bdev,
 			      sector_t from, sector_t size)
 {
-	unsigned int zone_size = bdev_zone_size(bdev);
+	unsigned int zone_sectors = bdev_zone_sectors(bdev);
 
 	/*
 	 * If this function is called, then the disk is a zoned block device
@@ -446,7 +446,7 @@ static bool part_zone_aligned(struct gendisk *disk,
 	 * regular block devices (no zone operation) and their zone size will
 	 * be reported as 0. Allow this case.
 	 */
-	if (!zone_size)
+	if (!zone_sectors)
 		return true;
 
 	/*
@@ -455,24 +455,24 @@ static bool part_zone_aligned(struct gendisk *disk,
 	 * use it. Check the zone size too: it should be a power of 2 number
 	 * of sectors.
 	 */
-	if (WARN_ON_ONCE(!is_power_of_2(zone_size))) {
+	if (WARN_ON_ONCE(!is_power_of_2(zone_sectors))) {
 		u32 rem;
 
-		div_u64_rem(from, zone_size, &rem);
+		div_u64_rem(from, zone_sectors, &rem);
 		if (rem)
 			return false;
 		if ((from + size) < get_capacity(disk)) {
-			div_u64_rem(size, zone_size, &rem);
+			div_u64_rem(size, zone_sectors, &rem);
 			if (rem)
 				return false;
 		}
 
 	} else {
 
-		if (from & (zone_size - 1))
+		if (from & (zone_sectors - 1))
 			return false;
 		if ((from + size) < get_capacity(disk) &&
-		    (size & (zone_size - 1)))
+		    (size & (zone_sectors - 1)))
 			return false;
 
 	}

drivers/auxdisplay/Kconfig

@@ -132,9 +132,9 @@ config HT16K33
 	tristate "Holtek Ht16K33 LED controller with keyscan"
 	depends on FB && OF && I2C && INPUT
 	select FB_SYS_FOPS
-	select FB_CFB_FILLRECT
-	select FB_CFB_COPYAREA
-	select FB_CFB_IMAGEBLIT
+	select FB_SYS_FILLRECT
+	select FB_SYS_COPYAREA
+	select FB_SYS_IMAGEBLIT
 	select INPUT_MATRIXKMAP
 	select FB_BACKLIGHT
 	help

drivers/base/base.h

@@ -141,8 +141,6 @@ extern void device_unblock_probing(void);
 extern struct kset *devices_kset;
 extern void devices_kset_move_last(struct device *dev);
 
-extern struct device_attribute dev_attr_deferred_probe;
-
 #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS)
 extern void module_add_driver(struct module *mod, struct device_driver *drv);
 extern void module_remove_driver(struct device_driver *drv);

drivers/base/core.c

@@ -1060,14 +1060,8 @@ static int device_add_attrs(struct device *dev)
 			goto err_remove_dev_groups;
 	}
 
-	error = device_create_file(dev, &dev_attr_deferred_probe);
-	if (error)
-		goto err_remove_online;
-
 	return 0;
 
- err_remove_online:
-	device_remove_file(dev, &dev_attr_online);
  err_remove_dev_groups:
 	device_remove_groups(dev, dev->groups);
  err_remove_type_groups:
@@ -1085,7 +1079,6 @@ static void device_remove_attrs(struct device *dev)
 	struct class *class = dev->class;
 	const struct device_type *type = dev->type;
 
-	device_remove_file(dev, &dev_attr_deferred_probe);
 	device_remove_file(dev, &dev_attr_online);
 	device_remove_groups(dev, dev->groups);
 

drivers/base/dd.c

@@ -53,19 +53,6 @@ static LIST_HEAD(deferred_probe_pending_list);
 static LIST_HEAD(deferred_probe_active_list);
 static atomic_t deferred_trigger_count = ATOMIC_INIT(0);
 
-static ssize_t deferred_probe_show(struct device *dev,
-				   struct device_attribute *attr, char *buf)
-{
-	bool value;
-
-	mutex_lock(&deferred_probe_mutex);
-	value = !list_empty(&dev->p->deferred_probe);
-	mutex_unlock(&deferred_probe_mutex);
-
-	return sprintf(buf, "%d\n", value);
-}
-DEVICE_ATTR_RO(deferred_probe);
-
 /*
  * In some cases, like suspend to RAM or hibernation, It might be reasonable
  * to prohibit probing of devices as it could be unsafe.

drivers/block/nbd.c

@@ -1042,6 +1042,7 @@ static int __init nbd_init(void)
 		return -ENOMEM;
 
 	for (i = 0; i < nbds_max; i++) {
+		struct request_queue *q;
 		struct gendisk *disk = alloc_disk(1 << part_shift);
 		if (!disk)
 			goto out;
@@ -1067,12 +1068,13 @@ static int __init nbd_init(void)
 		 * every gendisk to have its very own request_queue struct.
 		 * These structs are big so we dynamically allocate them.
 		 */
-		disk->queue = blk_mq_init_queue(&nbd_dev[i].tag_set);
-		if (!disk->queue) {
+		q = blk_mq_init_queue(&nbd_dev[i].tag_set);
+		if (IS_ERR(q)) {
 			blk_mq_free_tag_set(&nbd_dev[i].tag_set);
 			put_disk(disk);
 			goto out;
 		}
+		disk->queue = q;
 
 		/*
 		 * Tell the block layer that we are not a rotational device

drivers/block/virtio_blk.c

@@ -56,6 +56,7 @@ struct virtblk_req {
 	struct virtio_blk_outhdr out_hdr;
 	struct virtio_scsi_inhdr in_hdr;
 	u8 status;
+	u8 sense[SCSI_SENSE_BUFFERSIZE];
 	struct scatterlist sg[];
 };
 
@@ -102,7 +103,8 @@ static int __virtblk_add_req(struct virtqueue *vq,
 	}
 
 	if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
-		sg_init_one(&sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
+		memcpy(vbr->sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
+		sg_init_one(&sense, vbr->sense, SCSI_SENSE_BUFFERSIZE);
 		sgs[num_out + num_in++] = &sense;
 		sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
 		sgs[num_out + num_in++] = &inhdr;
@@ -628,11 +630,12 @@ static int virtblk_probe(struct virtio_device *vdev)
 	if (err)
 		goto out_put_disk;
 
-	q = vblk->disk->queue = blk_mq_init_queue(&vblk->tag_set);
+	q = blk_mq_init_queue(&vblk->tag_set);
 	if (IS_ERR(q)) {
 		err = -ENOMEM;
 		goto out_free_tags;
 	}
+	vblk->disk->queue = q;
 
 	q->queuedata = vblk;
 

drivers/char/mem.c

@@ -381,9 +381,6 @@ static ssize_t read_kmem(struct file *file, char __user *buf,
 	char *kbuf; /* k-addr because vread() takes vmlist_lock rwlock */
 	int err = 0;
 
-	if (!pfn_valid(PFN_DOWN(p)))
-		return -EIO;
-
 	read = 0;
 	if (p < (unsigned long) high_memory) {
 		low_count = count;
@@ -412,6 +409,8 @@ static ssize_t read_kmem(struct file *file, char __user *buf,
 			 * by the kernel or data corruption may occur
 			 */
 			kbuf = xlate_dev_kmem_ptr((void *)p);
+			if (!virt_addr_valid(kbuf))
+				return -ENXIO;
 
 			if (copy_to_user(buf, kbuf, sz))
 				return -EFAULT;
@@ -482,6 +481,8 @@ static ssize_t do_write_kmem(unsigned long p, const char __user *buf,
 		 * corruption may occur.
 		 */
 		ptr = xlate_dev_kmem_ptr((void *)p);
+		if (!virt_addr_valid(ptr))
+			return -ENXIO;
 
 		copied = copy_from_user(ptr, buf, sz);
 		if (copied) {
@@ -512,9 +513,6 @@ static ssize_t write_kmem(struct file *file, const char __user *buf,
 	char *kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */
 	int err = 0;
 
-	if (!pfn_valid(PFN_DOWN(p)))
-		return -EIO;
-
 	if (p < (unsigned long) high_memory) {
 		unsigned long to_write = min_t(unsigned long, count,
 					       (unsigned long)high_memory - p);

drivers/char/ppdev.c

@@ -290,6 +290,7 @@ static int register_device(int minor, struct pp_struct *pp)
 	struct pardevice *pdev = NULL;
 	char *name;
 	struct pardev_cb ppdev_cb;
+	int rc = 0;
 
 	name = kasprintf(GFP_KERNEL, CHRDEV "%x", minor);
 	if (name == NULL)
@@ -298,8 +299,8 @@ static int register_device(int minor, struct pp_struct *pp)
 	port = parport_find_number(minor);
 	if (!port) {
 		pr_warn("%s: no associated port!\n", name);
-		kfree(name);
-		return -ENXIO;
+		rc = -ENXIO;
+		goto err;
 	}
 
 	memset(&ppdev_cb, 0, sizeof(ppdev_cb));
@@ -308,16 +309,18 @@ static int register_device(int minor, struct pp_struct *pp)
 	ppdev_cb.private = pp;
 	pdev = parport_register_dev_model(port, name, &ppdev_cb, minor);
 	parport_put_port(port);
-	kfree(name);
 
 	if (!pdev) {
 		pr_warn("%s: failed to register device!\n", name);
-		return -ENXIO;
+		rc = -ENXIO;
+		goto err;
 	}
 
 	pp->pdev = pdev;
 	dev_dbg(&pdev->dev, "registered pardevice\n");
-	return 0;
+err:
+	kfree(name);
+	return rc;
 }
 
 static enum ieee1284_phase init_phase(int mode)

drivers/dma/dw/Kconfig

@@ -24,5 +24,5 @@ config DW_DMAC_PCI
 	select DW_DMAC_CORE
 	help
 	  Support the Synopsys DesignWare AHB DMA controller on the
-	  platfroms that enumerate it as a PCI device. For example,
+	  platforms that enumerate it as a PCI device. For example,
 	  Intel Medfield has integrated this GPDMA controller.

drivers/dma/ioat/hw.h

@@ -64,6 +64,8 @@
 #define PCI_DEVICE_ID_INTEL_IOAT_BDX8	0x6f2e
 #define PCI_DEVICE_ID_INTEL_IOAT_BDX9	0x6f2f
 
+#define PCI_DEVICE_ID_INTEL_IOAT_SKX	0x2021
+
 #define IOAT_VER_1_2            0x12    /* Version 1.2 */
 #define IOAT_VER_2_0            0x20    /* Version 2.0 */
 #define IOAT_VER_3_0            0x30    /* Version 3.0 */

drivers/dma/ioat/init.c

@@ -106,6 +106,8 @@ static struct pci_device_id ioat_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX8) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX9) },
 
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SKX) },
+
 	/* I/OAT v3.3 platforms */
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD0) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD1) },
@@ -243,10 +245,15 @@ static bool is_bdx_ioat(struct pci_dev *pdev)
 	}
 }
 
+static inline bool is_skx_ioat(struct pci_dev *pdev)
+{
+	return (pdev->device == PCI_DEVICE_ID_INTEL_IOAT_SKX) ? true : false;
+}
+
 static bool is_xeon_cb32(struct pci_dev *pdev)
 {
 	return is_jf_ioat(pdev) || is_snb_ioat(pdev) || is_ivb_ioat(pdev) ||
-		is_hsw_ioat(pdev) || is_bdx_ioat(pdev);
+		is_hsw_ioat(pdev) || is_bdx_ioat(pdev) || is_skx_ioat(pdev);
 }
 
 bool is_bwd_ioat(struct pci_dev *pdev)
@@ -693,7 +700,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c)
 	/* doing 2 32bit writes to mmio since 1 64b write doesn't work */
 	ioat_chan->completion =
 		dma_pool_zalloc(ioat_chan->ioat_dma->completion_pool,
-				GFP_KERNEL, &ioat_chan->completion_dma);
+				GFP_NOWAIT, &ioat_chan->completion_dma);
 	if (!ioat_chan->completion)
 		return -ENOMEM;
 
@@ -703,7 +710,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c)
 	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
 
 	order = IOAT_MAX_ORDER;
-	ring = ioat_alloc_ring(c, order, GFP_KERNEL);
+	ring = ioat_alloc_ring(c, order, GFP_NOWAIT);
 	if (!ring)
 		return -ENOMEM;
 
@@ -1357,6 +1364,8 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	device->version = readb(device->reg_base + IOAT_VER_OFFSET);
 	if (device->version >= IOAT_VER_3_0) {
+		if (is_skx_ioat(pdev))
+			device->version = IOAT_VER_3_2;
 		err = ioat3_dma_probe(device, ioat_dca_enabled);
 
 		if (device->version >= IOAT_VER_3_3)

drivers/dma/omap-dma.c

@@ -938,21 +938,14 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 		d->ccr |= CCR_DST_AMODE_POSTINC;
 		if (port_window) {
 			d->ccr |= CCR_SRC_AMODE_DBLIDX;
-			d->ei = 1;
-			/*
-			 * One frame covers the port_window and by  configure
-			 * the source frame index to be -1 * (port_window - 1)
-			 * we instruct the sDMA that after a frame is processed
-			 * it should move back to the start of the window.
-			 */
-			d->fi = -(port_window_bytes - 1);
 
 			if (port_window_bytes >= 64)
-				d->csdp = CSDP_SRC_BURST_64 | CSDP_SRC_PACKED;
+				d->csdp |= CSDP_SRC_BURST_64;
 			else if (port_window_bytes >= 32)
-				d->csdp = CSDP_SRC_BURST_32 | CSDP_SRC_PACKED;
+				d->csdp |= CSDP_SRC_BURST_32;
 			else if (port_window_bytes >= 16)
-				d->csdp = CSDP_SRC_BURST_16 | CSDP_SRC_PACKED;
+				d->csdp |= CSDP_SRC_BURST_16;
+
 		} else {
 			d->ccr |= CCR_SRC_AMODE_CONSTANT;
 		}
@@ -962,13 +955,21 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 		d->ccr |= CCR_SRC_AMODE_POSTINC;
 		if (port_window) {
 			d->ccr |= CCR_DST_AMODE_DBLIDX;
+			d->ei = 1;
+			/*
+			 * One frame covers the port_window and by  configure
+			 * the source frame index to be -1 * (port_window - 1)
+			 * we instruct the sDMA that after a frame is processed
+			 * it should move back to the start of the window.
+			 */
+			d->fi = -(port_window_bytes - 1);
 
 			if (port_window_bytes >= 64)
-				d->csdp = CSDP_DST_BURST_64 | CSDP_DST_PACKED;
+				d->csdp |= CSDP_DST_BURST_64;
 			else if (port_window_bytes >= 32)
-				d->csdp = CSDP_DST_BURST_32 | CSDP_DST_PACKED;
+				d->csdp |= CSDP_DST_BURST_32;
 			else if (port_window_bytes >= 16)
-				d->csdp = CSDP_DST_BURST_16 | CSDP_DST_PACKED;
+				d->csdp |= CSDP_DST_BURST_16;
 		} else {
 			d->ccr |= CCR_DST_AMODE_CONSTANT;
 		}
@@ -1017,7 +1018,7 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 		osg->addr = sg_dma_address(sgent);
 		osg->en = en;
 		osg->fn = sg_dma_len(sgent) / frame_bytes;
-		if (port_window && dir == DMA_MEM_TO_DEV) {
+		if (port_window && dir == DMA_DEV_TO_MEM) {
 			osg->ei = 1;
 			/*
 			 * One frame covers the port_window and by  configure
@@ -1452,6 +1453,7 @@ static int omap_dma_probe(struct platform_device *pdev)
 	struct omap_dmadev *od;
 	struct resource *res;
 	int rc, i, irq;
+	u32 lch_count;
 
 	od = devm_kzalloc(&pdev->dev, sizeof(*od), GFP_KERNEL);
 	if (!od)
@@ -1494,20 +1496,31 @@ static int omap_dma_probe(struct platform_device *pdev)
 	spin_lock_init(&od->lock);
 	spin_lock_init(&od->irq_lock);
 
-	if (!pdev->dev.of_node) {
-		od->dma_requests = od->plat->dma_attr->lch_count;
-		if (unlikely(!od->dma_requests))
-			od->dma_requests = OMAP_SDMA_REQUESTS;
-	} else if (of_property_read_u32(pdev->dev.of_node, "dma-requests",
-					&od->dma_requests)) {
+	/* Number of DMA requests */
+	od->dma_requests = OMAP_SDMA_REQUESTS;
+	if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node,
+						      "dma-requests",
+						      &od->dma_requests)) {
 		dev_info(&pdev->dev,
 			 "Missing dma-requests property, using %u.\n",
 			 OMAP_SDMA_REQUESTS);
-		od->dma_requests = OMAP_SDMA_REQUESTS;
 	}
 
-	od->lch_map = devm_kcalloc(&pdev->dev, od->dma_requests,
-				   sizeof(*od->lch_map), GFP_KERNEL);
+	/* Number of available logical channels */
+	if (!pdev->dev.of_node) {
+		lch_count = od->plat->dma_attr->lch_count;
+		if (unlikely(!lch_count))
+			lch_count = OMAP_SDMA_CHANNELS;
+	} else if (of_property_read_u32(pdev->dev.of_node, "dma-channels",
+					&lch_count)) {
+		dev_info(&pdev->dev,
+			 "Missing dma-channels property, using %u.\n",
+			 OMAP_SDMA_CHANNELS);
+		lch_count = OMAP_SDMA_CHANNELS;
+	}
+
+	od->lch_map = devm_kcalloc(&pdev->dev, lch_count, sizeof(*od->lch_map),
+				   GFP_KERNEL);
 	if (!od->lch_map)
 		return -ENOMEM;
 

drivers/dma/pl330.c

@@ -448,6 +448,9 @@ struct dma_pl330_chan {
 
 	/* for cyclic capability */
 	bool cyclic;
+
+	/* for runtime pm tracking */
+	bool active;
 };
 
 struct pl330_dmac {
@@ -2033,6 +2036,7 @@ static void pl330_tasklet(unsigned long data)
 		_stop(pch->thread);
 		spin_unlock(&pch->thread->dmac->lock);
 		power_down = true;
+		pch->active = false;
 	} else {
 		/* Make sure the PL330 Channel thread is active */
 		spin_lock(&pch->thread->dmac->lock);
@@ -2052,6 +2056,7 @@ static void pl330_tasklet(unsigned long data)
 			desc->status = PREP;
 			list_move_tail(&desc->node, &pch->work_list);
 			if (power_down) {
+				pch->active = true;
 				spin_lock(&pch->thread->dmac->lock);
 				_start(pch->thread);
 				spin_unlock(&pch->thread->dmac->lock);
@@ -2166,6 +2171,7 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	unsigned long flags;
 	struct pl330_dmac *pl330 = pch->dmac;
 	LIST_HEAD(list);
+	bool power_down = false;
 
 	pm_runtime_get_sync(pl330->ddma.dev);
 	spin_lock_irqsave(&pch->lock, flags);
@@ -2176,6 +2182,8 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	pch->thread->req[0].desc = NULL;
 	pch->thread->req[1].desc = NULL;
 	pch->thread->req_running = -1;
+	power_down = pch->active;
+	pch->active = false;
 
 	/* Mark all desc done */
 	list_for_each_entry(desc, &pch->submitted_list, node) {
@@ -2193,6 +2201,8 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	list_splice_tail_init(&pch->completed_list, &pl330->desc_pool);
 	spin_unlock_irqrestore(&pch->lock, flags);
 	pm_runtime_mark_last_busy(pl330->ddma.dev);
+	if (power_down)
+		pm_runtime_put_autosuspend(pl330->ddma.dev);
 	pm_runtime_put_autosuspend(pl330->ddma.dev);
 
 	return 0;
@@ -2357,6 +2367,7 @@ static void pl330_issue_pending(struct dma_chan *chan)
 		 * updated on work_list emptiness status.
 		 */
 		WARN_ON(list_empty(&pch->submitted_list));
+		pch->active = true;
 		pm_runtime_get_sync(pch->dmac->ddma.dev);
 	}
 	list_splice_tail_init(&pch->submitted_list, &pch->work_list);

drivers/dma/sh/rcar-dmac.c

@@ -986,6 +986,7 @@ static void rcar_dmac_free_chan_resources(struct dma_chan *chan)
 {
 	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
 	struct rcar_dmac *dmac = to_rcar_dmac(chan->device);
+	struct rcar_dmac_chan_map *map = &rchan->map;
 	struct rcar_dmac_desc_page *page, *_page;
 	struct rcar_dmac_desc *desc;
 	LIST_HEAD(list);
@@ -1019,6 +1020,13 @@ static void rcar_dmac_free_chan_resources(struct dma_chan *chan)
 		free_page((unsigned long)page);
 	}
 
+	/* Remove slave mapping if present. */
+	if (map->slave.xfer_size) {
+		dma_unmap_resource(chan->device->dev, map->addr,
+				   map->slave.xfer_size, map->dir, 0);
+		map->slave.xfer_size = 0;
+	}
+
 	pm_runtime_put(chan->device->dev);
 }
 

drivers/dma/stm32-dma.c

@@ -880,7 +880,7 @@ static enum dma_status stm32_dma_tx_status(struct dma_chan *c,
 	struct virt_dma_desc *vdesc;
 	enum dma_status status;
 	unsigned long flags;
-	u32 residue;
+	u32 residue = 0;
 
 	status = dma_cookie_status(c, cookie, state);
 	if ((status == DMA_COMPLETE) || (!state))
@@ -888,16 +888,12 @@ static enum dma_status stm32_dma_tx_status(struct dma_chan *c,
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
 	vdesc = vchan_find_desc(&chan->vchan, cookie);
-	if (cookie == chan->desc->vdesc.tx.cookie) {
+	if (chan->desc && cookie == chan->desc->vdesc.tx.cookie)
 		residue = stm32_dma_desc_residue(chan, chan->desc,
 						 chan->next_sg);
-	} else if (vdesc) {
+	else if (vdesc)
 		residue = stm32_dma_desc_residue(chan,
 						 to_stm32_dma_desc(vdesc), 0);
-	} else {
-		residue = 0;
-	}
-
 	dma_set_residue(state, residue);
 
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);
@@ -972,21 +968,18 @@ static struct dma_chan *stm32_dma_of_xlate(struct of_phandle_args *dma_spec,
 	struct stm32_dma_chan *chan;
 	struct dma_chan *c;
 
-	if (dma_spec->args_count < 3)
+	if (dma_spec->args_count < 4)
 		return NULL;
 
 	cfg.channel_id = dma_spec->args[0];
 	cfg.request_line = dma_spec->args[1];
 	cfg.stream_config = dma_spec->args[2];
-	cfg.threshold = 0;
+	cfg.threshold = dma_spec->args[3];
 
 	if ((cfg.channel_id >= STM32_DMA_MAX_CHANNELS) || (cfg.request_line >=
 				STM32_DMA_MAX_REQUEST_ID))
 		return NULL;
 
-	if (dma_spec->args_count > 3)
-		cfg.threshold = dma_spec->args[3];
-
 	chan = &dmadev->chan[cfg.channel_id];
 
 	c = dma_get_slave_channel(&chan->vchan.chan);

drivers/dma/ti-dma-crossbar.c

@@ -149,6 +149,7 @@ static int ti_am335x_xbar_probe(struct platform_device *pdev)
 	match = of_match_node(ti_am335x_master_match, dma_node);
 	if (!match) {
 		dev_err(&pdev->dev, "DMA master is not supported\n");
+		of_node_put(dma_node);
 		return -EINVAL;
 	}
 
@@ -339,6 +340,7 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 	match = of_match_node(ti_dra7_master_match, dma_node);
 	if (!match) {
 		dev_err(&pdev->dev, "DMA master is not supported\n");
+		of_node_put(dma_node);
 		return -EINVAL;
 	}
 

drivers/extcon/extcon.c

@@ -453,7 +453,7 @@ int extcon_sync(struct extcon_dev *edev, unsigned int id)
 		dev_err(&edev->dev, "out of memory in extcon_set_state\n");
 		kobject_uevent(&edev->dev.kobj, KOBJ_CHANGE);
 
-		return 0;
+		return -ENOMEM;
 	}
 
 	length = name_show(&edev->dev, NULL, prop_buf);

drivers/firmware/efi/fake_mem.c

@@ -71,8 +71,7 @@ void __init efi_fake_memmap(void)
 	}
 
 	/* allocate memory for new EFI memmap */
-	new_memmap_phy = memblock_alloc(efi.memmap.desc_size * new_nr_map,
-					PAGE_SIZE);
+	new_memmap_phy = efi_memmap_alloc(new_nr_map);
 	if (!new_memmap_phy)
 		return;
 

drivers/firmware/efi/libstub/efistub.h

@@ -39,14 +39,6 @@ efi_status_t efi_file_close(void *handle);
 
 unsigned long get_dram_base(efi_system_table_t *sys_table_arg);
 
-efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
-			unsigned long orig_fdt_size,
-			void *fdt, int new_fdt_size, char *cmdline_ptr,
-			u64 initrd_addr, u64 initrd_size,
-			efi_memory_desc_t *memory_map,
-			unsigned long map_size, unsigned long desc_size,
-			u32 desc_ver);
-
 efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 					    void *handle,
 					    unsigned long *new_fdt_addr,

drivers/firmware/efi/libstub/fdt.c

@@ -16,13 +16,10 @@
 
 #include "efistub.h"
 
-efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
-			unsigned long orig_fdt_size,
-			void *fdt, int new_fdt_size, char *cmdline_ptr,
-			u64 initrd_addr, u64 initrd_size,
-			efi_memory_desc_t *memory_map,
-			unsigned long map_size, unsigned long desc_size,
-			u32 desc_ver)
+static efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
+			       unsigned long orig_fdt_size,
+			       void *fdt, int new_fdt_size, char *cmdline_ptr,
+			       u64 initrd_addr, u64 initrd_size)
 {
 	int node, num_rsv;
 	int status;
@@ -101,25 +98,23 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
 	if (status)
 		goto fdt_set_fail;
 
-	fdt_val64 = cpu_to_fdt64((u64)(unsigned long)memory_map);
+	fdt_val64 = U64_MAX; /* placeholder */
 	status = fdt_setprop(fdt, node, "linux,uefi-mmap-start",
 			     &fdt_val64,  sizeof(fdt_val64));
 	if (status)
 		goto fdt_set_fail;
 
-	fdt_val32 = cpu_to_fdt32(map_size);
+	fdt_val32 = U32_MAX; /* placeholder */
 	status = fdt_setprop(fdt, node, "linux,uefi-mmap-size",
 			     &fdt_val32,  sizeof(fdt_val32));
 	if (status)
 		goto fdt_set_fail;
 
-	fdt_val32 = cpu_to_fdt32(desc_size);
 	status = fdt_setprop(fdt, node, "linux,uefi-mmap-desc-size",
 			     &fdt_val32, sizeof(fdt_val32));
 	if (status)
 		goto fdt_set_fail;
 
-	fdt_val32 = cpu_to_fdt32(desc_ver);
 	status = fdt_setprop(fdt, node, "linux,uefi-mmap-desc-ver",
 			     &fdt_val32, sizeof(fdt_val32));
 	if (status)
@@ -148,6 +143,43 @@ fdt_set_fail:
 	return EFI_LOAD_ERROR;
 }
 
+static efi_status_t update_fdt_memmap(void *fdt, struct efi_boot_memmap *map)
+{
+	int node = fdt_path_offset(fdt, "/chosen");
+	u64 fdt_val64;
+	u32 fdt_val32;
+	int err;
+
+	if (node < 0)
+		return EFI_LOAD_ERROR;
+
+	fdt_val64 = cpu_to_fdt64((unsigned long)*map->map);
+	err = fdt_setprop_inplace(fdt, node, "linux,uefi-mmap-start",
+				  &fdt_val64, sizeof(fdt_val64));
+	if (err)
+		return EFI_LOAD_ERROR;
+
+	fdt_val32 = cpu_to_fdt32(*map->map_size);
+	err = fdt_setprop_inplace(fdt, node, "linux,uefi-mmap-size",
+				  &fdt_val32, sizeof(fdt_val32));
+	if (err)
+		return EFI_LOAD_ERROR;
+
+	fdt_val32 = cpu_to_fdt32(*map->desc_size);
+	err = fdt_setprop_inplace(fdt, node, "linux,uefi-mmap-desc-size",
+				  &fdt_val32, sizeof(fdt_val32));
+	if (err)
+		return EFI_LOAD_ERROR;
+
+	fdt_val32 = cpu_to_fdt32(*map->desc_ver);
+	err = fdt_setprop_inplace(fdt, node, "linux,uefi-mmap-desc-ver",
+				  &fdt_val32, sizeof(fdt_val32));
+	if (err)
+		return EFI_LOAD_ERROR;
+
+	return EFI_SUCCESS;
+}
+
 #ifndef EFI_FDT_ALIGN
 #define EFI_FDT_ALIGN EFI_PAGE_SIZE
 #endif
@@ -243,20 +275,10 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 			goto fail;
 		}
 
-		/*
-		 * Now that we have done our final memory allocation (and free)
-		 * we can get the memory map key  needed for
-		 * exit_boot_services().
-		 */
-		status = efi_get_memory_map(sys_table, &map);
-		if (status != EFI_SUCCESS)
-			goto fail_free_new_fdt;
-
 		status = update_fdt(sys_table,
 				    (void *)fdt_addr, fdt_size,
 				    (void *)*new_fdt_addr, new_fdt_size,
-				    cmdline_ptr, initrd_addr, initrd_size,
-				    memory_map, map_size, desc_size, desc_ver);
+				    cmdline_ptr, initrd_addr, initrd_size);
 
 		/* Succeeding the first time is the expected case. */
 		if (status == EFI_SUCCESS)
@@ -266,20 +288,16 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 			/*
 			 * We need to allocate more space for the new
 			 * device tree, so free existing buffer that is
-			 * too small.  Also free memory map, as we will need
-			 * to get new one that reflects the free/alloc we do
-			 * on the device tree buffer.
+			 * too small.
 			 */
 			efi_free(sys_table, new_fdt_size, *new_fdt_addr);
-			sys_table->boottime->free_pool(memory_map);
 			new_fdt_size += EFI_PAGE_SIZE;
 		} else {
 			pr_efi_err(sys_table, "Unable to construct new device tree.\n");
-			goto fail_free_mmap;
+			goto fail_free_new_fdt;
 		}
 	}
 
-	sys_table->boottime->free_pool(memory_map);
 	priv.runtime_map = runtime_map;
 	priv.runtime_entry_count = &runtime_entry_count;
 	status = efi_exit_boot_services(sys_table, handle, &map, &priv,
@@ -288,6 +306,16 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 	if (status == EFI_SUCCESS) {
 		efi_set_virtual_address_map_t *svam;
 
+		status = update_fdt_memmap((void *)*new_fdt_addr, &map);
+		if (status != EFI_SUCCESS) {
+			/*
+			 * The kernel won't get far without the memory map, but
+			 * may still be able to print something meaningful so
+			 * return success here.
+			 */
+			return EFI_SUCCESS;
+		}
+
 		/* Install the new virtual address map */
 		svam = sys_table->runtime->set_virtual_address_map;
 		status = svam(runtime_entry_count * desc_size, desc_size,
@@ -319,9 +347,6 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 
 	pr_efi_err(sys_table, "Exit boot services failed.\n");
 
-fail_free_mmap:
-	sys_table->boottime->free_pool(memory_map);
-
 fail_free_new_fdt:
 	efi_free(sys_table, new_fdt_size, *new_fdt_addr);
 

drivers/firmware/efi/memmap.c

@@ -9,6 +9,44 @@
 #include <linux/efi.h>
 #include <linux/io.h>
 #include <asm/early_ioremap.h>
+#include <linux/memblock.h>
+#include <linux/slab.h>
+
+static phys_addr_t __init __efi_memmap_alloc_early(unsigned long size)
+{
+	return memblock_alloc(size, 0);
+}
+
+static phys_addr_t __init __efi_memmap_alloc_late(unsigned long size)
+{
+	unsigned int order = get_order(size);
+	struct page *p = alloc_pages(GFP_KERNEL, order);
+
+	if (!p)
+		return 0;
+
+	return PFN_PHYS(page_to_pfn(p));
+}
+
+/**
+ * efi_memmap_alloc - Allocate memory for the EFI memory map
+ * @num_entries: Number of entries in the allocated map.
+ *
+ * Depending on whether mm_init() has already been invoked or not,
+ * either memblock or "normal" page allocation is used.
+ *
+ * Returns the physical address of the allocated memory map on
+ * success, zero on failure.
+ */
+phys_addr_t __init efi_memmap_alloc(unsigned int num_entries)
+{
+	unsigned long size = num_entries * efi.memmap.desc_size;
+
+	if (slab_is_available())
+		return __efi_memmap_alloc_late(size);
+
+	return __efi_memmap_alloc_early(size);
+}
 
 /**
  * __efi_memmap_init - Common code for mapping the EFI memory map

drivers/hid/hid-core.c

@@ -2496,6 +2496,7 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0002) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0003) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0004) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_PETZL, USB_DEVICE_ID_PETZL_HEADLAMP) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PHILIPS, USB_DEVICE_ID_PHILIPS_IEEE802154_DONGLE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_POWERCOM, USB_DEVICE_ID_POWERCOM_UPS) },
 #if IS_ENABLED(CONFIG_MOUSE_SYNAPTICS_USB)

drivers/hid/hid-cypress.c

@@ -39,6 +39,9 @@ static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	if (!(quirks & CP_RDESC_SWAPPED_MIN_MAX))
 		return rdesc;
 
+	if (*rsize < 4)
+		return rdesc;
+
 	for (i = 0; i < *rsize - 4; i++)
 		if (rdesc[i] == 0x29 && rdesc[i + 2] == 0x19) {
 			rdesc[i] = 0x19;

drivers/hid/hid-ids.h

@@ -816,6 +816,9 @@
 #define USB_VENDOR_ID_PETALYNX		0x18b1
 #define USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE	0x0037
 
+#define USB_VENDOR_ID_PETZL		0x2122
+#define USB_DEVICE_ID_PETZL_HEADLAMP	0x1234
+
 #define USB_VENDOR_ID_PHILIPS		0x0471
 #define USB_DEVICE_ID_PHILIPS_IEEE802154_DONGLE 0x0617
 

drivers/hid/i2c-hid/i2c-hid.c

@@ -426,6 +426,15 @@ static int i2c_hid_hwreset(struct i2c_client *client)
 	if (ret)
 		goto out_unlock;
 
+	/*
+	 * The HID over I2C specification states that if a DEVICE needs time
+	 * after the PWR_ON request, it should utilise CLOCK stretching.
+	 * However, it has been observered that the Windows driver provides a
+	 * 1ms sleep between the PWR_ON and RESET requests and that some devices
+	 * rely on this.
+	 */
+	usleep_range(1000, 5000);
+
 	i2c_hid_dbg(ihid, "resetting...\n");
 
 	ret = i2c_hid_command(client, &hid_reset_cmd, NULL, 0);

drivers/i2c/busses/i2c-piix4.c

@@ -585,10 +585,29 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr,
 		 u8 command, int size, union i2c_smbus_data *data)
 {
 	struct i2c_piix4_adapdata *adapdata = i2c_get_adapdata(adap);
+	unsigned short piix4_smba = adapdata->smba;
+	int retries = MAX_TIMEOUT;
+	int smbslvcnt;
 	u8 smba_en_lo;
 	u8 port;
 	int retval;
 
+	/* Request the SMBUS semaphore, avoid conflicts with the IMC */
+	smbslvcnt  = inb_p(SMBSLVCNT);
+	do {
+		outb_p(smbslvcnt | 0x10, SMBSLVCNT);
+
+		/* Check the semaphore status */
+		smbslvcnt  = inb_p(SMBSLVCNT);
+		if (smbslvcnt & 0x10)
+			break;
+
+		usleep_range(1000, 2000);
+	} while (--retries);
+	/* SMBus is still owned by the IMC, we give up */
+	if (!retries)
+		return -EBUSY;
+
 	mutex_lock(&piix4_mutex_sb800);
 
 	outb_p(piix4_port_sel_sb800, SB800_PIIX4_SMB_IDX);
@@ -606,6 +625,9 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr,
 
 	mutex_unlock(&piix4_mutex_sb800);
 
+	/* Release the semaphore */
+	outb_p(smbslvcnt | 0x20, SMBSLVCNT);
+
 	return retval;
 }
 

drivers/i2c/i2c-core.c

@@ -931,7 +931,10 @@ static int i2c_device_probe(struct device *dev)
 	if (!client->irq) {
 		int irq = -ENOENT;
 
-		if (dev->of_node) {
+		if (client->flags & I2C_CLIENT_HOST_NOTIFY) {
+			dev_dbg(dev, "Using Host Notify IRQ\n");
+			irq = i2c_smbus_host_notify_to_irq(client);
+		} else if (dev->of_node) {
 			irq = of_irq_get_byname(dev->of_node, "irq");
 			if (irq == -EINVAL || irq == -ENODATA)
 				irq = of_irq_get(dev->of_node, 0);
@@ -940,14 +943,7 @@ static int i2c_device_probe(struct device *dev)
 		}
 		if (irq == -EPROBE_DEFER)
 			return irq;
-		/*
-		 * ACPI and OF did not find any useful IRQ, try to see
-		 * if Host Notify can be used.
-		 */
-		if (irq < 0) {
-			dev_dbg(dev, "Using Host Notify IRQ\n");
-			irq = i2c_smbus_host_notify_to_irq(client);
-		}
+
 		if (irq < 0)
 			irq = 0;
 
@@ -1708,7 +1704,7 @@ static struct i2c_client *of_i2c_register_device(struct i2c_adapter *adap,
 
 	if (i2c_check_addr_validity(addr, info.flags)) {
 		dev_err(&adap->dev, "of_i2c: invalid addr=%x on %s\n",
-			info.addr, node->full_name);
+			addr, node->full_name);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -1716,6 +1712,9 @@ static struct i2c_client *of_i2c_register_device(struct i2c_adapter *adap,
 	info.of_node = of_node_get(node);
 	info.archdata = &dev_ad;
 
+	if (of_property_read_bool(node, "host-notify"))
+		info.flags |= I2C_CLIENT_HOST_NOTIFY;
+
 	if (of_get_property(node, "wakeup-source", NULL))
 		info.flags |= I2C_CLIENT_WAKE;
 
@@ -3633,7 +3632,7 @@ int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb)
 	int ret;
 
 	if (!client || !slave_cb) {
-		WARN(1, "insufficent data\n");
+		WARN(1, "insufficient data\n");
 		return -EINVAL;
 	}
 

drivers/i2c/i2c-dev.c

@@ -331,7 +331,7 @@ static noinline int i2cdev_ioctl_smbus(struct i2c_client *client,
 		unsigned long arg)
 {
 	struct i2c_smbus_ioctl_data data_arg;
-	union i2c_smbus_data temp;
+	union i2c_smbus_data temp = {};
 	int datasize, res;
 
 	if (copy_from_user(&data_arg,

drivers/input/joydev.c

@@ -22,7 +22,6 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
-#include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/poll.h>
 #include <linux/init.h>

drivers/input/joystick/xpad.c

@@ -1377,6 +1377,12 @@ static int xpad_init_input(struct usb_xpad *xpad)
 	input_dev->name = xpad->name;
 	input_dev->phys = xpad->phys;
 	usb_to_input_id(xpad->udev, &input_dev->id);
+
+	if (xpad->xtype == XTYPE_XBOX360W) {
+		/* x360w controllers and the receiver have different ids */
+		input_dev->id.product = 0x02a1;
+	}
+
 	input_dev->dev.parent = &xpad->intf->dev;
 
 	input_set_drvdata(input_dev, xpad);

drivers/input/misc/adxl34x-i2c.c

@@ -136,7 +136,6 @@ static const struct i2c_device_id adxl34x_id[] = {
 
 MODULE_DEVICE_TABLE(i2c, adxl34x_id);
 
-#ifdef CONFIG_OF
 static const struct of_device_id adxl34x_of_id[] = {
 	/*
 	 * The ADXL346 is backward-compatible with the ADXL345. Differences are
@@ -153,13 +152,12 @@ static const struct of_device_id adxl34x_of_id[] = {
 };
 
 MODULE_DEVICE_TABLE(of, adxl34x_of_id);
-#endif
 
 static struct i2c_driver adxl34x_driver = {
 	.driver = {
 		.name = "adxl34x",
 		.pm = &adxl34x_i2c_pm,
-		.of_match_table = of_match_ptr(adxl34x_of_id),
+		.of_match_table = adxl34x_of_id,
 	},
 	.probe    = adxl34x_i2c_probe,
 	.remove   = adxl34x_i2c_remove,

drivers/input/mouse/alps.h

@@ -114,7 +114,7 @@ enum SS4_PACKET_ID {
 				 (_b[1] & 0x7F)		\
 				)
 
-#define SS4_TS_Y_V2(_b)		(s8)(				\
+#define SS4_TS_Y_V2(_b)		-(s8)(				\
 				 ((_b[3] & 0x01) << 7) |	\
 				 (_b[2] & 0x7F)		\
 				)

drivers/input/mouse/synaptics_i2c.c

@@ -29,7 +29,7 @@
  * after soft reset, we should wait for 1 ms
  * before the device becomes operational
  */
-#define SOFT_RESET_DELAY_MS	3
+#define SOFT_RESET_DELAY_US	3000
 /* and after hard reset, we should wait for max 500ms */
 #define HARD_RESET_DELAY_MS	500
 
@@ -311,7 +311,7 @@ static int synaptics_i2c_reset_config(struct i2c_client *client)
 	if (ret) {
 		dev_err(&client->dev, "Unable to reset device\n");
 	} else {
-		msleep(SOFT_RESET_DELAY_MS);
+		usleep_range(SOFT_RESET_DELAY_US, SOFT_RESET_DELAY_US + 100);
 		ret = synaptics_i2c_config(client);
 		if (ret)
 			dev_err(&client->dev, "Unable to config device\n");

drivers/input/rmi4/Kconfig

@@ -41,7 +41,8 @@ config RMI4_SMB
 
 config RMI4_F03
         bool "RMI4 Function 03 (PS2 Guest)"
-        depends on RMI4_CORE && SERIO
+	depends on RMI4_CORE
+	depends on SERIO=y || RMI4_CORE=SERIO
         help
           Say Y here if you want to add support for RMI4 function 03.
 

drivers/input/serio/i8042-x86ia64io.h

@@ -211,6 +211,12 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = {
 			DMI_MATCH(DMI_PRODUCT_VERSION, "Rev 1"),
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C15B"),
+		},
+	},
 	{ }
 };
 

drivers/input/touchscreen/elants_i2c.c

@@ -914,9 +914,9 @@ static irqreturn_t elants_i2c_irq(int irq, void *_dev)
 
 		case QUEUE_HEADER_NORMAL:
 			report_count = ts->buf[FW_HDR_COUNT];
-			if (report_count > 3) {
+			if (report_count == 0 || report_count > 3) {
 				dev_err(&client->dev,
-					"too large report count: %*ph\n",
+					"bad report count: %*ph\n",
 					HEADER_SIZE, ts->buf);
 				break;
 			}

drivers/md/md.h

@@ -212,6 +212,7 @@ extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 				int is_new);
 struct md_cluster_info;
 
+/* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */
 enum mddev_flags {
 	MD_ARRAY_FIRST_USE,	/* First use of array, needs initialization */
 	MD_CLOSING,		/* If set, we are closing the array, do not open
@@ -702,4 +703,11 @@ static inline int mddev_is_clustered(struct mddev *mddev)
 {
 	return mddev->cluster_info && mddev->bitmap_info.nodes > 1;
 }
+
+/* clear unsupported mddev_flags */
+static inline void mddev_clear_unsupported_flags(struct mddev *mddev,
+	unsigned long unsupported_flags)
+{
+	mddev->flags &= ~unsupported_flags;
+}
 #endif /* _MD_MD_H */

drivers/md/raid0.c

@@ -26,6 +26,11 @@
 #include "raid0.h"
 #include "raid5.h"
 
+#define UNSUPPORTED_MDDEV_FLAGS		\
+	((1L << MD_HAS_JOURNAL) |	\
+	 (1L << MD_JOURNAL_CLEAN) |	\
+	 (1L << MD_FAILFAST_SUPPORTED))
+
 static int raid0_congested(struct mddev *mddev, int bits)
 {
 	struct r0conf *conf = mddev->private;
@@ -539,8 +544,7 @@ static void *raid0_takeover_raid45(struct mddev *mddev)
 	mddev->delta_disks = -1;
 	/* make sure it will be not marked as dirty */
 	mddev->recovery_cp = MaxSector;
-	clear_bit(MD_HAS_JOURNAL, &mddev->flags);
-	clear_bit(MD_JOURNAL_CLEAN, &mddev->flags);
+	mddev_clear_unsupported_flags(mddev, UNSUPPORTED_MDDEV_FLAGS);
 
 	create_strip_zones(mddev, &priv_conf);
 
@@ -583,7 +587,7 @@ static void *raid0_takeover_raid10(struct mddev *mddev)
 	mddev->degraded = 0;
 	/* make sure it will be not marked as dirty */
 	mddev->recovery_cp = MaxSector;
-	clear_bit(MD_FAILFAST_SUPPORTED, &mddev->flags);
+	mddev_clear_unsupported_flags(mddev, UNSUPPORTED_MDDEV_FLAGS);
 
 	create_strip_zones(mddev, &priv_conf);
 	return priv_conf;
@@ -626,7 +630,7 @@ static void *raid0_takeover_raid1(struct mddev *mddev)
 	mddev->raid_disks = 1;
 	/* make sure it will be not marked as dirty */
 	mddev->recovery_cp = MaxSector;
-	clear_bit(MD_FAILFAST_SUPPORTED, &mddev->flags);
+	mddev_clear_unsupported_flags(mddev, UNSUPPORTED_MDDEV_FLAGS);
 
 	create_strip_zones(mddev, &priv_conf);
 	return priv_conf;

drivers/md/raid1.c

@@ -42,6 +42,10 @@
 #include "raid1.h"
 #include "bitmap.h"
 
+#define UNSUPPORTED_MDDEV_FLAGS		\
+	((1L << MD_HAS_JOURNAL) |	\
+	 (1L << MD_JOURNAL_CLEAN))
+
 /*
  * Number of guaranteed r1bios in case of extreme VM load:
  */
@@ -1066,17 +1070,107 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	kfree(plug);
 }
 
-static void raid1_make_request(struct mddev *mddev, struct bio * bio)
+static void raid1_read_request(struct mddev *mddev, struct bio *bio,
+				 struct r1bio *r1_bio)
 {
 	struct r1conf *conf = mddev->private;
 	struct raid1_info *mirror;
-	struct r1bio *r1_bio;
 	struct bio *read_bio;
+	struct bitmap *bitmap = mddev->bitmap;
+	const int op = bio_op(bio);
+	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
+	int sectors_handled;
+	int max_sectors;
+	int rdisk;
+
+	wait_barrier(conf, bio);
+
+read_again:
+	rdisk = read_balance(conf, r1_bio, &max_sectors);
+
+	if (rdisk < 0) {
+		/* couldn't find anywhere to read from */
+		raid_end_bio_io(r1_bio);
+		return;
+	}
+	mirror = conf->mirrors + rdisk;
+
+	if (test_bit(WriteMostly, &mirror->rdev->flags) &&
+	    bitmap) {
+		/*
+		 * Reading from a write-mostly device must take care not to
+		 * over-take any writes that are 'behind'
+		 */
+		raid1_log(mddev, "wait behind writes");
+		wait_event(bitmap->behind_wait,
+			   atomic_read(&bitmap->behind_writes) == 0);
+	}
+	r1_bio->read_disk = rdisk;
+	r1_bio->start_next_window = 0;
+
+	read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+	bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector,
+		 max_sectors);
+
+	r1_bio->bios[rdisk] = read_bio;
+
+	read_bio->bi_iter.bi_sector = r1_bio->sector +
+		mirror->rdev->data_offset;
+	read_bio->bi_bdev = mirror->rdev->bdev;
+	read_bio->bi_end_io = raid1_end_read_request;
+	bio_set_op_attrs(read_bio, op, do_sync);
+	if (test_bit(FailFast, &mirror->rdev->flags) &&
+	    test_bit(R1BIO_FailFast, &r1_bio->state))
+	        read_bio->bi_opf |= MD_FAILFAST;
+	read_bio->bi_private = r1_bio;
+
+	if (mddev->gendisk)
+	        trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
+	                              read_bio, disk_devt(mddev->gendisk),
+	                              r1_bio->sector);
+
+	if (max_sectors < r1_bio->sectors) {
+		/*
+		 * could not read all from this device, so we will need another
+		 * r1_bio.
+		 */
+		sectors_handled = (r1_bio->sector + max_sectors
+				   - bio->bi_iter.bi_sector);
+		r1_bio->sectors = max_sectors;
+		spin_lock_irq(&conf->device_lock);
+		if (bio->bi_phys_segments == 0)
+			bio->bi_phys_segments = 2;
+		else
+			bio->bi_phys_segments++;
+		spin_unlock_irq(&conf->device_lock);
+
+		/*
+		 * Cannot call generic_make_request directly as that will be
+		 * queued in __make_request and subsequent mempool_alloc might
+		 * block waiting for it.  So hand bio over to raid1d.
+		 */
+		reschedule_retry(r1_bio);
+
+		r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
+
+		r1_bio->master_bio = bio;
+		r1_bio->sectors = bio_sectors(bio) - sectors_handled;
+		r1_bio->state = 0;
+		r1_bio->mddev = mddev;
+		r1_bio->sector = bio->bi_iter.bi_sector + sectors_handled;
+		goto read_again;
+	} else
+		generic_make_request(read_bio);
+}
+
+static void raid1_write_request(struct mddev *mddev, struct bio *bio,
+				struct r1bio *r1_bio)
+{
+	struct r1conf *conf = mddev->private;
 	int i, disks;
-	struct bitmap *bitmap;
+	struct bitmap *bitmap = mddev->bitmap;
 	unsigned long flags;
 	const int op = bio_op(bio);
-	const int rw = bio_data_dir(bio);
 	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
 	const unsigned long do_flush_fua = (bio->bi_opf &
 						(REQ_PREFLUSH | REQ_FUA));
@@ -1096,15 +1190,15 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio)
 
 	md_write_start(mddev, bio); /* wait on superblock update early */
 
-	if (bio_data_dir(bio) == WRITE &&
-	    ((bio_end_sector(bio) > mddev->suspend_lo &&
+	if ((bio_end_sector(bio) > mddev->suspend_lo &&
 	    bio->bi_iter.bi_sector < mddev->suspend_hi) ||
 	    (mddev_is_clustered(mddev) &&
 	     md_cluster_ops->area_resyncing(mddev, WRITE,
-		     bio->bi_iter.bi_sector, bio_end_sector(bio))))) {
-		/* As the suspend_* range is controlled by
-		 * userspace, we want an interruptible
-		 * wait.
+		     bio->bi_iter.bi_sector, bio_end_sector(bio)))) {
+
+		/*
+		 * As the suspend_* range is controlled by userspace, we want
+		 * an interruptible wait.
 		 */
 		DEFINE_WAIT(w);
 		for (;;) {
@@ -1115,128 +1209,15 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio)
 			    bio->bi_iter.bi_sector >= mddev->suspend_hi ||
 			    (mddev_is_clustered(mddev) &&
 			     !md_cluster_ops->area_resyncing(mddev, WRITE,
-				     bio->bi_iter.bi_sector, bio_end_sector(bio))))
+				     bio->bi_iter.bi_sector,
+				     bio_end_sector(bio))))
 				break;
 			schedule();
 		}
 		finish_wait(&conf->wait_barrier, &w);
 	}
-
 	start_next_window = wait_barrier(conf, bio);
 
-	bitmap = mddev->bitmap;
-
-	/*
-	 * make_request() can abort the operation when read-ahead is being
-	 * used and no empty request is available.
-	 *
-	 */
-	r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
-
-	r1_bio->master_bio = bio;
-	r1_bio->sectors = bio_sectors(bio);
-	r1_bio->state = 0;
-	r1_bio->mddev = mddev;
-	r1_bio->sector = bio->bi_iter.bi_sector;
-
-	/* We might need to issue multiple reads to different
-	 * devices if there are bad blocks around, so we keep
-	 * track of the number of reads in bio->bi_phys_segments.
-	 * If this is 0, there is only one r1_bio and no locking
-	 * will be needed when requests complete.  If it is
-	 * non-zero, then it is the number of not-completed requests.
-	 */
-	bio->bi_phys_segments = 0;
-	bio_clear_flag(bio, BIO_SEG_VALID);
-
-	if (rw == READ) {
-		/*
-		 * read balancing logic:
-		 */
-		int rdisk;
-
-read_again:
-		rdisk = read_balance(conf, r1_bio, &max_sectors);
-
-		if (rdisk < 0) {
-			/* couldn't find anywhere to read from */
-			raid_end_bio_io(r1_bio);
-			return;
-		}
-		mirror = conf->mirrors + rdisk;
-
-		if (test_bit(WriteMostly, &mirror->rdev->flags) &&
-		    bitmap) {
-			/* Reading from a write-mostly device must
-			 * take care not to over-take any writes
-			 * that are 'behind'
-			 */
-			raid1_log(mddev, "wait behind writes");
-			wait_event(bitmap->behind_wait,
-				   atomic_read(&bitmap->behind_writes) == 0);
-		}
-		r1_bio->read_disk = rdisk;
-		r1_bio->start_next_window = 0;
-
-		read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector,
-			 max_sectors);
-
-		r1_bio->bios[rdisk] = read_bio;
-
-		read_bio->bi_iter.bi_sector = r1_bio->sector +
-			mirror->rdev->data_offset;
-		read_bio->bi_bdev = mirror->rdev->bdev;
-		read_bio->bi_end_io = raid1_end_read_request;
-		bio_set_op_attrs(read_bio, op, do_sync);
-		if (test_bit(FailFast, &mirror->rdev->flags) &&
-		    test_bit(R1BIO_FailFast, &r1_bio->state))
-			read_bio->bi_opf |= MD_FAILFAST;
-		read_bio->bi_private = r1_bio;
-
-		if (mddev->gendisk)
-			trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
-					      read_bio, disk_devt(mddev->gendisk),
-					      r1_bio->sector);
-
-		if (max_sectors < r1_bio->sectors) {
-			/* could not read all from this device, so we will
-			 * need another r1_bio.
-			 */
-
-			sectors_handled = (r1_bio->sector + max_sectors
-					   - bio->bi_iter.bi_sector);
-			r1_bio->sectors = max_sectors;
-			spin_lock_irq(&conf->device_lock);
-			if (bio->bi_phys_segments == 0)
-				bio->bi_phys_segments = 2;
-			else
-				bio->bi_phys_segments++;
-			spin_unlock_irq(&conf->device_lock);
-			/* Cannot call generic_make_request directly
-			 * as that will be queued in __make_request
-			 * and subsequent mempool_alloc might block waiting
-			 * for it.  So hand bio over to raid1d.
-			 */
-			reschedule_retry(r1_bio);
-
-			r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
-
-			r1_bio->master_bio = bio;
-			r1_bio->sectors = bio_sectors(bio) - sectors_handled;
-			r1_bio->state = 0;
-			r1_bio->mddev = mddev;
-			r1_bio->sector = bio->bi_iter.bi_sector +
-				sectors_handled;
-			goto read_again;
-		} else
-			generic_make_request(read_bio);
-		return;
-	}
-
-	/*
-	 * WRITE:
-	 */
 	if (conf->pending_count >= max_queued_requests) {
 		md_wakeup_thread(mddev->thread);
 		raid1_log(mddev, "wait queued");
@@ -1280,8 +1261,7 @@ read_again:
 			int bad_sectors;
 			int is_bad;
 
-			is_bad = is_badblock(rdev, r1_bio->sector,
-					     max_sectors,
+			is_bad = is_badblock(rdev, r1_bio->sector, max_sectors,
 					     &first_bad, &bad_sectors);
 			if (is_bad < 0) {
 				/* mustn't write here until the bad block is
@@ -1370,7 +1350,8 @@ read_again:
 			continue;
 
 		mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		bio_trim(mbio, r1_bio->sector - bio->bi_iter.bi_sector, max_sectors);
+		bio_trim(mbio, r1_bio->sector - bio->bi_iter.bi_sector,
+			 max_sectors);
 
 		if (first_clone) {
 			/* do behind I/O ?
@@ -1464,6 +1445,40 @@ read_again:
 	wake_up(&conf->wait_barrier);
 }
 
+static void raid1_make_request(struct mddev *mddev, struct bio *bio)
+{
+	struct r1conf *conf = mddev->private;
+	struct r1bio *r1_bio;
+
+	/*
+	 * make_request() can abort the operation when read-ahead is being
+	 * used and no empty request is available.
+	 *
+	 */
+	r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
+
+	r1_bio->master_bio = bio;
+	r1_bio->sectors = bio_sectors(bio);
+	r1_bio->state = 0;
+	r1_bio->mddev = mddev;
+	r1_bio->sector = bio->bi_iter.bi_sector;
+
+	/*
+	 * We might need to issue multiple reads to different devices if there
+	 * are bad blocks around, so we keep track of the number of reads in
+	 * bio->bi_phys_segments.  If this is 0, there is only one r1_bio and
+	 * no locking will be needed when requests complete.  If it is
+	 * non-zero, then it is the number of not-completed requests.
+	 */
+	bio->bi_phys_segments = 0;
+	bio_clear_flag(bio, BIO_SEG_VALID);
+
+	if (bio_data_dir(bio) == READ)
+		raid1_read_request(mddev, bio, r1_bio);
+	else
+		raid1_write_request(mddev, bio, r1_bio);
+}
+
 static void raid1_status(struct seq_file *seq, struct mddev *mddev)
 {
 	struct r1conf *conf = mddev->private;
@@ -3246,8 +3261,8 @@ static void *raid1_takeover(struct mddev *mddev)
 		if (!IS_ERR(conf)) {
 			/* Array must appear to be quiesced */
 			conf->array_frozen = 1;
-			clear_bit(MD_HAS_JOURNAL, &mddev->flags);
-			clear_bit(MD_JOURNAL_CLEAN, &mddev->flags);
+			mddev_clear_unsupported_flags(mddev,
+				UNSUPPORTED_MDDEV_FLAGS);
 		}
 		return conf;
 	}

drivers/md/raid10.c

@@ -1087,23 +1087,122 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	kfree(plug);
 }
 
-static void __make_request(struct mddev *mddev, struct bio *bio)
+static void raid10_read_request(struct mddev *mddev, struct bio *bio,
+				struct r10bio *r10_bio)
 {
 	struct r10conf *conf = mddev->private;
-	struct r10bio *r10_bio;
 	struct bio *read_bio;
+	const int op = bio_op(bio);
+	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
+	int sectors_handled;
+	int max_sectors;
+	sector_t sectors;
+	struct md_rdev *rdev;
+	int slot;
+
+	/*
+	 * Register the new request and wait if the reconstruction
+	 * thread has put up a bar for new requests.
+	 * Continue immediately if no resync is active currently.
+	 */
+	wait_barrier(conf);
+
+	sectors = bio_sectors(bio);
+	while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+	    bio->bi_iter.bi_sector < conf->reshape_progress &&
+	    bio->bi_iter.bi_sector + sectors > conf->reshape_progress) {
+		/*
+		 * IO spans the reshape position.  Need to wait for reshape to
+		 * pass
+		 */
+		raid10_log(conf->mddev, "wait reshape");
+		allow_barrier(conf);
+		wait_event(conf->wait_barrier,
+			   conf->reshape_progress <= bio->bi_iter.bi_sector ||
+			   conf->reshape_progress >= bio->bi_iter.bi_sector +
+			   sectors);
+		wait_barrier(conf);
+	}
+
+read_again:
+	rdev = read_balance(conf, r10_bio, &max_sectors);
+	if (!rdev) {
+		raid_end_bio_io(r10_bio);
+		return;
+	}
+	slot = r10_bio->read_slot;
+
+	read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+	bio_trim(read_bio, r10_bio->sector - bio->bi_iter.bi_sector,
+		 max_sectors);
+
+	r10_bio->devs[slot].bio = read_bio;
+	r10_bio->devs[slot].rdev = rdev;
+
+	read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr +
+		choose_data_offset(r10_bio, rdev);
+	read_bio->bi_bdev = rdev->bdev;
+	read_bio->bi_end_io = raid10_end_read_request;
+	bio_set_op_attrs(read_bio, op, do_sync);
+	if (test_bit(FailFast, &rdev->flags) &&
+	    test_bit(R10BIO_FailFast, &r10_bio->state))
+	        read_bio->bi_opf |= MD_FAILFAST;
+	read_bio->bi_private = r10_bio;
+
+	if (mddev->gendisk)
+	        trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
+	                              read_bio, disk_devt(mddev->gendisk),
+	                              r10_bio->sector);
+	if (max_sectors < r10_bio->sectors) {
+		/*
+		 * Could not read all from this device, so we will need another
+		 * r10_bio.
+		 */
+		sectors_handled = (r10_bio->sector + max_sectors
+				   - bio->bi_iter.bi_sector);
+		r10_bio->sectors = max_sectors;
+		spin_lock_irq(&conf->device_lock);
+		if (bio->bi_phys_segments == 0)
+			bio->bi_phys_segments = 2;
+		else
+			bio->bi_phys_segments++;
+		spin_unlock_irq(&conf->device_lock);
+		/*
+		 * Cannot call generic_make_request directly as that will be
+		 * queued in __generic_make_request and subsequent
+		 * mempool_alloc might block waiting for it.  so hand bio over
+		 * to raid10d.
+		 */
+		reschedule_retry(r10_bio);
+
+		r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
+
+		r10_bio->master_bio = bio;
+		r10_bio->sectors = bio_sectors(bio) - sectors_handled;
+		r10_bio->state = 0;
+		r10_bio->mddev = mddev;
+		r10_bio->sector = bio->bi_iter.bi_sector + sectors_handled;
+		goto read_again;
+	} else
+		generic_make_request(read_bio);
+	return;
+}
+
+static void raid10_write_request(struct mddev *mddev, struct bio *bio,
+				 struct r10bio *r10_bio)
+{
+	struct r10conf *conf = mddev->private;
 	int i;
 	const int op = bio_op(bio);
-	const int rw = bio_data_dir(bio);
 	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
 	const unsigned long do_fua = (bio->bi_opf & REQ_FUA);
 	unsigned long flags;
 	struct md_rdev *blocked_rdev;
 	struct blk_plug_cb *cb;
 	struct raid10_plug_cb *plug = NULL;
+	sector_t sectors;
 	int sectors_handled;
 	int max_sectors;
-	int sectors;
 
 	md_write_start(mddev, bio);
 
@@ -1118,8 +1217,9 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 	while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    bio->bi_iter.bi_sector < conf->reshape_progress &&
 	    bio->bi_iter.bi_sector + sectors > conf->reshape_progress) {
-		/* IO spans the reshape position.  Need to wait for
-		 * reshape to pass
+		/*
+		 * IO spans the reshape position.  Need to wait for reshape to
+		 * pass
 		 */
 		raid10_log(conf->mddev, "wait reshape");
 		allow_barrier(conf);
@@ -1129,8 +1229,8 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 			   sectors);
 		wait_barrier(conf);
 	}
+
 	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
-	    bio_data_dir(bio) == WRITE &&
 	    (mddev->reshape_backwards
 	     ? (bio->bi_iter.bi_sector < conf->reshape_safe &&
 		bio->bi_iter.bi_sector + sectors > conf->reshape_progress)
@@ -1148,98 +1248,6 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 		conf->reshape_safe = mddev->reshape_position;
 	}
 
-	r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
-
-	r10_bio->master_bio = bio;
-	r10_bio->sectors = sectors;
-
-	r10_bio->mddev = mddev;
-	r10_bio->sector = bio->bi_iter.bi_sector;
-	r10_bio->state = 0;
-
-	/* We might need to issue multiple reads to different
-	 * devices if there are bad blocks around, so we keep
-	 * track of the number of reads in bio->bi_phys_segments.
-	 * If this is 0, there is only one r10_bio and no locking
-	 * will be needed when the request completes.  If it is
-	 * non-zero, then it is the number of not-completed requests.
-	 */
-	bio->bi_phys_segments = 0;
-	bio_clear_flag(bio, BIO_SEG_VALID);
-
-	if (rw == READ) {
-		/*
-		 * read balancing logic:
-		 */
-		struct md_rdev *rdev;
-		int slot;
-
-read_again:
-		rdev = read_balance(conf, r10_bio, &max_sectors);
-		if (!rdev) {
-			raid_end_bio_io(r10_bio);
-			return;
-		}
-		slot = r10_bio->read_slot;
-
-		read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		bio_trim(read_bio, r10_bio->sector - bio->bi_iter.bi_sector,
-			 max_sectors);
-
-		r10_bio->devs[slot].bio = read_bio;
-		r10_bio->devs[slot].rdev = rdev;
-
-		read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr +
-			choose_data_offset(r10_bio, rdev);
-		read_bio->bi_bdev = rdev->bdev;
-		read_bio->bi_end_io = raid10_end_read_request;
-		bio_set_op_attrs(read_bio, op, do_sync);
-		if (test_bit(FailFast, &rdev->flags) &&
-		    test_bit(R10BIO_FailFast, &r10_bio->state))
-			read_bio->bi_opf |= MD_FAILFAST;
-		read_bio->bi_private = r10_bio;
-
-		if (mddev->gendisk)
-			trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
-					      read_bio, disk_devt(mddev->gendisk),
-					      r10_bio->sector);
-		if (max_sectors < r10_bio->sectors) {
-			/* Could not read all from this device, so we will
-			 * need another r10_bio.
-			 */
-			sectors_handled = (r10_bio->sector + max_sectors
-					   - bio->bi_iter.bi_sector);
-			r10_bio->sectors = max_sectors;
-			spin_lock_irq(&conf->device_lock);
-			if (bio->bi_phys_segments == 0)
-				bio->bi_phys_segments = 2;
-			else
-				bio->bi_phys_segments++;
-			spin_unlock_irq(&conf->device_lock);
-			/* Cannot call generic_make_request directly
-			 * as that will be queued in __generic_make_request
-			 * and subsequent mempool_alloc might block
-			 * waiting for it.  so hand bio over to raid10d.
-			 */
-			reschedule_retry(r10_bio);
-
-			r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
-
-			r10_bio->master_bio = bio;
-			r10_bio->sectors = bio_sectors(bio) - sectors_handled;
-			r10_bio->state = 0;
-			r10_bio->mddev = mddev;
-			r10_bio->sector = bio->bi_iter.bi_sector +
-				sectors_handled;
-			goto read_again;
-		} else
-			generic_make_request(read_bio);
-		return;
-	}
-
-	/*
-	 * WRITE:
-	 */
 	if (conf->pending_count >= max_queued_requests) {
 		md_wakeup_thread(mddev->thread);
 		raid10_log(mddev, "wait queued");
@@ -1300,8 +1308,7 @@ retry_write:
 			int bad_sectors;
 			int is_bad;
 
-			is_bad = is_badblock(rdev, dev_sector,
-					     max_sectors,
+			is_bad = is_badblock(rdev, dev_sector, max_sectors,
 					     &first_bad, &bad_sectors);
 			if (is_bad < 0) {
 				/* Mustn't write here until the bad block
@@ -1405,8 +1412,7 @@ retry_write:
 			r10_bio->devs[i].bio = mbio;
 
 			mbio->bi_iter.bi_sector	= (r10_bio->devs[i].addr+
-					   choose_data_offset(r10_bio,
-							      rdev));
+					   choose_data_offset(r10_bio, rdev));
 			mbio->bi_bdev = rdev->bdev;
 			mbio->bi_end_io	= raid10_end_write_request;
 			bio_set_op_attrs(mbio, op, do_sync | do_fua);
@@ -1457,8 +1463,7 @@ retry_write:
 			r10_bio->devs[i].repl_bio = mbio;
 
 			mbio->bi_iter.bi_sector	= (r10_bio->devs[i].addr +
-					   choose_data_offset(
-						   r10_bio, rdev));
+					   choose_data_offset(r10_bio, rdev));
 			mbio->bi_bdev = rdev->bdev;
 			mbio->bi_end_io	= raid10_end_write_request;
 			bio_set_op_attrs(mbio, op, do_sync | do_fua);
@@ -1503,6 +1508,36 @@ retry_write:
 	one_write_done(r10_bio);
 }
 
+static void __make_request(struct mddev *mddev, struct bio *bio)
+{
+	struct r10conf *conf = mddev->private;
+	struct r10bio *r10_bio;
+
+	r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
+
+	r10_bio->master_bio = bio;
+	r10_bio->sectors = bio_sectors(bio);
+
+	r10_bio->mddev = mddev;
+	r10_bio->sector = bio->bi_iter.bi_sector;
+	r10_bio->state = 0;
+
+	/*
+	 * We might need to issue multiple reads to different devices if there
+	 * are bad blocks around, so we keep track of the number of reads in
+	 * bio->bi_phys_segments.  If this is 0, there is only one r10_bio and
+	 * no locking will be needed when the request completes.  If it is
+	 * non-zero, then it is the number of not-completed requests.
+	 */
+	bio->bi_phys_segments = 0;
+	bio_clear_flag(bio, BIO_SEG_VALID);
+
+	if (bio_data_dir(bio) == READ)
+		raid10_read_request(mddev, bio, r10_bio);
+	else
+		raid10_write_request(mddev, bio, r10_bio);
+}
+
 static void raid10_make_request(struct mddev *mddev, struct bio *bio)
 {
 	struct r10conf *conf = mddev->private;

drivers/md/raid5-cache.c

@@ -1682,8 +1682,7 @@ out:
 
 static struct stripe_head *
 r5c_recovery_alloc_stripe(struct r5conf *conf,
-			  sector_t stripe_sect,
-			  sector_t log_start)
+			  sector_t stripe_sect)
 {
 	struct stripe_head *sh;
 
@@ -1692,7 +1691,6 @@ r5c_recovery_alloc_stripe(struct r5conf *conf,
 		return NULL;  /* no more stripe available */
 
 	r5l_recovery_reset_stripe(sh);
-	sh->log_start = log_start;
 
 	return sh;
 }
@@ -1862,7 +1860,7 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log,
 						stripe_sect);
 
 		if (!sh) {
-			sh = r5c_recovery_alloc_stripe(conf, stripe_sect, ctx->pos);
+			sh = r5c_recovery_alloc_stripe(conf, stripe_sect);
 			/*
 			 * cannot get stripe from raid5_get_active_stripe
 			 * try replay some stripes
@@ -1871,7 +1869,7 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log,
 				r5c_recovery_replay_stripes(
 					cached_stripe_list, ctx);
 				sh = r5c_recovery_alloc_stripe(
-					conf, stripe_sect, ctx->pos);
+					conf, stripe_sect);
 			}
 			if (!sh) {
 				pr_debug("md/raid:%s: Increasing stripe cache size to %d to recovery data on journal.\n",
@@ -1879,8 +1877,8 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log,
 					conf->min_nr_stripes * 2);
 				raid5_set_cache_size(mddev,
 						     conf->min_nr_stripes * 2);
-				sh = r5c_recovery_alloc_stripe(
-					conf, stripe_sect, ctx->pos);
+				sh = r5c_recovery_alloc_stripe(conf,
+							       stripe_sect);
 			}
 			if (!sh) {
 				pr_err("md/raid:%s: Cannot get enough stripes due to memory pressure. Recovery failed.\n",
@@ -1894,7 +1892,6 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log,
 			if (!test_bit(STRIPE_R5C_CACHING, &sh->state) &&
 			    test_bit(R5_Wantwrite, &sh->dev[sh->pd_idx].flags)) {
 				r5l_recovery_replay_one_stripe(conf, sh, ctx);
-				sh->log_start = ctx->pos;
 				list_move_tail(&sh->lru, cached_stripe_list);
 			}
 			r5l_recovery_load_data(log, sh, ctx, payload,
@@ -1933,8 +1930,6 @@ static void r5c_recovery_load_one_stripe(struct r5l_log *log,
 			set_bit(R5_UPTODATE, &dev->flags);
 		}
 	}
-	list_add_tail(&sh->r5c, &log->stripe_in_journal_list);
-	atomic_inc(&log->stripe_in_journal_count);
 }
 
 /*
@@ -2070,6 +2065,7 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
 	struct stripe_head *sh, *next;
 	struct mddev *mddev = log->rdev->mddev;
 	struct page *page;
+	sector_t next_checkpoint = MaxSector;
 
 	page = alloc_page(GFP_KERNEL);
 	if (!page) {
@@ -2078,6 +2074,8 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
 		return -ENOMEM;
 	}
 
+	WARN_ON(list_empty(&ctx->cached_list));
+
 	list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) {
 		struct r5l_meta_block *mb;
 		int i;
@@ -2123,12 +2121,15 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
 		sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page,
 			     REQ_OP_WRITE, REQ_FUA, false);
 		sh->log_start = ctx->pos;
+		list_add_tail(&sh->r5c, &log->stripe_in_journal_list);
+		atomic_inc(&log->stripe_in_journal_count);
 		ctx->pos = write_pos;
 		ctx->seq += 1;
-
+		next_checkpoint = sh->log_start;
 		list_del_init(&sh->lru);
 		raid5_release_stripe(sh);
 	}
+	log->next_checkpoint = next_checkpoint;
 	__free_page(page);
 	return 0;
 }
@@ -2139,7 +2140,6 @@ static int r5l_recovery_log(struct r5l_log *log)
 	struct r5l_recovery_ctx ctx;
 	int ret;
 	sector_t pos;
-	struct stripe_head *sh;
 
 	ctx.pos = log->last_checkpoint;
 	ctx.seq = log->last_cp_seq;
@@ -2164,16 +2164,13 @@ static int r5l_recovery_log(struct r5l_log *log)
 		log->next_checkpoint = ctx.pos;
 		r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++);
 		ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
-	} else {
-		sh = list_last_entry(&ctx.cached_list, struct stripe_head, lru);
-		log->next_checkpoint = sh->log_start;
 	}
 
 	if ((ctx.data_only_stripes == 0) && (ctx.data_parity_stripes == 0))
 		pr_debug("md/raid:%s: starting from clean shutdown\n",
 			 mdname(mddev));
 	else {
-		pr_debug("md/raid:%s: recoverying %d data-only stripes and %d data-parity stripes\n",
+		pr_debug("md/raid:%s: recovering %d data-only stripes and %d data-parity stripes\n",
 			 mdname(mddev), ctx.data_only_stripes,
 			 ctx.data_parity_stripes);
 
@@ -2418,9 +2415,6 @@ void r5c_finish_stripe_write_out(struct r5conf *conf,
 	if (do_wakeup)
 		wake_up(&conf->wait_for_overlap);
 
-	if (conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH)
-		return;
-
 	spin_lock_irq(&conf->log->stripe_in_journal_lock);
 	list_del_init(&sh->r5c);
 	spin_unlock_irq(&conf->log->stripe_in_journal_lock);
@@ -2639,14 +2633,16 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
 	spin_lock_init(&log->stripe_in_journal_lock);
 	atomic_set(&log->stripe_in_journal_count, 0);
 
+	rcu_assign_pointer(conf->log, log);
+
 	if (r5l_load_log(log))
 		goto error;
 
-	rcu_assign_pointer(conf->log, log);
 	set_bit(MD_HAS_JOURNAL, &conf->mddev->flags);
 	return 0;
 
 error:
+	rcu_assign_pointer(conf->log, NULL);
 	md_unregister_thread(&log->reclaim_thread);
 reclaim_thread:
 	mempool_destroy(log->meta_pool);

drivers/md/raid5.c

@@ -62,6 +62,8 @@
 #include "raid0.h"
 #include "bitmap.h"
 
+#define UNSUPPORTED_MDDEV_FLAGS	(1L << MD_FAILFAST_SUPPORTED)
+
 #define cpu_to_group(cpu) cpu_to_node(cpu)
 #define ANY_GROUP NUMA_NO_NODE
 
@@ -7829,8 +7831,9 @@ static void *raid5_takeover_raid1(struct mddev *mddev)
 	mddev->new_chunk_sectors = chunksect;
 
 	ret = setup_conf(mddev);
-	if (!IS_ERR_VALUE(ret))
-		clear_bit(MD_FAILFAST_SUPPORTED, &mddev->flags);
+	if (!IS_ERR(ret))
+		mddev_clear_unsupported_flags(mddev,
+			UNSUPPORTED_MDDEV_FLAGS);
 	return ret;
 }
 

drivers/misc/mei/bus-fixup.c

@@ -152,6 +152,9 @@ static void mei_mkhi_fix(struct mei_cl_device *cldev)
 {
 	int ret;
 
+	if (!cldev->bus->hbm_f_os_supported)
+		return;
+
 	ret = mei_cldev_enable(cldev);
 	if (ret)
 		return;

drivers/misc/mei/debugfs.c

@@ -180,6 +180,8 @@ static ssize_t mei_dbgfs_read_devstate(struct file *fp, char __user *ubuf,
 				 dev->hbm_f_ev_supported);
 		pos += scnprintf(buf + pos, bufsz - pos, "\tFA: %01d\n",
 				 dev->hbm_f_fa_supported);
+		pos += scnprintf(buf + pos, bufsz - pos, "\tOS: %01d\n",
+				 dev->hbm_f_os_supported);
 	}
 
 	pos += scnprintf(buf + pos, bufsz - pos, "pg:  %s, %s\n",

drivers/misc/mei/hbm.c

@@ -989,6 +989,10 @@ static void mei_hbm_config_features(struct mei_device *dev)
 	/* Fixed Address Client Support */
 	if (dev->version.major_version >= HBM_MAJOR_VERSION_FA)
 		dev->hbm_f_fa_supported = 1;
+
+	/* OS ver message Support */
+	if (dev->version.major_version >= HBM_MAJOR_VERSION_OS)
+		dev->hbm_f_os_supported = 1;
 }
 
 /**

drivers/misc/mei/hw.h

@@ -76,6 +76,12 @@
 #define HBM_MINOR_VERSION_FA               0
 #define HBM_MAJOR_VERSION_FA               2
 
+/*
+ * MEI version with OS ver message support
+ */
+#define HBM_MINOR_VERSION_OS               0
+#define HBM_MAJOR_VERSION_OS               2
+
 /* Host bus message command opcode */
 #define MEI_HBM_CMD_OP_MSK                  0x7f
 /* Host bus message command RESPONSE */

drivers/misc/mei/mei_dev.h

@@ -406,6 +406,7 @@ const char *mei_pg_state_str(enum mei_pg_state state);
  * @hbm_f_ev_supported  : hbm feature event notification
  * @hbm_f_fa_supported  : hbm feature fixed address client
  * @hbm_f_ie_supported  : hbm feature immediate reply to enum request
+ * @hbm_f_os_supported  : hbm feature support OS ver message
  *
  * @me_clients_rwsem: rw lock over me_clients list
  * @me_clients  : list of FW clients
@@ -487,6 +488,7 @@ struct mei_device {
 	unsigned int hbm_f_ev_supported:1;
 	unsigned int hbm_f_fa_supported:1;
 	unsigned int hbm_f_ie_supported:1;
+	unsigned int hbm_f_os_supported:1;
 
 	struct rw_semaphore me_clients_rwsem;
 	struct list_head me_clients;

drivers/mmc/core/mmc_ops.c

@@ -506,9 +506,6 @@ static int mmc_poll_for_busy(struct mmc_card *card, unsigned int timeout_ms,
 		}
 	} while (busy);
 
-	if (host->ops->card_busy && send_status)
-		return mmc_switch_status(card);
-
 	return 0;
 }
 
@@ -577,24 +574,26 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 	if (!use_busy_signal)
 		goto out;
 
-	/* Switch to new timing before poll and check switch status. */
-	if (timing)
-		mmc_set_timing(host, timing);
-
 	/*If SPI or used HW busy detection above, then we don't need to poll. */
 	if (((host->caps & MMC_CAP_WAIT_WHILE_BUSY) && use_r1b_resp) ||
-		mmc_host_is_spi(host)) {
-		if (send_status)
-			err = mmc_switch_status(card);
+		mmc_host_is_spi(host))
 		goto out_tim;
-	}
 
 	/* Let's try to poll to find out when the command is completed. */
 	err = mmc_poll_for_busy(card, timeout_ms, send_status, retry_crc_err);
+	if (err)
+		goto out;
 
 out_tim:
-	if (err && timing)
-		mmc_set_timing(host, old_timing);
+	/* Switch to new timing before check switch status. */
+	if (timing)
+		mmc_set_timing(host, timing);
+
+	if (send_status) {
+		err = mmc_switch_status(card);
+		if (err && timing)
+			mmc_set_timing(host, old_timing);
+	}
 out:
 	mmc_retune_release(host);
 

drivers/mmc/host/meson-gx-mmc.c

@@ -578,13 +578,15 @@ static irqreturn_t meson_mmc_irq(int irq, void *dev_id)
 {
 	struct meson_host *host = dev_id;
 	struct mmc_request *mrq;
-	struct mmc_command *cmd = host->cmd;
+	struct mmc_command *cmd;
 	u32 irq_en, status, raw_status;
 	irqreturn_t ret = IRQ_HANDLED;
 
 	if (WARN_ON(!host))
 		return IRQ_NONE;
 
+	cmd = host->cmd;
+
 	mrq = host->mrq;
 
 	if (WARN_ON(!mrq))
@@ -670,10 +672,10 @@ static irqreturn_t meson_mmc_irq_thread(int irq, void *dev_id)
 	int ret = IRQ_HANDLED;
 
 	if (WARN_ON(!mrq))
-		ret = IRQ_NONE;
+		return IRQ_NONE;
 
 	if (WARN_ON(!cmd))
-		ret = IRQ_NONE;
+		return IRQ_NONE;
 
 	data = cmd->data;
 	if (data) {

drivers/mmc/host/mxs-mmc.c

@@ -309,6 +309,9 @@ static void mxs_mmc_ac(struct mxs_mmc_host *host)
 	cmd0 = BF_SSP(cmd->opcode, CMD0_CMD);
 	cmd1 = cmd->arg;
 
+	if (cmd->opcode == MMC_STOP_TRANSMISSION)
+		cmd0 |= BM_SSP_CMD0_APPEND_8CYC;
+
 	if (host->sdio_irq_en) {
 		ctrl0 |= BM_SSP_CTRL0_SDIO_IRQ_CHECK;
 		cmd0 |= BM_SSP_CMD0_CONT_CLKING_EN | BM_SSP_CMD0_SLOW_CLKING_EN;
@@ -417,8 +420,7 @@ static void mxs_mmc_adtc(struct mxs_mmc_host *host)
 		       ssp->base + HW_SSP_BLOCK_SIZE);
 	}
 
-	if ((cmd->opcode == MMC_STOP_TRANSMISSION) ||
-	    (cmd->opcode == SD_IO_RW_EXTENDED))
+	if (cmd->opcode == SD_IO_RW_EXTENDED)
 		cmd0 |= BM_SSP_CMD0_APPEND_8CYC;
 
 	cmd1 = cmd->arg;

drivers/mmc/host/sdhci-acpi.c

@@ -395,7 +395,8 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 	/* Power on the SDHCI controller and its children */
 	acpi_device_fix_up_power(device);
 	list_for_each_entry(child, &device->children, node)
-		acpi_device_fix_up_power(child);
+		if (child->status.present && child->status.enabled)
+			acpi_device_fix_up_power(child);
 
 	if (acpi_bus_get_status(device) || !device->status.present)
 		return -ENODEV;

drivers/mtd/nand/Kconfig

@@ -426,6 +426,7 @@ config MTD_NAND_ORION
 
 config MTD_NAND_OXNAS
 	tristate "NAND Flash support for Oxford Semiconductor SoC"
+	depends on HAS_IOMEM
 	help
 	  This enables the NAND flash controller on Oxford Semiconductor SoCs.
 
@@ -540,7 +541,7 @@ config MTD_NAND_FSMC
 	  Flexible Static Memory Controller (FSMC)
 
 config MTD_NAND_XWAY
-	tristate "Support for NAND on Lantiq XWAY SoC"
+	bool "Support for NAND on Lantiq XWAY SoC"
 	depends on LANTIQ && SOC_TYPE_XWAY
 	help
 	  Enables support for NAND Flash chips on Lantiq XWAY SoCs. NAND is attached

drivers/mtd/nand/lpc32xx_mlc.c

@@ -775,7 +775,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	init_completion(&host->comp_controller);
 
 	host->irq = platform_get_irq(pdev, 0);
-	if ((host->irq < 0) || (host->irq >= NR_IRQS)) {
+	if (host->irq < 0) {
 		dev_err(&pdev->dev, "failed to get platform irq\n");
 		res = -EINVAL;
 		goto err_exit3;

drivers/mtd/nand/tango_nand.c

@@ -632,11 +632,13 @@ static int tango_nand_probe(struct platform_device *pdev)
 	if (IS_ERR(nfc->pbus_base))
 		return PTR_ERR(nfc->pbus_base);
 
+	writel_relaxed(MODE_RAW, nfc->pbus_base + PBUS_PAD_MODE);
+
 	clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
-	nfc->chan = dma_request_chan(&pdev->dev, "nfc_sbox");
+	nfc->chan = dma_request_chan(&pdev->dev, "rxtx");
 	if (IS_ERR(nfc->chan))
 		return PTR_ERR(nfc->chan);
 

drivers/mtd/nand/xway_nand.c

@@ -232,7 +232,6 @@ static const struct of_device_id xway_nand_match[] = {
 	{ .compatible = "lantiq,nand-xway" },
 	{},
 };
-MODULE_DEVICE_TABLE(of, xway_nand_match);
 
 static struct platform_driver xway_nand_driver = {
 	.probe	= xway_nand_probe,
@@ -243,6 +242,4 @@ static struct platform_driver xway_nand_driver = {
 	},
 };
 
-module_platform_driver(xway_nand_driver);
-
-MODULE_LICENSE("GPL");
+builtin_platform_driver(xway_nand_driver);

drivers/net/ethernet/broadcom/bcmsysport.c

@@ -710,11 +710,8 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 	unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs;
 	unsigned int pkts_compl = 0, bytes_compl = 0;
 	struct bcm_sysport_cb *cb;
-	struct netdev_queue *txq;
 	u32 hw_ind;
 
-	txq = netdev_get_tx_queue(ndev, ring->index);
-
 	/* Compute how many descriptors have been processed since last call */
 	hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index));
 	c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK;
@@ -745,9 +742,6 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 
 	ring->c_index = c_index;
 
-	if (netif_tx_queue_stopped(txq) && pkts_compl)
-		netif_tx_wake_queue(txq);
-
 	netif_dbg(priv, tx_done, ndev,
 		  "ring=%d c_index=%d pkts_compl=%d, bytes_compl=%d\n",
 		  ring->index, ring->c_index, pkts_compl, bytes_compl);
@@ -759,16 +753,33 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 static unsigned int bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 					   struct bcm_sysport_tx_ring *ring)
 {
+	struct netdev_queue *txq;
 	unsigned int released;
 	unsigned long flags;
 
+	txq = netdev_get_tx_queue(priv->netdev, ring->index);
+
 	spin_lock_irqsave(&ring->lock, flags);
 	released = __bcm_sysport_tx_reclaim(priv, ring);
+	if (released)
+		netif_tx_wake_queue(txq);
+
 	spin_unlock_irqrestore(&ring->lock, flags);
 
 	return released;
 }
 
+/* Locked version of the per-ring TX reclaim, but does not wake the queue */
+static void bcm_sysport_tx_clean(struct bcm_sysport_priv *priv,
+				 struct bcm_sysport_tx_ring *ring)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ring->lock, flags);
+	__bcm_sysport_tx_reclaim(priv, ring);
+	spin_unlock_irqrestore(&ring->lock, flags);
+}
+
 static int bcm_sysport_tx_poll(struct napi_struct *napi, int budget)
 {
 	struct bcm_sysport_tx_ring *ring =
@@ -1252,7 +1263,7 @@ static void bcm_sysport_fini_tx_ring(struct bcm_sysport_priv *priv,
 	napi_disable(&ring->napi);
 	netif_napi_del(&ring->napi);
 
-	bcm_sysport_tx_reclaim(priv, ring);
+	bcm_sysport_tx_clean(priv, ring);
 
 	kfree(ring->cbs);
 	ring->cbs = NULL;

drivers/net/ethernet/cavium/thunder/thunder_bgx.c

@@ -47,8 +47,9 @@ struct lmac {
 struct bgx {
 	u8			bgx_id;
 	struct	lmac		lmac[MAX_LMAC_PER_BGX];
-	int			lmac_count;
+	u8			lmac_count;
 	u8			max_lmac;
+	u8                      acpi_lmac_idx;
 	void __iomem		*reg_base;
 	struct pci_dev		*pdev;
 	bool                    is_dlm;
@@ -1143,13 +1144,13 @@ static acpi_status bgx_acpi_register_phy(acpi_handle handle,
 	if (acpi_bus_get_device(handle, &adev))
 		goto out;
 
-	acpi_get_mac_address(dev, adev, bgx->lmac[bgx->lmac_count].mac);
+	acpi_get_mac_address(dev, adev, bgx->lmac[bgx->acpi_lmac_idx].mac);
 
-	SET_NETDEV_DEV(&bgx->lmac[bgx->lmac_count].netdev, dev);
+	SET_NETDEV_DEV(&bgx->lmac[bgx->acpi_lmac_idx].netdev, dev);
 
-	bgx->lmac[bgx->lmac_count].lmacid = bgx->lmac_count;
+	bgx->lmac[bgx->acpi_lmac_idx].lmacid = bgx->acpi_lmac_idx;
+	bgx->acpi_lmac_idx++; /* move to next LMAC */
 out:
-	bgx->lmac_count++;
 	return AE_OK;
 }
 

drivers/net/ethernet/emulex/benet/be_cmds.c

@@ -1118,7 +1118,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr,
 err:
 	mutex_unlock(&adapter->mcc_lock);
 
-	 if (status == MCC_STATUS_UNAUTHORIZED_REQUEST)
+	 if (base_status(status) == MCC_STATUS_UNAUTHORIZED_REQUEST)
 		status = -EPERM;
 
 	return status;