Linux 4.14-rc3

-----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJZ0WQ6AAoJEHm+PkMAQRiGuloH/3sF4qfBhPuJo8OTf0uCtQ18
 4Ux9zZbm81df/Jjz0exAp1Jqk+TvdIS3OXPWcKilvbUBP16hQcsxFTnI/5QF+YcN
 87aNr+OCMJzOBK4suN1yhzO46NYHeIizdB0PTZVL1Zsto69Tt31D8VJmgH6oBxAw
 Isb/nAkOr31dZ9PI5UEExTIanUt6EywVb0UswA+2rNl3h1UkeasQCpMpK2n6HBhU
 kVD7sxEd/CN0MmfhB0HrySSam/BeSpOtzoU9bemOwrU2uu9+5+2rqMe7Gsdj4nX6
 3Kk+7FQNktlrhxCZIFN/+CdusOUuDd8r/75d7DnsRK5YvSb0sZzJkfD3Nba68Ms=
 =7J2+
 -----END PGP SIGNATURE-----

BackMerge tag 'v4.14-rc3' into drm-next

Linux 4.14-rc3

Requested by Daniel for the tracing build fix in fixes.

Documentation/cpu-freq/index.txt

@@ -32,8 +32,6 @@ cpufreq-stats.txt -	General description of sysfs cpufreq stats.
 
 index.txt	-	File index, Mailing list and Links (this document)
 
-intel-pstate.txt -	Intel pstate cpufreq driver specific file.
-
 pcc-cpufreq.txt -	PCC cpufreq driver specific file.
 
 

Documentation/devicetree/bindings/leds/ams,as3645a.txt

@@ -15,11 +15,14 @@ Required properties
 
 compatible	: Must be "ams,as3645a".
 reg		: The I2C address of the device. Typically 0x30.
+#address-cells	: 1
+#size-cells	: 0
 
 
-Required properties of the "flash" child node
+Required properties of the flash child node (0)
-=============================================
+===============================================
 
+reg: 0
 flash-timeout-us: Flash timeout in microseconds. The value must be in
 		  the range [100000, 850000] and divisible by 50000.
 flash-max-microamp: Maximum flash current in microamperes. Has to be
@@ -33,20 +36,21 @@ ams,input-max-microamp: Maximum flash controller input current. The
 			and divisible by 50000.
 
 
-Optional properties of the "flash" child node
+Optional properties of the flash child node
-=============================================
+===========================================
 
 label		: The label of the flash LED.
 
 
-Required properties of the "indicator" child node
+Required properties of the indicator child node (1)
-=================================================
+===================================================
 
+reg: 1
 led-max-microamp: Maximum indicator current. The allowed values are
 		  2500, 5000, 7500 and 10000.
 
-Optional properties of the "indicator" child node
+Optional properties of the indicator child node
-=================================================
+===============================================
 
 label		: The label of the indicator LED.
 
@@ -55,16 +59,20 @@ Example
 =======
 
 	as3645a@30 {
+		#address-cells: 1
+		#size-cells: 0
 		reg = <0x30>;
 		compatible = "ams,as3645a";
-		flash {
+		flash@0 {
+			reg = <0x0>;
 			flash-timeout-us = <150000>;
 			flash-max-microamp = <320000>;
 			led-max-microamp = <60000>;
 			ams,input-max-microamp = <1750000>;
 			label = "as3645a:flash";
 		};
-		indicator {
+		indicator@1 {
+			reg = <0x1>;
 			led-max-microamp = <10000>;
 			label = "as3645a:indicator";
 		};

MAINTAINERS

@@ -8603,6 +8603,12 @@ M:	Sean Wang <sean.wang@mediatek.com>
 S:	Maintained
 F:	drivers/media/rc/mtk-cir.c
 
+MEDIATEK PMIC LED DRIVER
+M:	Sean Wang <sean.wang@mediatek.com>
+S:	Maintained
+F:	drivers/leds/leds-mt6323.c
+F:	Documentation/devicetree/bindings/leds/leds-mt6323.txt
+
 MEDIATEK ETHERNET DRIVER
 M:	Felix Fietkau <nbd@openwrt.org>
 M:	John Crispin <john@phrozen.org>

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
@@ -1172,11 +1172,11 @@ headers_check: headers_install
 
 PHONY += kselftest
 kselftest:
-	$(Q)$(MAKE) -C tools/testing/selftests run_tests
+	$(Q)$(MAKE) -C $(srctree)/tools/testing/selftests run_tests
 
 PHONY += kselftest-clean
 kselftest-clean:
-	$(Q)$(MAKE) -C tools/testing/selftests clean
+	$(Q)$(MAKE) -C $(srctree)/tools/testing/selftests clean
 
 PHONY += kselftest-merge
 kselftest-merge:

arch/arm/boot/dts/omap3-n950-n9.dtsi

@@ -267,15 +267,19 @@ &i2c2 {
 	clock-frequency = <400000>;
 
 	as3645a@30 {
+		#address-cells = <1>;
+		#size-cells = <0>;
 		reg = <0x30>;
 		compatible = "ams,as3645a";
-		flash {
+		flash@0 {
+			reg = <0x0>;
 			flash-timeout-us = <150000>;
 			flash-max-microamp = <320000>;
 			led-max-microamp = <60000>;
-			peak-current-limit = <1750000>;
+			ams,input-max-microamp = <1750000>;
 		};
-		indicator {
+		indicator@1 {
+			reg = <0x1>;
 			led-max-microamp = <10000>;
 		};
 	};

arch/arm64/include/asm/pgtable.h

@@ -401,7 +401,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 /* Find an entry in the third-level page table. */
 #define pte_index(addr)		(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 
-#define pte_offset_phys(dir,addr)	(pmd_page_paddr(*(dir)) + pte_index(addr) * sizeof(pte_t))
+#define pte_offset_phys(dir,addr)	(pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t))
 #define pte_offset_kernel(dir,addr)	((pte_t *)__va(pte_offset_phys((dir), (addr))))
 
 #define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))

arch/arm64/kernel/head.S

@@ -384,6 +384,7 @@ ENTRY(kimage_vaddr)
  * booted in EL1 or EL2 respectively.
  */
 ENTRY(el2_setup)
+	msr	SPsel, #1			// We want to use SP_EL{1,2}
 	mrs	x0, CurrentEL
 	cmp	x0, #CurrentEL_EL2
 	b.eq	1f

arch/arm64/mm/fault.c

@@ -651,7 +651,7 @@ static const struct fault_info fault_info[] = {
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 0 translation fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
-	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
 	{ do_bad,		SIGBUS,  0,		"unknown 8"			},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},

arch/microblaze/Kconfig

@@ -39,7 +39,7 @@ config MICROBLAZE
 # Endianness selection
 choice
 	prompt "Endianness selection"
-	default CPU_BIG_ENDIAN
+	default CPU_LITTLE_ENDIAN
 	help
 	  microblaze architectures can be configured for either little or
 	  big endian formats. Be sure to select the appropriate mode.

arch/microblaze/include/uapi/asm/Kbuild

@@ -7,6 +7,7 @@ generic-y += fcntl.h
 generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
+generic-y += kvm_para.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += param.h

arch/microblaze/kernel/dma.c

@@ -165,7 +165,7 @@ int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
 			     unsigned long attrs)
 {
 #ifdef CONFIG_MMU
-	unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	unsigned long user_count = vma_pages(vma);
 	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long off = vma->vm_pgoff;
 	unsigned long pfn;

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1121,6 +1121,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 BEGIN_FTR_SECTION
 	mtspr	SPRN_PPR, r0
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+/* Move canary into DSISR to check for later */
+BEGIN_FTR_SECTION
+	li	r0, 0x7fff
+	mtspr	SPRN_HDSISR, r0
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
 	ld	r0, VCPU_GPR(R0)(r4)
 	ld	r4, VCPU_GPR(R4)(r4)
 
@@ -1956,9 +1963,14 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 kvmppc_hdsi:
 	ld	r3, VCPU_KVM(r9)
 	lbz	r0, KVM_RADIX(r3)
-	cmpwi	r0, 0
 	mfspr	r4, SPRN_HDAR
 	mfspr	r6, SPRN_HDSISR
+BEGIN_FTR_SECTION
+	/* Look for DSISR canary. If we find it, retry instruction */
+	cmpdi	r6, 0x7fff
+	beq	6f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+	cmpwi	r0, 0
 	bne	.Lradix_hdsi		/* on radix, just save DAR/DSISR/ASDR */
 	/* HPTE not found fault or protection fault? */
 	andis.	r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h

arch/um/kernel/time.c

@@ -98,7 +98,7 @@ static struct clocksource timer_clocksource = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static void __init timer_setup(void)
+static void __init um_timer_setup(void)
 {
 	int err;
 
@@ -132,5 +132,5 @@ void read_persistent_clock(struct timespec *ts)
 void __init time_init(void)
 {
 	timer_set_signal_handler();
-	late_time_init = timer_setup;
+	late_time_init = um_timer_setup;
 }

arch/x86/events/intel/cstate.c

@@ -552,6 +552,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE,  snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE,  snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
@@ -560,6 +561,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates),
+
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);

arch/x86/events/intel/rapl.c

@@ -775,6 +775,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init),
+
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init),
 	{},
 };
 

arch/x86/events/intel/uncore_snbep.c

@@ -3462,7 +3462,7 @@ static struct intel_uncore_ops skx_uncore_iio_ops = {
 static struct intel_uncore_type skx_uncore_iio = {
 	.name			= "iio",
 	.num_counters		= 4,
-	.num_boxes		= 5,
+	.num_boxes		= 6,
 	.perf_ctr_bits		= 48,
 	.event_ctl		= SKX_IIO0_MSR_PMON_CTL0,
 	.perf_ctr		= SKX_IIO0_MSR_PMON_CTR0,
@@ -3492,7 +3492,7 @@ static const struct attribute_group skx_uncore_format_group = {
 static struct intel_uncore_type skx_uncore_irp = {
 	.name			= "irp",
 	.num_counters		= 2,
-	.num_boxes		= 5,
+	.num_boxes		= 6,
 	.perf_ctr_bits		= 48,
 	.event_ctl		= SKX_IRP0_MSR_PMON_CTL0,
 	.perf_ctr		= SKX_IRP0_MSR_PMON_CTR0,

arch/x86/events/msr.c

@@ -63,6 +63,14 @@ static bool test_intel(int idx)
 	case INTEL_FAM6_ATOM_SILVERMONT1:
 	case INTEL_FAM6_ATOM_SILVERMONT2:
 	case INTEL_FAM6_ATOM_AIRMONT:
+
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_DENVERTON:
+
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+
+	case INTEL_FAM6_XEON_PHI_KNL:
+	case INTEL_FAM6_XEON_PHI_KNM:
 		if (idx == PERF_MSR_SMI)
 			return true;
 		break;

arch/x86/ia32/ia32_signal.c

@@ -231,7 +231,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 		 ksig->ka.sa.sa_restorer)
 		sp = (unsigned long) ksig->ka.sa.sa_restorer;
 
-	if (fpu->fpstate_active) {
+	if (fpu->initialized) {
 		unsigned long fx_aligned, math_size;
 
 		sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);

arch/x86/include/asm/asm.h

@@ -11,10 +11,12 @@
 # define __ASM_FORM_COMMA(x) " " #x ","
 #endif
 
-#ifdef CONFIG_X86_32
+#ifndef __x86_64__
+/* 32 bit */
 # define __ASM_SEL(a,b) __ASM_FORM(a)
 # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a)
 #else
+/* 64 bit */
 # define __ASM_SEL(a,b) __ASM_FORM(b)
 # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b)
 #endif
@@ -139,8 +141,8 @@
  * gets set up by the containing function.  If you forget to do this, objtool
  * may print a "call without frame pointer save/setup" warning.
  */
-register unsigned int __asm_call_sp asm("esp");
+register unsigned long current_stack_pointer asm(_ASM_SP);
-#define ASM_CALL_CONSTRAINT "+r" (__asm_call_sp)
+#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
 #endif
 
 #endif /* _ASM_X86_ASM_H */

arch/x86/include/asm/fpu/internal.h

@@ -23,11 +23,9 @@
 /*
  * High level FPU state handling functions:
  */
-extern void fpu__activate_curr(struct fpu *fpu);
+extern void fpu__initialize(struct fpu *fpu);
-extern void fpu__activate_fpstate_read(struct fpu *fpu);
+extern void fpu__prepare_read(struct fpu *fpu);
-extern void fpu__activate_fpstate_write(struct fpu *fpu);
+extern void fpu__prepare_write(struct fpu *fpu);
-extern void fpu__current_fpstate_write_begin(void);
-extern void fpu__current_fpstate_write_end(void);
 extern void fpu__save(struct fpu *fpu);
 extern void fpu__restore(struct fpu *fpu);
 extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
@@ -120,20 +118,11 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu);
 	err;								\
 })
 
-#define check_insn(insn, output, input...)				\
+#define kernel_insn(insn, output, input...)				\
-({									\
-	int err;							\
 	asm volatile("1:" #insn "\n\t"					\
 		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore)	\
-		     "3:  movl $-1,%[err]\n"				\
+		     : output : input)
-		     "    jmp  2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : [err] "=r" (err), output				\
-		     : "0"(0), input);					\
-	err;								\
-})
 
 static inline int copy_fregs_to_user(struct fregs_state __user *fx)
 {
@@ -153,20 +142,16 @@ static inline int copy_fxregs_to_user(struct fxregs_state __user *fx)
 
 static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
 {
-	int err;
-
 	if (IS_ENABLED(CONFIG_X86_32)) {
-		err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+		kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 	} else {
 		if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) {
-			err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+			kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
 		} else {
 			/* See comment in copy_fxregs_to_kernel() below. */
-			err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
+			kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
 		}
 	}
-	/* Copying from a kernel buffer to FPU registers should never fail: */
-	WARN_ON_FPU(err);
 }
 
 static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
@@ -183,9 +168,7 @@ static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
 
 static inline void copy_kernel_to_fregs(struct fregs_state *fx)
 {
-	int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-
-	WARN_ON_FPU(err);
 }
 
 static inline int copy_user_to_fregs(struct fregs_state __user *fx)
@@ -281,18 +264,13 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
  * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
  * XSAVE area format.
  */
-#define XSTATE_XRESTORE(st, lmask, hmask, err)				\
+#define XSTATE_XRESTORE(st, lmask, hmask)				\
 	asm volatile(ALTERNATIVE(XRSTOR,				\
 				 XRSTORS, X86_FEATURE_XSAVES)		\
 		     "\n"						\
-		     "xor %[err], %[err]\n"				\
 		     "3:\n"						\
-		     ".pushsection .fixup,\"ax\"\n"			\
+		     _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\
-		     "4: movl $-2, %[err]\n"				\
+		     :							\
-		     "jmp 3b\n"						\
-		     ".popsection\n"					\
-		     _ASM_EXTABLE(661b, 4b)				\
-		     : [err] "=r" (err)					\
 		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
@@ -336,7 +314,10 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
 	else
 		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
 
-	/* We should never fault when copying from a kernel buffer: */
+	/*
+	 * We should never fault when copying from a kernel buffer, and the FPU
+	 * state we set at boot time should be valid.
+	 */
 	WARN_ON_FPU(err);
 }
 
@@ -350,7 +331,7 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
 	u32 hmask = mask >> 32;
 	int err;
 
-	WARN_ON(!alternatives_patched);
+	WARN_ON_FPU(!alternatives_patched);
 
 	XSTATE_XSAVE(xstate, lmask, hmask, err);
 
@@ -365,12 +346,8 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
 {
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err;
 
-	XSTATE_XRESTORE(xstate, lmask, hmask, err);
+	XSTATE_XRESTORE(xstate, lmask, hmask);
-
-	/* We should never fault when copying from a kernel buffer: */
-	WARN_ON_FPU(err);
 }
 
 /*
@@ -526,37 +503,16 @@ static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu)
  */
 static inline void fpregs_deactivate(struct fpu *fpu)
 {
-	WARN_ON_FPU(!fpu->fpregs_active);
-
-	fpu->fpregs_active = 0;
 	this_cpu_write(fpu_fpregs_owner_ctx, NULL);
 	trace_x86_fpu_regs_deactivated(fpu);
 }
 
 static inline void fpregs_activate(struct fpu *fpu)
 {
-	WARN_ON_FPU(fpu->fpregs_active);
-
-	fpu->fpregs_active = 1;
 	this_cpu_write(fpu_fpregs_owner_ctx, fpu);
 	trace_x86_fpu_regs_activated(fpu);
 }
 
-/*
- * The question "does this thread have fpu access?"
- * is slightly racy, since preemption could come in
- * and revoke it immediately after the test.
- *
- * However, even in that very unlikely scenario,
- * we can just assume we have FPU access - typically
- * to save the FP state - we'll just take a #NM
- * fault and get the FPU access back.
- */
-static inline int fpregs_active(void)
-{
-	return current->thread.fpu.fpregs_active;
-}
-
 /*
  * FPU state switching for scheduling.
  *
@@ -571,14 +527,13 @@ static inline int fpregs_active(void)
 static inline void
 switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
-	if (old_fpu->fpregs_active) {
+	if (old_fpu->initialized) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
 			old_fpu->last_cpu = -1;
 		else
 			old_fpu->last_cpu = cpu;
 
 		/* But leave fpu_fpregs_owner_ctx! */
-		old_fpu->fpregs_active = 0;
 		trace_x86_fpu_regs_deactivated(old_fpu);
 	} else
 		old_fpu->last_cpu = -1;
@@ -595,7 +550,7 @@ switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu)
 {
 	bool preload = static_cpu_has(X86_FEATURE_FPU) &&
-		       new_fpu->fpstate_active;
+		       new_fpu->initialized;
 
 	if (preload) {
 		if (!fpregs_state_valid(new_fpu, cpu))
@@ -617,8 +572,7 @@ static inline void user_fpu_begin(void)
 	struct fpu *fpu = &current->thread.fpu;
 
 	preempt_disable();
-	if (!fpregs_active())
+	fpregs_activate(fpu);
-		fpregs_activate(fpu);
 	preempt_enable();
 }
 

arch/x86/include/asm/fpu/types.h

@@ -68,6 +68,9 @@ struct fxregs_state {
 /* Default value for fxregs_state.mxcsr: */
 #define MXCSR_DEFAULT		0x1f80
 
+/* Copy both mxcsr & mxcsr_flags with a single u64 memcpy: */
+#define MXCSR_AND_FLAGS_SIZE sizeof(u64)
+
 /*
  * Software based FPU emulation state. This is arbitrary really,
  * it matches the x87 format to make it easier to understand:
@@ -290,36 +293,13 @@ struct fpu {
 	unsigned int			last_cpu;
 
 	/*
-	 * @fpstate_active:
+	 * @initialized:
 	 *
-	 * This flag indicates whether this context is active: if the task
+	 * This flag indicates whether this context is initialized: if the task
 	 * is not running then we can restore from this context, if the task
 	 * is running then we should save into this context.
 	 */
-	unsigned char			fpstate_active;
+	unsigned char			initialized;
-
-	/*
-	 * @fpregs_active:
-	 *
-	 * This flag determines whether a given context is actively
-	 * loaded into the FPU's registers and that those registers
-	 * represent the task's current FPU state.
-	 *
-	 * Note the interaction with fpstate_active:
-	 *
-	 *   # task does not use the FPU:
-	 *   fpstate_active == 0
-	 *
-	 *   # task uses the FPU and regs are active:
-	 *   fpstate_active == 1 && fpregs_active == 1
-	 *
-	 *   # the regs are inactive but still match fpstate:
-	 *   fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu
-	 *
-	 * The third state is what we use for the lazy restore optimization
-	 * on lazy-switching CPUs.
-	 */
-	unsigned char			fpregs_active;
 
 	/*
 	 * @state:

arch/x86/include/asm/fpu/xstate.h

@@ -48,8 +48,12 @@ void fpu__xstate_clear_all_cpu_caps(void);
 void *get_xsave_addr(struct xregs_state *xsave, int xstate);
 const void *get_xsave_field_ptr(int xstate_field);
 int using_compacted_format(void);
-int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
+int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
-			void __user *ubuf, struct xregs_state *xsave);
+int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
-int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
+int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf);
-		     struct xregs_state *xsave);
+int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf);
+
+/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
+extern int validate_xstate_header(const struct xstate_header *hdr);
+
 #endif

arch/x86/include/asm/thread_info.h

@@ -158,17 +158,6 @@ struct thread_info {
  */
 #ifndef __ASSEMBLY__
 
-static inline unsigned long current_stack_pointer(void)
-{
-	unsigned long sp;
-#ifdef CONFIG_X86_64
-	asm("mov %%rsp,%0" : "=g" (sp));
-#else
-	asm("mov %%esp,%0" : "=g" (sp));
-#endif
-	return sp;
-}
-
 /*
  * Walks up the stack frames to make sure that the specified object is
  * entirely contained by a single stack frame.

arch/x86/include/asm/trace/fpu.h

@@ -12,25 +12,22 @@ DECLARE_EVENT_CLASS(x86_fpu,
 
 	TP_STRUCT__entry(
 		__field(struct fpu *, fpu)
-		__field(bool, fpregs_active)
+		__field(bool, initialized)
-		__field(bool, fpstate_active)
 		__field(u64, xfeatures)
 		__field(u64, xcomp_bv)
 		),
 
 	TP_fast_assign(
 		__entry->fpu		= fpu;
-		__entry->fpregs_active	= fpu->fpregs_active;
+		__entry->initialized	= fpu->initialized;
-		__entry->fpstate_active	= fpu->fpstate_active;
 		if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
 			__entry->xfeatures = fpu->state.xsave.header.xfeatures;
 			__entry->xcomp_bv  = fpu->state.xsave.header.xcomp_bv;
 		}
 	),
-	TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx",
+	TP_printk("x86/fpu: %p initialized: %d xfeatures: %llx xcomp_bv: %llx",
 			__entry->fpu,
-			__entry->fpregs_active,
+			__entry->initialized,
-			__entry->fpstate_active,
 			__entry->xfeatures,
 			__entry->xcomp_bv
 	)

arch/x86/include/asm/uaccess.h

@@ -337,7 +337,7 @@ do {									\
 		     _ASM_EXTABLE(1b, 4b)				\
 		     _ASM_EXTABLE(2b, 4b)				\
 		     : "=r" (retval), "=&A"(x)				\
-		     : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1),	\
+		     : "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1),	\
 		       "i" (errret), "0" (retval));			\
 })
 

arch/x86/include/asm/xen/hypercall.h

@@ -551,13 +551,13 @@ static inline void
 MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
 			struct desc_struct desc)
 {
-	u32 *p = (u32 *) &desc;
-
 	mcl->op = __HYPERVISOR_update_descriptor;
 	if (sizeof(maddr) == sizeof(long)) {
 		mcl->args[0] = maddr;
 		mcl->args[1] = *(unsigned long *)&desc;
 	} else {
+		u32 *p = (u32 *)&desc;
+
 		mcl->args[0] = maddr;
 		mcl->args[1] = maddr >> 32;
 		mcl->args[2] = *p++;

arch/x86/kernel/fpu/core.c

@@ -100,7 +100,7 @@ void __kernel_fpu_begin(void)
 
 	kernel_fpu_disable();
 
-	if (fpu->fpregs_active) {
+	if (fpu->initialized) {
 		/*
 		 * Ignore return value -- we don't care if reg state
 		 * is clobbered.
@@ -116,7 +116,7 @@ void __kernel_fpu_end(void)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
-	if (fpu->fpregs_active)
+	if (fpu->initialized)
 		copy_kernel_to_fpregs(&fpu->state);
 
 	kernel_fpu_enable();
@@ -148,7 +148,7 @@ void fpu__save(struct fpu *fpu)
 
 	preempt_disable();
 	trace_x86_fpu_before_save(fpu);
-	if (fpu->fpregs_active) {
+	if (fpu->initialized) {
 		if (!copy_fpregs_to_fpstate(fpu)) {
 			copy_kernel_to_fpregs(&fpu->state);
 		}
@@ -189,10 +189,9 @@ EXPORT_SYMBOL_GPL(fpstate_init);
 
 int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 {
-	dst_fpu->fpregs_active = 0;
 	dst_fpu->last_cpu = -1;
 
-	if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU))
+	if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU))
 		return 0;
 
 	WARN_ON_FPU(src_fpu != &current->thread.fpu);
@@ -206,26 +205,14 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	/*
 	 * Save current FPU registers directly into the child
 	 * FPU context, without any memory-to-memory copying.
-	 * In lazy mode, if the FPU context isn't loaded into
-	 * fpregs, CR0.TS will be set and do_device_not_available
-	 * will load the FPU context.
 	 *
-	 * We have to do all this with preemption disabled,
+	 * ( The function 'fails' in the FNSAVE case, which destroys
-	 * mostly because of the FNSAVE case, because in that
+	 *   register contents so we have to copy them back. )
-	 * case we must not allow preemption in the window
-	 * between the FNSAVE and us marking the context lazy.
-	 *
-	 * It shouldn't be an issue as even FNSAVE is plenty
-	 * fast in terms of critical section length.
 	 */
-	preempt_disable();
 	if (!copy_fpregs_to_fpstate(dst_fpu)) {
-		memcpy(&src_fpu->state, &dst_fpu->state,
+		memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size);
-		       fpu_kernel_xstate_size);
-
 		copy_kernel_to_fpregs(&src_fpu->state);
 	}
-	preempt_enable();
 
 	trace_x86_fpu_copy_src(src_fpu);
 	trace_x86_fpu_copy_dst(dst_fpu);
@@ -237,45 +224,48 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
  * Activate the current task's in-memory FPU context,
  * if it has not been used before:
  */
-void fpu__activate_curr(struct fpu *fpu)
+void fpu__initialize(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu);
 
-	if (!fpu->fpstate_active) {
+	if (!fpu->initialized) {
 		fpstate_init(&fpu->state);
 		trace_x86_fpu_init_state(fpu);
 
 		trace_x86_fpu_activate_state(fpu);
 		/* Safe to do for the current task: */
-		fpu->fpstate_active = 1;
+		fpu->initialized = 1;
 	}
 }
-EXPORT_SYMBOL_GPL(fpu__activate_curr);
+EXPORT_SYMBOL_GPL(fpu__initialize);
 
 /*
  * This function must be called before we read a task's fpstate.
  *
- * If the task has not used the FPU before then initialize its
+ * There's two cases where this gets called:
- * fpstate.
+ *
+ * - for the current task (when coredumping), in which case we have
+ *   to save the latest FPU registers into the fpstate,
+ *
+ * - or it's called for stopped tasks (ptrace), in which case the
+ *   registers were already saved by the context-switch code when
+ *   the task scheduled out - we only have to initialize the registers
+ *   if they've never been initialized.
  *
  * If the task has used the FPU before then save it.
  */
-void fpu__activate_fpstate_read(struct fpu *fpu)
+void fpu__prepare_read(struct fpu *fpu)
 {
-	/*
+	if (fpu == &current->thread.fpu) {
-	 * If fpregs are active (in the current CPU), then
-	 * copy them to the fpstate:
-	 */
-	if (fpu->fpregs_active) {
 		fpu__save(fpu);
 	} else {
-		if (!fpu->fpstate_active) {
+		if (!fpu->initialized) {
 			fpstate_init(&fpu->state);
 			trace_x86_fpu_init_state(fpu);
 
 			trace_x86_fpu_activate_state(fpu);
 			/* Safe to do for current and for stopped child tasks: */
-			fpu->fpstate_active = 1;
+			fpu->initialized = 1;
 		}
 	}
 }
@@ -283,17 +273,17 @@ void fpu__activate_fpstate_read(struct fpu *fpu)
 /*
  * This function must be called before we write a task's fpstate.
  *
- * If the task has used the FPU before then unlazy it.
+ * If the task has used the FPU before then invalidate any cached FPU registers.
  * If the task has not used the FPU before then initialize its fpstate.
  *
  * After this function call, after registers in the fpstate are
  * modified and the child task has woken up, the child task will
  * restore the modified FPU state from the modified context. If we
- * didn't clear its lazy status here then the lazy in-registers
+ * didn't clear its cached status here then the cached in-registers
  * state pending on its former CPU could be restored, corrupting
  * the modifications.
  */
-void fpu__activate_fpstate_write(struct fpu *fpu)
+void fpu__prepare_write(struct fpu *fpu)
 {
 	/*
 	 * Only stopped child tasks can be used to modify the FPU
@@ -301,8 +291,8 @@ void fpu__activate_fpstate_write(struct fpu *fpu)
 	 */
 	WARN_ON_FPU(fpu == &current->thread.fpu);
 
-	if (fpu->fpstate_active) {
+	if (fpu->initialized) {
-		/* Invalidate any lazy state: */
+		/* Invalidate any cached state: */
 		__fpu_invalidate_fpregs_state(fpu);
 	} else {
 		fpstate_init(&fpu->state);
@@ -310,73 +300,10 @@ void fpu__activate_fpstate_write(struct fpu *fpu)
 
 		trace_x86_fpu_activate_state(fpu);
 		/* Safe to do for stopped child tasks: */
-		fpu->fpstate_active = 1;
+		fpu->initialized = 1;
 	}
 }
 
-/*
- * This function must be called before we write the current
- * task's fpstate.
- *
- * This call gets the current FPU register state and moves
- * it in to the 'fpstate'.  Preemption is disabled so that
- * no writes to the 'fpstate' can occur from context
- * swiches.
- *
- * Must be followed by a fpu__current_fpstate_write_end().
- */
-void fpu__current_fpstate_write_begin(void)
-{
-	struct fpu *fpu = &current->thread.fpu;
-
-	/*
-	 * Ensure that the context-switching code does not write
-	 * over the fpstate while we are doing our update.
-	 */
-	preempt_disable();
-
-	/*
-	 * Move the fpregs in to the fpu's 'fpstate'.
-	 */
-	fpu__activate_fpstate_read(fpu);
-
-	/*
-	 * The caller is about to write to 'fpu'.  Ensure that no
-	 * CPU thinks that its fpregs match the fpstate.  This
-	 * ensures we will not be lazy and skip a XRSTOR in the
-	 * future.
-	 */
-	__fpu_invalidate_fpregs_state(fpu);
-}
-
-/*
- * This function must be paired with fpu__current_fpstate_write_begin()
- *
- * This will ensure that the modified fpstate gets placed back in
- * the fpregs if necessary.
- *
- * Note: This function may be called whether or not an _actual_
- * write to the fpstate occurred.
- */
-void fpu__current_fpstate_write_end(void)
-{
-	struct fpu *fpu = &current->thread.fpu;
-
-	/*
-	 * 'fpu' now has an updated copy of the state, but the
-	 * registers may still be out of date.  Update them with
-	 * an XRSTOR if they are active.
-	 */
-	if (fpregs_active())
-		copy_kernel_to_fpregs(&fpu->state);
-
-	/*
-	 * Our update is done and the fpregs/fpstate are in sync
-	 * if necessary.  Context switches can happen again.
-	 */
-	preempt_enable();
-}
-
 /*
  * 'fpu__restore()' is called to copy FPU registers from
  * the FPU fpstate to the live hw registers and to activate
@@ -389,7 +316,7 @@ void fpu__current_fpstate_write_end(void)
  */
 void fpu__restore(struct fpu *fpu)
 {
-	fpu__activate_curr(fpu);
+	fpu__initialize(fpu);
 
 	/* Avoid __kernel_fpu_begin() right after fpregs_activate() */
 	kernel_fpu_disable();
@@ -414,15 +341,17 @@ void fpu__drop(struct fpu *fpu)
 {
 	preempt_disable();
 
-	if (fpu->fpregs_active) {
+	if (fpu == &current->thread.fpu) {
-		/* Ignore delayed exceptions from user space */
+		if (fpu->initialized) {
-		asm volatile("1: fwait\n"
+			/* Ignore delayed exceptions from user space */
-			     "2:\n"
+			asm volatile("1: fwait\n"
-			     _ASM_EXTABLE(1b, 2b));
+				     "2:\n"
-		fpregs_deactivate(fpu);
+				     _ASM_EXTABLE(1b, 2b));
+			fpregs_deactivate(fpu);
+		}
 	}
 
-	fpu->fpstate_active = 0;
+	fpu->initialized = 0;
 
 	trace_x86_fpu_dropped(fpu);
 
@@ -462,9 +391,11 @@ void fpu__clear(struct fpu *fpu)
 	 * Make sure fpstate is cleared and initialized.
 	 */
 	if (static_cpu_has(X86_FEATURE_FPU)) {
-		fpu__activate_curr(fpu);
+		preempt_disable();
+		fpu__initialize(fpu);
 		user_fpu_begin();
 		copy_init_fpstate_to_fpregs();
+		preempt_enable();
 	}
 }
 

arch/x86/kernel/fpu/init.c

@@ -240,7 +240,7 @@ static void __init fpu__init_system_ctx_switch(void)
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
 
-	WARN_ON_FPU(current->thread.fpu.fpstate_active);
+	WARN_ON_FPU(current->thread.fpu.initialized);
 }
 
 /*

arch/x86/kernel/fpu/regset.c

@@ -16,14 +16,14 @@ int regset_fpregs_active(struct task_struct *target, const struct user_regset *r
 {
 	struct fpu *target_fpu = &target->thread.fpu;
 
-	return target_fpu->fpstate_active ? regset->n : 0;
+	return target_fpu->initialized ? regset->n : 0;
 }
 
 int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
 {
 	struct fpu *target_fpu = &target->thread.fpu;
 
-	if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active)
+	if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->initialized)
 		return regset->n;
 	else
 		return 0;
@@ -38,7 +38,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
 	if (!boot_cpu_has(X86_FEATURE_FXSR))
 		return -ENODEV;
 
-	fpu__activate_fpstate_read(fpu);
+	fpu__prepare_read(fpu);
 	fpstate_sanitize_xstate(fpu);
 
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
@@ -55,7 +55,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
 	if (!boot_cpu_has(X86_FEATURE_FXSR))
 		return -ENODEV;
 
-	fpu__activate_fpstate_write(fpu);
+	fpu__prepare_write(fpu);
 	fpstate_sanitize_xstate(fpu);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
@@ -89,10 +89,13 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
 
 	xsave = &fpu->state.xsave;
 
-	fpu__activate_fpstate_read(fpu);
+	fpu__prepare_read(fpu);
 
 	if (using_compacted_format()) {
-		ret = copyout_from_xsaves(pos, count, kbuf, ubuf, xsave);
+		if (kbuf)
+			ret = copy_xstate_to_kernel(kbuf, xsave, pos, count);
+		else
+			ret = copy_xstate_to_user(ubuf, xsave, pos, count);
 	} else {
 		fpstate_sanitize_xstate(fpu);
 		/*
@@ -129,12 +132,23 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
 
 	xsave = &fpu->state.xsave;
 
-	fpu__activate_fpstate_write(fpu);
+	fpu__prepare_write(fpu);
 
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
+	if (using_compacted_format()) {
-		ret = copyin_to_xsaves(kbuf, ubuf, xsave);
+		if (kbuf)
-	else
+			ret = copy_kernel_to_xstate(xsave, kbuf);
+		else
+			ret = copy_user_to_xstate(xsave, ubuf);
+	} else {
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+		if (!ret)
+			ret = validate_xstate_header(&xsave->header);
+	}
+
+	/*
+	 * mxcsr reserved bits must be masked to zero for security reasons.
+	 */
+	xsave->i387.mxcsr &= mxcsr_feature_mask;
 
 	/*
 	 * In case of failure, mark all states as init:
@@ -142,16 +156,6 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
 	if (ret)
 		fpstate_init(&fpu->state);
 
-	/*
-	 * mxcsr reserved bits must be masked to zero for security reasons.
-	 */
-	xsave->i387.mxcsr &= mxcsr_feature_mask;
-	xsave->header.xfeatures &= xfeatures_mask;
-	/*
-	 * These bits must be zero.
-	 */
-	memset(&xsave->header.reserved, 0, 48);
-
 	return ret;
 }
 
@@ -299,7 +303,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset,
 	struct fpu *fpu = &target->thread.fpu;
 	struct user_i387_ia32_struct env;
 
-	fpu__activate_fpstate_read(fpu);
+	fpu__prepare_read(fpu);
 
 	if (!boot_cpu_has(X86_FEATURE_FPU))
 		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
@@ -329,7 +333,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 	struct user_i387_ia32_struct env;
 	int ret;
 
-	fpu__activate_fpstate_write(fpu);
+	fpu__prepare_write(fpu);
 	fpstate_sanitize_xstate(fpu);
 
 	if (!boot_cpu_has(X86_FEATURE_FPU))
@@ -369,7 +373,7 @@ int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu)
 	struct fpu *fpu = &tsk->thread.fpu;
 	int fpvalid;
 
-	fpvalid = fpu->fpstate_active;
+	fpvalid = fpu->initialized;
 	if (fpvalid)
 		fpvalid = !fpregs_get(tsk, NULL,
 				      0, sizeof(struct user_i387_ia32_struct),

arch/x86/kernel/fpu/signal.c

@@ -155,7 +155,8 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
  */
 int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 {
-	struct xregs_state *xsave = &current->thread.fpu.state.xsave;
+	struct fpu *fpu = &current->thread.fpu;
+	struct xregs_state *xsave = &fpu->state.xsave;
 	struct task_struct *tsk = current;
 	int ia32_fxstate = (buf != buf_fx);
 
@@ -170,13 +171,13 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 			sizeof(struct user_i387_ia32_struct), NULL,
 			(struct _fpstate_32 __user *) buf) ? -1 : 1;
 
-	if (fpregs_active() || using_compacted_format()) {
+	if (fpu->initialized || using_compacted_format()) {
 		/* Save the live register state to the user directly. */
 		if (copy_fpregs_to_sigframe(buf_fx))
 			return -1;
 		/* Update the thread's fxstate to save the fsave header. */
 		if (ia32_fxstate)
-			copy_fxregs_to_kernel(&tsk->thread.fpu);
+			copy_fxregs_to_kernel(fpu);
 	} else {
 		/*
 		 * It is a *bug* if kernel uses compacted-format for xsave
@@ -189,7 +190,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 			return -1;
 		}
 
-		fpstate_sanitize_xstate(&tsk->thread.fpu);
+		fpstate_sanitize_xstate(fpu);
 		if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size))
 			return -1;
 	}
@@ -213,8 +214,11 @@ sanitize_restored_xstate(struct task_struct *tsk,
 	struct xstate_header *header = &xsave->header;
 
 	if (use_xsave()) {
-		/* These bits must be zero. */
+		/*
-		memset(header->reserved, 0, 48);
+		 * Note: we don't need to zero the reserved bits in the
+		 * xstate_header here because we either didn't copy them at all,
+		 * or we checked earlier that they aren't set.
+		 */
 
 		/*
 		 * Init the state that is not present in the memory
@@ -223,7 +227,7 @@ sanitize_restored_xstate(struct task_struct *tsk,
 		if (fx_only)
 			header->xfeatures = XFEATURE_MASK_FPSSE;
 		else
-			header->xfeatures &= (xfeatures_mask & xfeatures);
+			header->xfeatures &= xfeatures;
 	}
 
 	if (use_fxsr()) {
@@ -279,7 +283,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 	if (!access_ok(VERIFY_READ, buf, size))
 		return -EACCES;
 
-	fpu__activate_curr(fpu);
+	fpu__initialize(fpu);
 
 	if (!static_cpu_has(X86_FEATURE_FPU))
 		return fpregs_soft_set(current, NULL,
@@ -307,28 +311,29 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		/*
 		 * For 32-bit frames with fxstate, copy the user state to the
 		 * thread's fpu state, reconstruct fxstate from the fsave
-		 * header. Sanitize the copied state etc.
+		 * header. Validate and sanitize the copied state.
 		 */
 		struct fpu *fpu = &tsk->thread.fpu;
 		struct user_i387_ia32_struct env;
 		int err = 0;
 
 		/*
-		 * Drop the current fpu which clears fpu->fpstate_active. This ensures
+		 * Drop the current fpu which clears fpu->initialized. This ensures
 		 * that any context-switch during the copy of the new state,
 		 * avoids the intermediate state from getting restored/saved.
 		 * Thus avoiding the new restored state from getting corrupted.
 		 * We will be ready to restore/save the state only after
-		 * fpu->fpstate_active is again set.
+		 * fpu->initialized is again set.
 		 */
 		fpu__drop(fpu);
 
 		if (using_compacted_format()) {
-			err = copyin_to_xsaves(NULL, buf_fx,
+			err = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
-					       &fpu->state.xsave);
 		} else {
-			err = __copy_from_user(&fpu->state.xsave,
+			err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
-					       buf_fx, state_size);
+
+			if (!err && state_size > offsetof(struct xregs_state, header))
+				err = validate_xstate_header(&fpu->state.xsave.header);
 		}
 
 		if (err || __copy_from_user(&env, buf, sizeof(env))) {
@@ -339,7 +344,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 			sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
 		}
 
-		fpu->fpstate_active = 1;
+		fpu->initialized = 1;
 		preempt_disable();
 		fpu__restore(fpu);
 		preempt_enable();

arch/x86/kernel/fpu/xstate.c

@@ -483,6 +483,30 @@ int using_compacted_format(void)
 	return boot_cpu_has(X86_FEATURE_XSAVES);
 }
 
+/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
+int validate_xstate_header(const struct xstate_header *hdr)
+{
+	/* No unknown or supervisor features may be set */
+	if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR))
+		return -EINVAL;
+
+	/* Userspace must use the uncompacted format */
+	if (hdr->xcomp_bv)
+		return -EINVAL;
+
+	/*
+	 * If 'reserved' is shrunken to add a new field, make sure to validate
+	 * that new field here!
+	 */
+	BUILD_BUG_ON(sizeof(hdr->reserved) != 48);
+
+	/* No reserved bits may be set */
+	if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved)))
+		return -EINVAL;
+
+	return 0;
+}
+
 static void __xstate_dump_leaves(void)
 {
 	int i;
@@ -867,7 +891,7 @@ const void *get_xsave_field_ptr(int xsave_state)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
-	if (!fpu->fpstate_active)
+	if (!fpu->initialized)
 		return NULL;
 	/*
 	 * fpu__save() takes the CPU's xstate registers
@@ -920,48 +944,55 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 }
 #endif /* ! CONFIG_ARCH_HAS_PKEYS */
 
+/*
+ * Weird legacy quirk: SSE and YMM states store information in the
+ * MXCSR and MXCSR_FLAGS fields of the FP area. That means if the FP
+ * area is marked as unused in the xfeatures header, we need to copy
+ * MXCSR and MXCSR_FLAGS if either SSE or YMM are in use.
+ */
+static inline bool xfeatures_mxcsr_quirk(u64 xfeatures)
+{
+	if (!(xfeatures & (XFEATURE_MASK_SSE|XFEATURE_MASK_YMM)))
+		return false;
+
+	if (xfeatures & XFEATURE_MASK_FP)
+		return false;
+
+	return true;
+}
+
 /*
  * This is similar to user_regset_copyout(), but will not add offset to
  * the source data pointer or increment pos, count, kbuf, and ubuf.
  */
-static inline int xstate_copyout(unsigned int pos, unsigned int count,
+static inline void
-				 void *kbuf, void __user *ubuf,
+__copy_xstate_to_kernel(void *kbuf, const void *data,
-				 const void *data, const int start_pos,
+			unsigned int offset, unsigned int size, unsigned int size_total)
-				 const int end_pos)
 {
-	if ((count == 0) || (pos < start_pos))
+	if (offset < size_total) {
-		return 0;
+		unsigned int copy = min(size, size_total - offset);
 
-	if (end_pos < 0 || pos < end_pos) {
+		memcpy(kbuf + offset, data, copy);
-		unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos));
-
-		if (kbuf) {
-			memcpy(kbuf + pos, data, copy);
-		} else {
-			if (__copy_to_user(ubuf + pos, data, copy))
-				return -EFAULT;
-		}
 	}
-	return 0;
 }
 
 /*
  * Convert from kernel XSAVES compacted format to standard format and copy
- * to a ptrace buffer. It supports partial copy but pos always starts from
+ * to a kernel-space ptrace buffer.
- * zero. This is called from xstateregs_get() and there we check the CPU
+ *
- * has XSAVES.
+ * It supports partial copy but pos always starts from zero. This is called
+ * from xstateregs_get() and there we check the CPU has XSAVES.
  */
-int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
+int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total)
-			void __user *ubuf, struct xregs_state *xsave)
 {
 	unsigned int offset, size;
-	int ret, i;
 	struct xstate_header header;
+	int i;
 
 	/*
 	 * Currently copy_regset_to_user() starts from pos 0:
 	 */
-	if (unlikely(pos != 0))
+	if (unlikely(offset_start != 0))
 		return -EFAULT;
 
 	/*
@@ -977,8 +1008,91 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
 	offset = offsetof(struct xregs_state, header);
 	size = sizeof(header);
 
-	ret = xstate_copyout(offset, size, kbuf, ubuf, &header, 0, count);
+	__copy_xstate_to_kernel(kbuf, &header, offset, size, size_total);
 
+	for (i = 0; i < XFEATURE_MAX; i++) {
+		/*
+		 * Copy only in-use xstates:
+		 */
+		if ((header.xfeatures >> i) & 1) {
+			void *src = __raw_xsave_addr(xsave, 1 << i);
+
+			offset = xstate_offsets[i];
+			size = xstate_sizes[i];
+
+			/* The next component has to fit fully into the output buffer: */
+			if (offset + size > size_total)
+				break;
+
+			__copy_xstate_to_kernel(kbuf, src, offset, size, size_total);
+		}
+
+	}
+
+	if (xfeatures_mxcsr_quirk(header.xfeatures)) {
+		offset = offsetof(struct fxregs_state, mxcsr);
+		size = MXCSR_AND_FLAGS_SIZE;
+		__copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total);
+	}
+
+	/*
+	 * Fill xsave->i387.sw_reserved value for ptrace frame:
+	 */
+	offset = offsetof(struct fxregs_state, sw_reserved);
+	size = sizeof(xstate_fx_sw_bytes);
+
+	__copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total);
+
+	return 0;
+}
+
+static inline int
+__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int offset, unsigned int size, unsigned int size_total)
+{
+	if (!size)
+		return 0;
+
+	if (offset < size_total) {
+		unsigned int copy = min(size, size_total - offset);
+
+		if (__copy_to_user(ubuf + offset, data, copy))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+/*
+ * Convert from kernel XSAVES compacted format to standard format and copy
+ * to a user-space buffer. It supports partial copy but pos always starts from
+ * zero. This is called from xstateregs_get() and there we check the CPU
+ * has XSAVES.
+ */
+int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total)
+{
+	unsigned int offset, size;
+	int ret, i;
+	struct xstate_header header;
+
+	/*
+	 * Currently copy_regset_to_user() starts from pos 0:
+	 */
+	if (unlikely(offset_start != 0))
+		return -EFAULT;
+
+	/*
+	 * The destination is a ptrace buffer; we put in only user xstates:
+	 */
+	memset(&header, 0, sizeof(header));
+	header.xfeatures = xsave->header.xfeatures;
+	header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
+
+	/*
+	 * Copy xregs_state->header:
+	 */
+	offset = offsetof(struct xregs_state, header);
+	size = sizeof(header);
+
+	ret = __copy_xstate_to_user(ubuf, &header, offset, size, size_total);
 	if (ret)
 		return ret;
 
@@ -992,25 +1106,30 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
 
-			ret = xstate_copyout(offset, size, kbuf, ubuf, src, 0, count);
+			/* The next component has to fit fully into the output buffer: */
+			if (offset + size > size_total)
+				break;
 
+			ret = __copy_xstate_to_user(ubuf, src, offset, size, size_total);
 			if (ret)
 				return ret;
-
-			if (offset + size >= count)
-				break;
 		}
 
 	}
 
+	if (xfeatures_mxcsr_quirk(header.xfeatures)) {
+		offset = offsetof(struct fxregs_state, mxcsr);
+		size = MXCSR_AND_FLAGS_SIZE;
+		__copy_xstate_to_user(ubuf, &xsave->i387.mxcsr, offset, size, size_total);
+	}
+
 	/*
 	 * Fill xsave->i387.sw_reserved value for ptrace frame:
 	 */
 	offset = offsetof(struct fxregs_state, sw_reserved);
 	size = sizeof(xstate_fx_sw_bytes);
 
-	ret = xstate_copyout(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count);
+	ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, size_total);
-
 	if (ret)
 		return ret;
 
@@ -1018,55 +1137,42 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
 }
 
 /*
- * Convert from a ptrace standard-format buffer to kernel XSAVES format
+ * Convert from a ptrace standard-format kernel buffer to kernel XSAVES format
- * and copy to the target thread. This is called from xstateregs_set() and
+ * and copy to the target thread. This is called from xstateregs_set().
- * there we check the CPU has XSAVES and a whole standard-sized buffer
- * exists.
  */
-int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
+int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
-		     struct xregs_state *xsave)
 {
 	unsigned int offset, size;
 	int i;
-	u64 xfeatures;
+	struct xstate_header hdr;
-	u64 allowed_features;
 
 	offset = offsetof(struct xregs_state, header);
-	size = sizeof(xfeatures);
+	size = sizeof(hdr);
 
-	if (kbuf) {
+	memcpy(&hdr, kbuf + offset, size);
-		memcpy(&xfeatures, kbuf + offset, size);
-	} else {
-		if (__copy_from_user(&xfeatures, ubuf + offset, size))
-			return -EFAULT;
-	}
 
-	/*
+	if (validate_xstate_header(&hdr))
-	 * Reject if the user sets any disabled or supervisor features:
-	 */
-	allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR;
-
-	if (xfeatures & ~allowed_features)
 		return -EINVAL;
 
 	for (i = 0; i < XFEATURE_MAX; i++) {
 		u64 mask = ((u64)1 << i);
 
-		if (xfeatures & mask) {
+		if (hdr.xfeatures & mask) {
 			void *dst = __raw_xsave_addr(xsave, 1 << i);
 
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
 
-			if (kbuf) {
+			memcpy(dst, kbuf + offset, size);
-				memcpy(dst, kbuf + offset, size);
-			} else {
-				if (__copy_from_user(dst, ubuf + offset, size))
-					return -EFAULT;
-			}
 		}
 	}
 
+	if (xfeatures_mxcsr_quirk(hdr.xfeatures)) {
+		offset = offsetof(struct fxregs_state, mxcsr);
+		size = MXCSR_AND_FLAGS_SIZE;
+		memcpy(&xsave->i387.mxcsr, kbuf + offset, size);
+	}
+
 	/*
 	 * The state that came in from userspace was user-state only.
 	 * Mask all the user states out of 'xfeatures':
@@ -1076,7 +1182,63 @@ int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
 	/*
 	 * Add back in the features that came in from userspace:
 	 */
-	xsave->header.xfeatures |= xfeatures;
+	xsave->header.xfeatures |= hdr.xfeatures;
+
+	return 0;
+}
+
+/*
+ * Convert from a ptrace or sigreturn standard-format user-space buffer to
+ * kernel XSAVES format and copy to the target thread. This is called from
+ * xstateregs_set(), as well as potentially from the sigreturn() and
+ * rt_sigreturn() system calls.
+ */
+int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
+{
+	unsigned int offset, size;
+	int i;
+	struct xstate_header hdr;
+
+	offset = offsetof(struct xregs_state, header);
+	size = sizeof(hdr);
+
+	if (__copy_from_user(&hdr, ubuf + offset, size))
+		return -EFAULT;
+
+	if (validate_xstate_header(&hdr))
+		return -EINVAL;
+
+	for (i = 0; i < XFEATURE_MAX; i++) {
+		u64 mask = ((u64)1 << i);
+
+		if (hdr.xfeatures & mask) {
+			void *dst = __raw_xsave_addr(xsave, 1 << i);
+
+			offset = xstate_offsets[i];
+			size = xstate_sizes[i];
+
+			if (__copy_from_user(dst, ubuf + offset, size))
+				return -EFAULT;
+		}
+	}
+
+	if (xfeatures_mxcsr_quirk(hdr.xfeatures)) {
+		offset = offsetof(struct fxregs_state, mxcsr);
+		size = MXCSR_AND_FLAGS_SIZE;
+		if (__copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size))
+			return -EFAULT;
+	}
+
+	/*
+	 * The state that came in from userspace was user-state only.
+	 * Mask all the user states out of 'xfeatures':
+	 */
+	xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR;
+
+	/*
+	 * Add back in the features that came in from userspace:
+	 */
+	xsave->header.xfeatures |= hdr.xfeatures;
 
 	return 0;
 }

arch/x86/kernel/irq_32.c

@@ -64,7 +64,7 @@ static void call_on_stack(void *func, void *stack)
 
 static inline void *current_stack(void)
 {
-	return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
+	return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
 }
 
 static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
@@ -88,7 +88,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 
 	/* Save the next esp at the bottom of the stack */
 	prev_esp = (u32 *)irqstk;
-	*prev_esp = current_stack_pointer();
+	*prev_esp = current_stack_pointer;
 
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
@@ -139,7 +139,7 @@ void do_softirq_own_stack(void)
 
 	/* Push the previous esp onto the stack */
 	prev_esp = (u32 *)irqstk;
-	*prev_esp = current_stack_pointer();
+	*prev_esp = current_stack_pointer;
 
 	call_on_stack(__do_softirq, isp);
 }

arch/x86/kernel/ksysfs.c

@@ -299,7 +299,7 @@ static int __init create_setup_data_nodes(struct kobject *parent)
 	return 0;
 
 out_clean_nodes:
-	for (j = i - 1; j > 0; j--)
+	for (j = i - 1; j >= 0; j--)
 		cleanup_setup_data_node(*(kobjp + j));
 	kfree(kobjp);
 out_setup_data_kobj:

arch/x86/kernel/kvm.c

@@ -140,7 +140,8 @@ void kvm_async_pf_task_wait(u32 token)
 
 	n.token = token;
 	n.cpu = smp_processor_id();
-	n.halted = is_idle_task(current) || preempt_count() > 1;
+	n.halted = is_idle_task(current) || preempt_count() > 1 ||
+		   rcu_preempt_depth();
 	init_swait_queue_head(&n.wq);
 	hlist_add_head(&n.link, &b->list);
 	raw_spin_unlock(&b->lock);

arch/x86/kernel/signal.c

@@ -263,7 +263,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 		sp = (unsigned long) ka->sa.sa_restorer;
 	}
 
-	if (fpu->fpstate_active) {
+	if (fpu->initialized) {
 		sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32),
 					  &buf_fx, &math_size);
 		*fpstate = (void __user *)sp;
@@ -279,7 +279,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 		return (void __user *)-1L;
 
 	/* save i387 and extended state */
-	if (fpu->fpstate_active &&
+	if (fpu->initialized &&
 	    copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0)
 		return (void __user *)-1L;
 
@@ -755,7 +755,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		/*
 		 * Ensure the signal handler starts with the new fpu state.
 		 */
-		if (fpu->fpstate_active)
+		if (fpu->initialized)
 			fpu__clear(fpu);
 	}
 	signal_setup_done(failed, ksig, stepping);

arch/x86/kernel/traps.c

@@ -142,7 +142,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
 	 * from double_fault.
 	 */
 	BUG_ON((unsigned long)(current_top_of_stack() -
-			       current_stack_pointer()) >= THREAD_SIZE);
+			       current_stack_pointer) >= THREAD_SIZE);
 
 	preempt_enable_no_resched();
 }

arch/x86/kvm/vmx.c

@@ -200,6 +200,8 @@ struct loaded_vmcs {
 	int cpu;
 	bool launched;
 	bool nmi_known_unmasked;
+	unsigned long vmcs_host_cr3;	/* May not match real cr3 */
+	unsigned long vmcs_host_cr4;	/* May not match real cr4 */
 	struct list_head loaded_vmcss_on_cpu_link;
 };
 
@@ -600,8 +602,6 @@ struct vcpu_vmx {
 		int           gs_ldt_reload_needed;
 		int           fs_reload_needed;
 		u64           msr_host_bndcfgs;
-		unsigned long vmcs_host_cr3;	/* May not match real cr3 */
-		unsigned long vmcs_host_cr4;	/* May not match real cr4 */
 	} host_state;
 	struct {
 		int vm86_active;
@@ -2202,46 +2202,44 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	struct pi_desc old, new;
 	unsigned int dest;
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
+	/*
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+	 * In case of hot-plug or hot-unplug, we may have to undo
-		!kvm_vcpu_apicv_active(vcpu))
+	 * vmx_vcpu_pi_put even if there is no assigned device.  And we
+	 * always keep PI.NDST up to date for simplicity: it makes the
+	 * code easier, and CPU migration is not a fast path.
+	 */
+	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
 		return;
 
+	/*
+	 * First handle the simple case where no cmpxchg is necessary; just
+	 * allow posting non-urgent interrupts.
+	 *
+	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+	 * PI.NDST: pi_post_block will do it for us and the wakeup_handler
+	 * expects the VCPU to be on the blocked_vcpu_list that matches
+	 * PI.NDST.
+	 */
+	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR ||
+	    vcpu->cpu == cpu) {
+		pi_clear_sn(pi_desc);
+		return;
+	}
+
+	/* The full case.  */
 	do {
 		old.control = new.control = pi_desc->control;
 
-		/*
+		dest = cpu_physical_id(cpu);
-		 * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there
-		 * are two possible cases:
-		 * 1. After running 'pre_block', context switch
-		 *    happened. For this case, 'sn' was set in
-		 *    vmx_vcpu_put(), so we need to clear it here.
-		 * 2. After running 'pre_block', we were blocked,
-		 *    and woken up by some other guy. For this case,
-		 *    we don't need to do anything, 'pi_post_block'
-		 *    will do everything for us. However, we cannot
-		 *    check whether it is case #1 or case #2 here
-		 *    (maybe, not needed), so we also clear sn here,
-		 *    I think it is not a big deal.
-		 */
-		if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) {
-			if (vcpu->cpu != cpu) {
-				dest = cpu_physical_id(cpu);
 
-				if (x2apic_enabled())
+		if (x2apic_enabled())
-					new.ndst = dest;
+			new.ndst = dest;
-				else
+		else
-					new.ndst = (dest << 8) & 0xFF00;
+			new.ndst = (dest << 8) & 0xFF00;
-			}
 
-			/* set 'NV' to 'notification vector' */
-			new.nv = POSTED_INTR_VECTOR;
-		}
-
-		/* Allow posting non-urgent interrupts */
 		new.sn = 0;
-	} while (cmpxchg(&pi_desc->control, old.control,
+	} while (cmpxchg64(&pi_desc->control, old.control,
-			new.control) != old.control);
+			   new.control) != old.control);
 }
 
 static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
@@ -5178,12 +5176,12 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 	 */
 	cr3 = __read_cr3();
 	vmcs_writel(HOST_CR3, cr3);		/* 22.2.3  FIXME: shadow tables */
-	vmx->host_state.vmcs_host_cr3 = cr3;
+	vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
 
 	/* Save the most likely value for this task's CR4 in the VMCS. */
 	cr4 = cr4_read_shadow();
 	vmcs_writel(HOST_CR4, cr4);			/* 22.2.3, 22.2.5 */
-	vmx->host_state.vmcs_host_cr4 = cr4;
+	vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
 
 	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
 #ifdef CONFIG_X86_64
@@ -9273,15 +9271,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
 	cr3 = __get_current_cr3_fast();
-	if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) {
+	if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) {
 		vmcs_writel(HOST_CR3, cr3);
-		vmx->host_state.vmcs_host_cr3 = cr3;
+		vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
 	}
 
 	cr4 = cr4_read_shadow();
-	if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
+	if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) {
 		vmcs_writel(HOST_CR4, cr4);
-		vmx->host_state.vmcs_host_cr4 = cr4;
+		vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
 	}
 
 	/* When single-stepping over STI and MOV SS, we must clear the
@@ -9591,6 +9589,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
 
+	/*
+	 * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
+	 * or POSTED_INTR_WAKEUP_VECTOR.
+	 */
+	vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+	vmx->pi_desc.sn = 1;
+
 	return &vmx->vcpu;
 
 free_vmcs:
@@ -9839,7 +9844,8 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
 
 	WARN_ON(!is_guest_mode(vcpu));
 
-	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) {
+	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) &&
+		!to_vmx(vcpu)->nested.nested_run_pending) {
 		vmcs12->vm_exit_intr_error_code = fault->error_code;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 				  PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
@@ -11704,6 +11710,37 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
 	kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
 }
 
+static void __pi_post_block(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct pi_desc old, new;
+	unsigned int dest;
+
+	do {
+		old.control = new.control = pi_desc->control;
+		WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
+		     "Wakeup handler not enabled while the VCPU is blocked\n");
+
+		dest = cpu_physical_id(vcpu->cpu);
+
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
+
+		/* set 'NV' to 'notification vector' */
+		new.nv = POSTED_INTR_VECTOR;
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
+
+	if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
+		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		list_del(&vcpu->blocked_vcpu_list);
+		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		vcpu->pre_pcpu = -1;
+	}
+}
+
 /*
  * This routine does the following things for vCPU which is going
  * to be blocked if VT-d PI is enabled.
@@ -11719,7 +11756,6 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
  */
 static int pi_pre_block(struct kvm_vcpu *vcpu)
 {
-	unsigned long flags;
 	unsigned int dest;
 	struct pi_desc old, new;
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
@@ -11729,34 +11765,20 @@ static int pi_pre_block(struct kvm_vcpu *vcpu)
 		!kvm_vcpu_apicv_active(vcpu))
 		return 0;
 
-	vcpu->pre_pcpu = vcpu->cpu;
+	WARN_ON(irqs_disabled());
-	spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
+	local_irq_disable();
-			  vcpu->pre_pcpu), flags);
+	if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
-	list_add_tail(&vcpu->blocked_vcpu_list,
+		vcpu->pre_pcpu = vcpu->cpu;
-		      &per_cpu(blocked_vcpu_on_cpu,
+		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-		      vcpu->pre_pcpu));
+		list_add_tail(&vcpu->blocked_vcpu_list,
-	spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock,
+			      &per_cpu(blocked_vcpu_on_cpu,
-			       vcpu->pre_pcpu), flags);
+				       vcpu->pre_pcpu));
+		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+	}
 
 	do {
 		old.control = new.control = pi_desc->control;
 
-		/*
-		 * We should not block the vCPU if
-		 * an interrupt is posted for it.
-		 */
-		if (pi_test_on(pi_desc) == 1) {
-			spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
-					  vcpu->pre_pcpu), flags);
-			list_del(&vcpu->blocked_vcpu_list);
-			spin_unlock_irqrestore(
-					&per_cpu(blocked_vcpu_on_cpu_lock,
-					vcpu->pre_pcpu), flags);
-			vcpu->pre_pcpu = -1;
-
-			return 1;
-		}
-
 		WARN((pi_desc->sn == 1),
 		     "Warning: SN field of posted-interrupts "
 		     "is set before blocking\n");
@@ -11778,10 +11800,15 @@ static int pi_pre_block(struct kvm_vcpu *vcpu)
 
 		/* set 'NV' to 'wakeup vector' */
 		new.nv = POSTED_INTR_WAKEUP_VECTOR;
-	} while (cmpxchg(&pi_desc->control, old.control,
+	} while (cmpxchg64(&pi_desc->control, old.control,
-			new.control) != old.control);
+			   new.control) != old.control);
 
-	return 0;
+	/* We should not block the vCPU if an interrupt is posted for it.  */
+	if (pi_test_on(pi_desc) == 1)
+		__pi_post_block(vcpu);
+
+	local_irq_enable();
+	return (vcpu->pre_pcpu == -1);
 }
 
 static int vmx_pre_block(struct kvm_vcpu *vcpu)
@@ -11797,44 +11824,13 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
 
 static void pi_post_block(struct kvm_vcpu *vcpu)
 {
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	if (vcpu->pre_pcpu == -1)
-	struct pi_desc old, new;
-	unsigned int dest;
-	unsigned long flags;
-
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
 		return;
 
-	do {
+	WARN_ON(irqs_disabled());
-		old.control = new.control = pi_desc->control;
+	local_irq_disable();
-
+	__pi_post_block(vcpu);
-		dest = cpu_physical_id(vcpu->cpu);
+	local_irq_enable();
-
-		if (x2apic_enabled())
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
-
-		/* Allow posting non-urgent interrupts */
-		new.sn = 0;
-
-		/* set 'NV' to 'notification vector' */
-		new.nv = POSTED_INTR_VECTOR;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
-
-	if(vcpu->pre_pcpu != -1) {
-		spin_lock_irqsave(
-			&per_cpu(blocked_vcpu_on_cpu_lock,
-			vcpu->pre_pcpu), flags);
-		list_del(&vcpu->blocked_vcpu_list);
-		spin_unlock_irqrestore(
-			&per_cpu(blocked_vcpu_on_cpu_lock,
-			vcpu->pre_pcpu), flags);
-		vcpu->pre_pcpu = -1;
-	}
 }
 
 static void vmx_post_block(struct kvm_vcpu *vcpu)

arch/x86/kvm/x86.c

@@ -7225,7 +7225,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	int r;
 	sigset_t sigsaved;
 
-	fpu__activate_curr(fpu);
+	fpu__initialize(fpu);
 
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

arch/x86/math-emu/fpu_entry.c

@@ -114,7 +114,7 @@ void math_emulate(struct math_emu_info *info)
 	struct desc_struct code_descriptor;
 	struct fpu *fpu = &current->thread.fpu;
 
-	fpu__activate_curr(fpu);
+	fpu__initialize(fpu);
 
 #ifdef RE_ENTRANT_CHECKING
 	if (emulating) {

arch/x86/mm/extable.c

@@ -2,6 +2,7 @@
 #include <linux/uaccess.h>
 #include <linux/sched/debug.h>
 
+#include <asm/fpu/internal.h>
 #include <asm/traps.h>
 #include <asm/kdebug.h>
 
@@ -78,6 +79,29 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup,
 }
 EXPORT_SYMBOL_GPL(ex_handler_refcount);
 
+/*
+ * Handler for when we fail to restore a task's FPU state.  We should never get
+ * here because the FPU state of a task using the FPU (task->thread.fpu.state)
+ * should always be valid.  However, past bugs have allowed userspace to set
+ * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn().
+ * These caused XRSTOR to fail when switching to the task, leaking the FPU
+ * registers of the task previously executing on the CPU.  Mitigate this class
+ * of vulnerability by restoring from the initial state (essentially, zeroing
+ * out all the FPU registers) if we can't restore from the task's FPU state.
+ */
+bool ex_handler_fprestore(const struct exception_table_entry *fixup,
+			  struct pt_regs *regs, int trapnr)
+{
+	regs->ip = ex_fixup_addr(fixup);
+
+	WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.",
+		  (void *)instruction_pointer(regs));
+
+	__copy_kernel_to_fpregs(&init_fpstate, -1);
+	return true;
+}
+EXPORT_SYMBOL_GPL(ex_handler_fprestore);
+
 bool ex_handler_ext(const struct exception_table_entry *fixup,
 		   struct pt_regs *regs, int trapnr)
 {

arch/x86/mm/fault.c

@@ -192,8 +192,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
  * 6. T1   : reaches here, sees vma_pkey(vma)=5, when we really
  *	     faulted on a pte with its pkey=4.
  */
-static void fill_sig_info_pkey(int si_code, siginfo_t *info,
+static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey)
-		struct vm_area_struct *vma)
 {
 	/* This is effectively an #ifdef */
 	if (!boot_cpu_has(X86_FEATURE_OSPKE))
@@ -209,7 +208,7 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info,
 	 * valid VMA, so we should never reach this without a
 	 * valid VMA.
 	 */
-	if (!vma) {
+	if (!pkey) {
 		WARN_ONCE(1, "PKU fault with no VMA passed in");
 		info->si_pkey = 0;
 		return;
@@ -219,13 +218,12 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info,
 	 * absolutely guranteed to be 100% accurate because of
 	 * the race explained above.
 	 */
-	info->si_pkey = vma_pkey(vma);
+	info->si_pkey = *pkey;
 }
 
 static void
 force_sig_info_fault(int si_signo, int si_code, unsigned long address,
-		     struct task_struct *tsk, struct vm_area_struct *vma,
+		     struct task_struct *tsk, u32 *pkey, int fault)
-		     int fault)
 {
 	unsigned lsb = 0;
 	siginfo_t info;
@@ -240,7 +238,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address,
 		lsb = PAGE_SHIFT;
 	info.si_addr_lsb = lsb;
 
-	fill_sig_info_pkey(si_code, &info, vma);
+	fill_sig_info_pkey(si_code, &info, pkey);
 
 	force_sig_info(si_signo, &info, tsk);
 }
@@ -762,8 +760,6 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	struct task_struct *tsk = current;
 	unsigned long flags;
 	int sig;
-	/* No context means no VMA to pass down */
-	struct vm_area_struct *vma = NULL;
 
 	/* Are we prepared to handle this kernel fault? */
 	if (fixup_exception(regs, X86_TRAP_PF)) {
@@ -788,7 +784,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 			/* XXX: hwpoison faults will set the wrong code. */
 			force_sig_info_fault(signal, si_code, address,
-					     tsk, vma, 0);
+					     tsk, NULL, 0);
 		}
 
 		/*
@@ -896,8 +892,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 
 static void
 __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
-		       unsigned long address, struct vm_area_struct *vma,
+		       unsigned long address, u32 *pkey, int si_code)
-		       int si_code)
 {
 	struct task_struct *tsk = current;
 
@@ -945,7 +940,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		tsk->thread.error_code	= error_code;
 		tsk->thread.trap_nr	= X86_TRAP_PF;
 
-		force_sig_info_fault(SIGSEGV, si_code, address, tsk, vma, 0);
+		force_sig_info_fault(SIGSEGV, si_code, address, tsk, pkey, 0);
 
 		return;
 	}
@@ -958,9 +953,9 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 
 static noinline void
 bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
-		     unsigned long address, struct vm_area_struct *vma)
+		     unsigned long address, u32 *pkey)
 {
-	__bad_area_nosemaphore(regs, error_code, address, vma, SEGV_MAPERR);
+	__bad_area_nosemaphore(regs, error_code, address, pkey, SEGV_MAPERR);
 }
 
 static void
@@ -968,6 +963,10 @@ __bad_area(struct pt_regs *regs, unsigned long error_code,
 	   unsigned long address,  struct vm_area_struct *vma, int si_code)
 {
 	struct mm_struct *mm = current->mm;
+	u32 pkey;
+
+	if (vma)
+		pkey = vma_pkey(vma);
 
 	/*
 	 * Something tried to access memory that isn't in our memory map..
@@ -975,7 +974,8 @@ __bad_area(struct pt_regs *regs, unsigned long error_code,
 	 */
 	up_read(&mm->mmap_sem);
 
-	__bad_area_nosemaphore(regs, error_code, address, vma, si_code);
+	__bad_area_nosemaphore(regs, error_code, address,
+			       (vma) ? &pkey : NULL, si_code);
 }
 
 static noinline void
@@ -1018,7 +1018,7 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
 
 static void
 do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
-	  struct vm_area_struct *vma, unsigned int fault)
+	  u32 *pkey, unsigned int fault)
 {
 	struct task_struct *tsk = current;
 	int code = BUS_ADRERR;
@@ -1045,13 +1045,12 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 		code = BUS_MCEERR_AR;
 	}
 #endif
-	force_sig_info_fault(SIGBUS, code, address, tsk, vma, fault);
+	force_sig_info_fault(SIGBUS, code, address, tsk, pkey, fault);
 }
 
 static noinline void
 mm_fault_error(struct pt_regs *regs, unsigned long error_code,
-	       unsigned long address, struct vm_area_struct *vma,
+	       unsigned long address, u32 *pkey, unsigned int fault)
-	       unsigned int fault)
 {
 	if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
 		no_context(regs, error_code, address, 0, 0);
@@ -1075,9 +1074,9 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	} else {
 		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
 			     VM_FAULT_HWPOISON_LARGE))
-			do_sigbus(regs, error_code, address, vma, fault);
+			do_sigbus(regs, error_code, address, pkey, fault);
 		else if (fault & VM_FAULT_SIGSEGV)
-			bad_area_nosemaphore(regs, error_code, address, vma);
+			bad_area_nosemaphore(regs, error_code, address, pkey);
 		else
 			BUG();
 	}
@@ -1267,6 +1266,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	struct mm_struct *mm;
 	int fault, major = 0;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+	u32 pkey;
 
 	tsk = current;
 	mm = tsk->mm;
@@ -1467,9 +1467,10 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 		return;
 	}
 
+	pkey = vma_pkey(vma);
 	up_read(&mm->mmap_sem);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
-		mm_fault_error(regs, error_code, address, vma, fault);
+		mm_fault_error(regs, error_code, address, &pkey, fault);
 		return;
 	}
 

arch/x86/mm/mem_encrypt.c

@@ -10,6 +10,8 @@
  * published by the Free Software Foundation.
  */
 
+#define DISABLE_BRANCH_PROFILING
+
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <linux/mm.h>

arch/x86/mm/pkeys.c

@@ -18,7 +18,6 @@
 
 #include <asm/cpufeature.h>             /* boot_cpu_has, ...            */
 #include <asm/mmu_context.h>            /* vma_pkey()                   */
-#include <asm/fpu/internal.h>           /* fpregs_active()              */
 
 int __execute_only_pkey(struct mm_struct *mm)
 {
@@ -45,7 +44,7 @@ int __execute_only_pkey(struct mm_struct *mm)
 	 */
 	preempt_disable();
 	if (!need_to_set_mm_pkey &&
-	    fpregs_active() &&
+	    current->thread.fpu.initialized &&
 	    !__pkru_allows_read(read_pkru(), execute_only_pkey)) {
 		preempt_enable();
 		return execute_only_pkey;

arch/x86/mm/tlb.c

@@ -191,7 +191,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			 * mapped in the new pgd, we'll double-fault.  Forcibly
 			 * map it.
 			 */
-			unsigned int index = pgd_index(current_stack_pointer());
+			unsigned int index = pgd_index(current_stack_pointer);
 			pgd_t *pgd = next->pgd + index;
 
 			if (unlikely(pgd_none(*pgd)))

arch/x86/xen/mmu_pv.c

@@ -1238,21 +1238,16 @@ static void __init xen_pagetable_cleanhighmap(void)
 	 * from _brk_limit way up to the max_pfn_mapped (which is the end of
 	 * the ramdisk). We continue on, erasing PMD entries that point to page
 	 * tables - do note that they are accessible at this stage via __va.
-	 * For good measure we also round up to the PMD - which means that if
+	 * As Xen is aligning the memory end to a 4MB boundary, for good
+	 * measure we also round up to PMD_SIZE * 2 - which means that if
 	 * anybody is using __ka address to the initial boot-stack - and try
 	 * to use it - they are going to crash. The xen_start_info has been
 	 * taken care of already in xen_setup_kernel_pagetable. */
 	addr = xen_start_info->pt_base;
-	size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE);
+	size = xen_start_info->nr_pt_frames * PAGE_SIZE;
 
-	xen_cleanhighmap(addr, addr + size);
+	xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2));
 	xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base));
-#ifdef DEBUG
-	/* This is superfluous and is not necessary, but you know what
-	 * lets do it. The MODULES_VADDR -> MODULES_END should be clear of
-	 * anything at this stage. */
-	xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1);
-#endif
 }
 #endif
 

block/blk-core.c

@@ -854,6 +854,9 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
 
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+	mutex_init(&q->blk_trace_mutex);
+#endif
 	mutex_init(&q->sysfs_lock);
 	spin_lock_init(&q->__queue_lock);
 

block/bsg-lib.c

@@ -154,7 +154,6 @@ static int bsg_prepare_job(struct device *dev, struct request *req)
 failjob_rls_rqst_payload:
 	kfree(job->request_payload.sg_list);
 failjob_rls_job:
-	kfree(job);
 	return -ENOMEM;
 }
 

block/partition-generic.c

@@ -112,7 +112,7 @@ ssize_t part_stat_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
-	struct request_queue *q = dev_to_disk(dev)->queue;
+	struct request_queue *q = part_to_disk(p)->queue;
 	unsigned int inflight[2];
 	int cpu;
 

drivers/acpi/apei/ghes.c

@@ -743,17 +743,19 @@ static int ghes_proc(struct ghes *ghes)
 	}
 	ghes_do_proc(ghes, ghes->estatus);
 
+out:
+	ghes_clear_estatus(ghes);
+
+	if (rc == -ENOENT)
+		return rc;
+
 	/*
 	 * GHESv2 type HEST entries introduce support for error acknowledgment,
 	 * so only acknowledge the error if this support is present.
 	 */
-	if (is_hest_type_generic_v2(ghes)) {
+	if (is_hest_type_generic_v2(ghes))
-		rc = ghes_ack_error(ghes->generic_v2);
+		return ghes_ack_error(ghes->generic_v2);
-		if (rc)
+
-			return rc;
-	}
-out:
-	ghes_clear_estatus(ghes);
 	return rc;
 }
 

drivers/base/power/opp/core.c

@@ -1581,6 +1581,9 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 
 	opp->available = availability_req;
 
+	dev_pm_opp_get(opp);
+	mutex_unlock(&opp_table->lock);
+
 	/* Notify the change of the OPP availability */
 	if (availability_req)
 		blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ENABLE,
@@ -1589,8 +1592,12 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 		blocking_notifier_call_chain(&opp_table->head,
 					     OPP_EVENT_DISABLE, opp);
 
+	dev_pm_opp_put(opp);
+	goto put_table;
+
 unlock:
 	mutex_unlock(&opp_table->lock);
+put_table:
 	dev_pm_opp_put_opp_table(opp_table);
 	return r;
 }

drivers/block/brd.c

@@ -342,7 +342,7 @@ static long __brd_direct_access(struct brd_device *brd, pgoff_t pgoff,
 
 	if (!brd)
 		return -ENODEV;
-	page = brd_insert_page(brd, PFN_PHYS(pgoff) / 512);
+	page = brd_insert_page(brd, (sector_t)pgoff << PAGE_SECTORS_SHIFT);
 	if (!page)
 		return -ENOSPC;
 	*kaddr = page_address(page);

drivers/block/loop.h

@@ -67,10 +67,8 @@ struct loop_device {
 struct loop_cmd {
 	struct kthread_work work;
 	struct request *rq;
-	union {
+	bool use_aio; /* use AIO interface to handle I/O */
-		bool use_aio; /* use AIO interface to handle I/O */
+	atomic_t ref; /* only for aio */
-		atomic_t ref; /* only for aio */
-	};
 	long ret;
 	struct kiocb iocb;
 	struct bio_vec *bvec;

drivers/block/nbd.c

@@ -1194,6 +1194,12 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	/* The block layer will pass back some non-nbd ioctls in case we have
+	 * special handling for them, but we don't so just return an error.
+	 */
+	if (_IOC_TYPE(cmd) != 0xab)
+		return -EINVAL;
+
 	mutex_lock(&nbd->config_lock);
 
 	/* Don't allow ioctl operations on a nbd device that was created with

drivers/clocksource/numachip.c

@@ -43,7 +43,7 @@ static int numachip2_set_next_event(unsigned long delta, struct clock_event_devi
 	return 0;
 }
 
-static struct clock_event_device numachip2_clockevent = {
+static const struct clock_event_device numachip2_clockevent __initconst = {
 	.name            = "numachip2",
 	.rating          = 400,
 	.set_next_event  = numachip2_set_next_event,

drivers/cpufreq/cpufreq-dt-platdev.c

@@ -118,6 +118,10 @@ static const struct of_device_id blacklist[] __initconst = {
 
 	{ .compatible = "sigma,tango4", },
 
+	{ .compatible = "ti,am33xx", },
+	{ .compatible = "ti,am43", },
+	{ .compatible = "ti,dra7", },
+
 	{ }
 };
 

drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c

@@ -636,7 +636,194 @@ static void gfx_v6_0_tiling_mode_table_init(struct amdgpu_device *adev)
 				NUM_BANKS(ADDR_SURF_2_BANK);
 		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++)
 			WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]);
-	} else if (adev->asic_type == CHIP_OLAND || adev->asic_type == CHIP_HAINAN) {
+	} else if (adev->asic_type == CHIP_OLAND) {
+		tilemode[0] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[1] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[2] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[3] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[4] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[5] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(split_equal_to_row_size) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[6] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(split_equal_to_row_size) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[7] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(split_equal_to_row_size) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[8] =   MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_LINEAR_ALIGNED) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[9] =   MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[10] =  MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[11] =  MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[12] =  MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[13] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[14] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[15] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[16] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[17] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				TILE_SPLIT(split_equal_to_row_size) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[21] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_2) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[22] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+		tilemode[23] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[24] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+				NUM_BANKS(ADDR_SURF_16_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+		tilemode[25] =  MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+				PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+				NUM_BANKS(ADDR_SURF_8_BANK) |
+				BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+				BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+				MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1);
+		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++)
+			WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]);
+	} else if (adev->asic_type == CHIP_HAINAN) {
 		tilemode[0] =   MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
 				ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
 				PIPE_CONFIG(ADDR_SURF_P2) |

drivers/gpu/drm/amd/amdkfd/kfd_chardev.c

@@ -892,6 +892,8 @@ static int kfd_ioctl_get_tile_config(struct file *filep,
 	int err = 0;
 
 	dev = kfd_device_by_id(args->gpu_id);
+	if (!dev)
+		return -EINVAL;
 
 	dev->kfd2kgd->get_tile_config(dev->kgd, &config);
 

drivers/gpu/drm/amd/amdkfd/kfd_events.c

@@ -292,7 +292,10 @@ static int create_signal_event(struct file *devkfd,
 				struct kfd_event *ev)
 {
 	if (p->signal_event_count == KFD_SIGNAL_EVENT_LIMIT) {
-		pr_warn("Signal event wasn't created because limit was reached\n");
+		if (!p->signal_event_limit_reached) {
+			pr_warn("Signal event wasn't created because limit was reached\n");
+			p->signal_event_limit_reached = true;
+		}
 		return -ENOMEM;
 	}
 

drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c

@@ -184,7 +184,7 @@ static void uninitialize(struct kernel_queue *kq)
 	if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ)
 		kq->mqd->destroy_mqd(kq->mqd,
 					kq->queue->mqd,
-					false,
+					KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 					QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS,
 					kq->queue->pipe,
 					kq->queue->queue);
@@ -210,6 +210,11 @@ static int acquire_packet_buffer(struct kernel_queue *kq,
 	uint32_t wptr, rptr;
 	unsigned int *queue_address;
 
+	/* When rptr == wptr, the buffer is empty.
+	 * When rptr == wptr + 1, the buffer is full.
+	 * It is always rptr that advances to the position of wptr, rather than
+	 * the opposite. So we can only use up to queue_size_dwords - 1 dwords.
+	 */
 	rptr = *kq->rptr_kernel;
 	wptr = *kq->wptr_kernel;
 	queue_address = (unsigned int *)kq->pq_kernel_addr;
@@ -219,11 +224,10 @@ static int acquire_packet_buffer(struct kernel_queue *kq,
 	pr_debug("wptr: %d\n", wptr);
 	pr_debug("queue_address 0x%p\n", queue_address);
 
-	available_size = (rptr - 1 - wptr + queue_size_dwords) %
+	available_size = (rptr + queue_size_dwords - 1 - wptr) %
 							queue_size_dwords;
 
-	if (packet_size_in_dwords >= queue_size_dwords ||
+	if (packet_size_in_dwords > available_size) {
-			packet_size_in_dwords >= available_size) {
 		/*
 		 * make sure calling functions know
 		 * acquire_packet_buffer() failed
@@ -233,6 +237,14 @@ static int acquire_packet_buffer(struct kernel_queue *kq,
 	}
 
 	if (wptr + packet_size_in_dwords >= queue_size_dwords) {
+		/* make sure after rolling back to position 0, there is
+		 * still enough space.
+		 */
+		if (packet_size_in_dwords >= rptr) {
+			*buffer_ptr = NULL;
+			return -ENOMEM;
+		}
+		/* fill nops, roll back and start at position 0 */
 		while (wptr > 0) {
 			queue_address[wptr] = kq->nop_packet;
 			wptr = (wptr + 1) % queue_size_dwords;

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -519,6 +519,7 @@ struct kfd_process {
 	struct list_head signal_event_pages;
 	u32 next_nonsignal_event_id;
 	size_t signal_event_count;
+	bool signal_event_limit_reached;
 };
 
 /**

drivers/gpu/drm/etnaviv/etnaviv_gem.c

@@ -551,12 +551,15 @@ static const struct etnaviv_gem_ops etnaviv_gem_shmem_ops = {
 void etnaviv_gem_free_object(struct drm_gem_object *obj)
 {
 	struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj);
+	struct etnaviv_drm_private *priv = obj->dev->dev_private;
 	struct etnaviv_vram_mapping *mapping, *tmp;
 
 	/* object should not be active */
 	WARN_ON(is_active(etnaviv_obj));
 
+	mutex_lock(&priv->gem_lock);
 	list_del(&etnaviv_obj->gem_node);
+	mutex_unlock(&priv->gem_lock);
 
 	list_for_each_entry_safe(mapping, tmp, &etnaviv_obj->vram_list,
 				 obj_node) {

drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c

@@ -445,8 +445,10 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data,
 	cmdbuf->user_size = ALIGN(args->stream_size, 8);
 
 	ret = etnaviv_gpu_submit(gpu, submit, cmdbuf);
-	if (ret == 0)
+	if (ret)
-		cmdbuf = NULL;
+		goto out;
+
+	cmdbuf = NULL;
 
 	if (args->flags & ETNA_SUBMIT_FENCE_FD_OUT) {
 		/*

drivers/gpu/drm/qxl/qxl_display.c

@@ -509,23 +509,25 @@ static void qxl_primary_atomic_update(struct drm_plane *plane,
 	    .y2 = qfb->base.height
 	};
 
-	if (!old_state->fb) {
+	if (old_state->fb) {
-		qxl_io_log(qdev,
-			   "create primary fb: %dx%d,%d,%d\n",
-			   bo->surf.width, bo->surf.height,
-			   bo->surf.stride, bo->surf.format);
-
-		qxl_io_create_primary(qdev, 0, bo);
-		bo->is_primary = true;
-		return;
-
-	} else {
 		qfb_old = to_qxl_framebuffer(old_state->fb);
 		bo_old = gem_to_qxl_bo(qfb_old->obj);
+	} else {
+		bo_old = NULL;
+	}
+
+	if (bo == bo_old)
+		return;
+
+	if (bo_old && bo_old->is_primary) {
+		qxl_io_destroy_primary(qdev);
 		bo_old->is_primary = false;
 	}
 
-	bo->is_primary = true;
+	if (!bo->is_primary) {
+		qxl_io_create_primary(qdev, 0, bo);
+		bo->is_primary = true;
+	}
 	qxl_draw_dirty_fb(qdev, qfb, bo, 0, 0, &norect, 1, 1);
 }
 
@@ -534,13 +536,15 @@ static void qxl_primary_atomic_disable(struct drm_plane *plane,
 {
 	struct qxl_device *qdev = plane->dev->dev_private;
 
-	if (old_state->fb)
+	if (old_state->fb) {
-	{	struct qxl_framebuffer *qfb =
+		struct qxl_framebuffer *qfb =
 			to_qxl_framebuffer(old_state->fb);
 		struct qxl_bo *bo = gem_to_qxl_bo(qfb->obj);
 
-		qxl_io_destroy_primary(qdev);
+		if (bo->is_primary) {
-		bo->is_primary = false;
+			qxl_io_destroy_primary(qdev);
+			bo->is_primary = false;
+		}
 	}
 }
 
@@ -698,14 +702,15 @@ static void qxl_plane_cleanup_fb(struct drm_plane *plane,
 	struct drm_gem_object *obj;
 	struct qxl_bo *user_bo;
 
-	if (!plane->state->fb) {
+	if (!old_state->fb) {
-		/* we never executed prepare_fb, so there's nothing to
+		/*
+		 * we never executed prepare_fb, so there's nothing to
 		 * unpin.
 		 */
 		return;
 	}
 
-	obj = to_qxl_framebuffer(plane->state->fb)->obj;
+	obj = to_qxl_framebuffer(old_state->fb)->obj;
 	user_bo = gem_to_qxl_bo(obj);
 	qxl_bo_unpin(user_bo);
 }

drivers/gpu/drm/radeon/radeon_device.c

@@ -1663,7 +1663,7 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend,
 	radeon_agp_suspend(rdev);
 
 	pci_save_state(dev->pdev);
-	if (freeze && rdev->family >= CHIP_CEDAR) {
+	if (freeze && rdev->family >= CHIP_CEDAR && !(rdev->flags & RADEON_IS_IGP)) {
 		rdev->asic->asic_reset(rdev, true);
 		pci_restore_state(dev->pdev);
 	} else if (suspend) {

drivers/gpu/drm/sun4i/Kconfig

@@ -26,7 +26,7 @@ config DRM_SUN4I_HDMI_CEC
        bool "Allwinner A10 HDMI CEC Support"
        depends on DRM_SUN4I_HDMI
        select CEC_CORE
-       depends on CEC_PIN
+       select CEC_PIN
        help
 	  Choose this option if you have an Allwinner SoC with an HDMI
 	  controller and want to use CEC.

drivers/gpu/drm/sun4i/sun4i_hdmi.h

@@ -15,7 +15,7 @@
 #include <drm/drm_connector.h>
 #include <drm/drm_encoder.h>
 
-#include <media/cec.h>
+#include <media/cec-pin.h>
 
 #define SUN4I_HDMI_CTRL_REG		0x004
 #define SUN4I_HDMI_CTRL_ENABLE			BIT(31)

drivers/gpu/drm/tegra/trace.h

@@ -63,6 +63,6 @@ DEFINE_EVENT(register_access, sor_readl,
 
 /* This part must be outside protection */
 #undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/tegra
 #define TRACE_INCLUDE_FILE trace
 #include <trace/define_trace.h>

drivers/infiniband/core/security.c

@@ -432,8 +432,10 @@ int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev)
 	atomic_set(&qp->qp_sec->error_list_count, 0);
 	init_completion(&qp->qp_sec->error_complete);
 	ret = security_ib_alloc_security(&qp->qp_sec->security);
-	if (ret)
+	if (ret) {
 		kfree(qp->qp_sec);
+		qp->qp_sec = NULL;
+	}
 
 	return ret;
 }

drivers/infiniband/core/uverbs_cmd.c

@@ -3869,15 +3869,15 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 	resp.raw_packet_caps = attr.raw_packet_caps;
 	resp.response_length += sizeof(resp.raw_packet_caps);
 
-	if (ucore->outlen < resp.response_length + sizeof(resp.xrq_caps))
+	if (ucore->outlen < resp.response_length + sizeof(resp.tm_caps))
 		goto end;
 
-	resp.xrq_caps.max_rndv_hdr_size = attr.xrq_caps.max_rndv_hdr_size;
+	resp.tm_caps.max_rndv_hdr_size	= attr.tm_caps.max_rndv_hdr_size;
-	resp.xrq_caps.max_num_tags      = attr.xrq_caps.max_num_tags;
+	resp.tm_caps.max_num_tags	= attr.tm_caps.max_num_tags;
-	resp.xrq_caps.max_ops		= attr.xrq_caps.max_ops;
+	resp.tm_caps.max_ops		= attr.tm_caps.max_ops;
-	resp.xrq_caps.max_sge		= attr.xrq_caps.max_sge;
+	resp.tm_caps.max_sge		= attr.tm_caps.max_sge;
-	resp.xrq_caps.flags		= attr.xrq_caps.flags;
+	resp.tm_caps.flags		= attr.tm_caps.flags;
-	resp.response_length += sizeof(resp.xrq_caps);
+	resp.response_length += sizeof(resp.tm_caps);
 end:
 	err = ib_copy_to_udata(ucore, &resp, resp.response_length);
 	return err;

drivers/infiniband/hw/hfi1/chip.c

@@ -1066,6 +1066,8 @@ static int read_idle_sma(struct hfi1_devdata *dd, u64 *data);
 static int thermal_init(struct hfi1_devdata *dd);
 
 static void update_statusp(struct hfi1_pportdata *ppd, u32 state);
+static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd,
+					    int msecs);
 static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state,
 				  int msecs);
 static void log_state_transition(struct hfi1_pportdata *ppd, u32 state);
@@ -8238,6 +8240,7 @@ static irqreturn_t general_interrupt(int irq, void *data)
 	u64 regs[CCE_NUM_INT_CSRS];
 	u32 bit;
 	int i;
+	irqreturn_t handled = IRQ_NONE;
 
 	this_cpu_inc(*dd->int_counter);
 
@@ -8258,9 +8261,10 @@ static irqreturn_t general_interrupt(int irq, void *data)
 	for_each_set_bit(bit, (unsigned long *)&regs[0],
 			 CCE_NUM_INT_CSRS * 64) {
 		is_interrupt(dd, bit);
+		handled = IRQ_HANDLED;
 	}
 
-	return IRQ_HANDLED;
+	return handled;
 }
 
 static irqreturn_t sdma_interrupt(int irq, void *data)
@@ -9413,7 +9417,7 @@ static void set_qsfp_int_n(struct hfi1_pportdata *ppd, u8 enable)
 	write_csr(dd, dd->hfi1_id ? ASIC_QSFP2_MASK : ASIC_QSFP1_MASK, mask);
 }
 
-void reset_qsfp(struct hfi1_pportdata *ppd)
+int reset_qsfp(struct hfi1_pportdata *ppd)
 {
 	struct hfi1_devdata *dd = ppd->dd;
 	u64 mask, qsfp_mask;
@@ -9443,6 +9447,13 @@ void reset_qsfp(struct hfi1_pportdata *ppd)
 	 * for alarms and warnings
 	 */
 	set_qsfp_int_n(ppd, 1);
+
+	/*
+	 * After the reset, AOC transmitters are enabled by default. They need
+	 * to be turned off to complete the QSFP setup before they can be
+	 * enabled again.
+	 */
+	return set_qsfp_tx(ppd, 0);
 }
 
 static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd,
@@ -10305,6 +10316,7 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason)
 {
 	struct hfi1_devdata *dd = ppd->dd;
 	u32 previous_state;
+	int offline_state_ret;
 	int ret;
 
 	update_lcb_cache(dd);
@@ -10326,28 +10338,11 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason)
 		ppd->offline_disabled_reason =
 		HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT);
 
-	/*
+	offline_state_ret = wait_phys_link_offline_substates(ppd, 10000);
-	 * Wait for offline transition. It can take a while for
+	if (offline_state_ret < 0)
-	 * the link to go down.
+		return offline_state_ret;
-	 */
-	ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 10000);
-	if (ret < 0)
-		return ret;
-
-	/*
-	 * Now in charge of LCB - must be after the physical state is
-	 * offline.quiet and before host_link_state is changed.
-	 */
-	set_host_lcb_access(dd);
-	write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */
-
-	/* make sure the logical state is also down */
-	ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000);
-	if (ret)
-		force_logical_link_state_down(ppd);
-
-	ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */
 
+	/* Disabling AOC transmitters */
 	if (ppd->port_type == PORT_TYPE_QSFP &&
 	    ppd->qsfp_info.limiting_active &&
 	    qsfp_mod_present(ppd)) {
@@ -10364,6 +10359,30 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason)
 		}
 	}
 
+	/*
+	 * Wait for the offline.Quiet transition if it hasn't happened yet. It
+	 * can take a while for the link to go down.
+	 */
+	if (offline_state_ret != PLS_OFFLINE_QUIET) {
+		ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 30000);
+		if (ret < 0)
+			return ret;
+	}
+
+	/*
+	 * Now in charge of LCB - must be after the physical state is
+	 * offline.quiet and before host_link_state is changed.
+	 */
+	set_host_lcb_access(dd);
+	write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */
+
+	/* make sure the logical state is also down */
+	ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000);
+	if (ret)
+		force_logical_link_state_down(ppd);
+
+	ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */
+
 	/*
 	 * The LNI has a mandatory wait time after the physical state
 	 * moves to Offline.Quiet.  The wait time may be different
@@ -10396,6 +10415,9 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason)
 			& (HLS_DN_POLL | HLS_VERIFY_CAP | HLS_GOING_UP)) {
 		/* went down while attempting link up */
 		check_lni_states(ppd);
+
+		/* The QSFP doesn't need to be reset on LNI failure */
+		ppd->qsfp_info.reset_needed = 0;
 	}
 
 	/* the active link width (downgrade) is 0 on link down */
@@ -12804,6 +12826,39 @@ static int wait_physical_linkstate(struct hfi1_pportdata *ppd, u32 state,
 	return 0;
 }
 
+/*
+ * wait_phys_link_offline_quiet_substates - wait for any offline substate
+ * @ppd: port device
+ * @msecs: the number of milliseconds to wait
+ *
+ * Wait up to msecs milliseconds for any offline physical link
+ * state change to occur.
+ * Returns 0 if at least one state is reached, otherwise -ETIMEDOUT.
+ */
+static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd,
+					    int msecs)
+{
+	u32 read_state;
+	unsigned long timeout;
+
+	timeout = jiffies + msecs_to_jiffies(msecs);
+	while (1) {
+		read_state = read_physical_state(ppd->dd);
+		if ((read_state & 0xF0) == PLS_OFFLINE)
+			break;
+		if (time_after(jiffies, timeout)) {
+			dd_dev_err(ppd->dd,
+				   "timeout waiting for phy link offline.quiet substates. Read state 0x%x, %dms\n",
+				   read_state, msecs);
+			return -ETIMEDOUT;
+		}
+		usleep_range(1950, 2050); /* sleep 2ms-ish */
+	}
+
+	log_state_transition(ppd, read_state);
+	return read_state;
+}
+
 #define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \
 (r &= ~SEND_CTXT_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK)
 

drivers/infiniband/hw/hfi1/chip.h

@@ -204,6 +204,7 @@
 #define PLS_OFFLINE_READY_TO_QUIET_LT	   0x92
 #define PLS_OFFLINE_REPORT_FAILURE		   0x93
 #define PLS_OFFLINE_READY_TO_QUIET_BCC	   0x94
+#define PLS_OFFLINE_QUIET_DURATION	   0x95
 #define PLS_POLLING				   0x20
 #define PLS_POLLING_QUIET			   0x20
 #define PLS_POLLING_ACTIVE			   0x21
@@ -722,7 +723,7 @@ void handle_link_downgrade(struct work_struct *work);
 void handle_link_bounce(struct work_struct *work);
 void handle_start_link(struct work_struct *work);
 void handle_sma_message(struct work_struct *work);
-void reset_qsfp(struct hfi1_pportdata *ppd);
+int reset_qsfp(struct hfi1_pportdata *ppd);
 void qsfp_event(struct work_struct *work);
 void start_freeze_handling(struct hfi1_pportdata *ppd, int flags);
 int send_idle_sma(struct hfi1_devdata *dd, u64 message);

drivers/infiniband/hw/hfi1/eprom.c

@@ -204,7 +204,10 @@ int eprom_init(struct hfi1_devdata *dd)
 	return ret;
 }
 
-/* magic character sequence that trails an image */
+/* magic character sequence that begins an image */
+#define IMAGE_START_MAGIC "APO="
+
+/* magic character sequence that might trail an image */
 #define IMAGE_TRAIL_MAGIC "egamiAPO"
 
 /* EPROM file types */
@@ -250,6 +253,7 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data,
 {
 	void *buffer;
 	void *p;
+	u32 length;
 	int ret;
 
 	buffer = kmalloc(P1_SIZE, GFP_KERNEL);
@@ -262,15 +266,21 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data,
 		return ret;
 	}
 
-	/* scan for image magic that may trail the actual data */
+	/* config partition is valid only if it starts with IMAGE_START_MAGIC */
-	p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE);
+	if (memcmp(buffer, IMAGE_START_MAGIC, strlen(IMAGE_START_MAGIC))) {
-	if (!p) {
 		kfree(buffer);
 		return -ENOENT;
 	}
 
+	/* scan for image magic that may trail the actual data */
+	p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE);
+	if (p)
+		length = p - buffer;
+	else
+		length = P1_SIZE;
+
 	*data = buffer;
-	*size = p - buffer;
+	*size = length;
 	return 0;
 }
 

drivers/infiniband/hw/hfi1/file_ops.c

@@ -930,15 +930,8 @@ static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo)
 	switch (ret) {
 	case 0:
 		ret = setup_base_ctxt(fd, uctxt);
-		if (uctxt->subctxt_cnt) {
+		if (ret)
-			/*
+			deallocate_ctxt(uctxt);
-			 * Base context is done (successfully or not), notify
-			 * anybody using a sub-context that is waiting for
-			 * this completion.
-			 */
-			clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags);
-			wake_up(&uctxt->wait);
-		}
 		break;
 	case 1:
 		ret = complete_subctxt(fd);
@@ -1305,25 +1298,25 @@ static int setup_base_ctxt(struct hfi1_filedata *fd,
 	/* Now allocate the RcvHdr queue and eager buffers. */
 	ret = hfi1_create_rcvhdrq(dd, uctxt);
 	if (ret)
-		return ret;
+		goto done;
 
 	ret = hfi1_setup_eagerbufs(uctxt);
 	if (ret)
-		goto setup_failed;
+		goto done;
 
 	/* If sub-contexts are enabled, do the appropriate setup */
 	if (uctxt->subctxt_cnt)
 		ret = setup_subctxt(uctxt);
 	if (ret)
-		goto setup_failed;
+		goto done;
 
 	ret = hfi1_alloc_ctxt_rcv_groups(uctxt);
 	if (ret)
-		goto setup_failed;
+		goto done;
 
 	ret = init_user_ctxt(fd, uctxt);
 	if (ret)
-		goto setup_failed;
+		goto done;
 
 	user_init(uctxt);
 
@@ -1331,12 +1324,22 @@ static int setup_base_ctxt(struct hfi1_filedata *fd,
 	fd->uctxt = uctxt;
 	hfi1_rcd_get(uctxt);
 
-	return 0;
+done:
+	if (uctxt->subctxt_cnt) {
+		/*
+		 * On error, set the failed bit so sub-contexts will clean up
+		 * correctly.
+		 */
+		if (ret)
+			set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags);
 
-setup_failed:
+		/*
-	/* Set the failed bit so sub-context init can do the right thing */
+		 * Base context is done (successfully or not), notify anybody
-	set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags);
+		 * using a sub-context that is waiting for this completion.
-	deallocate_ctxt(uctxt);
+		 */
+		clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags);
+		wake_up(&uctxt->wait);
+	}
 
 	return ret;
 }

drivers/infiniband/hw/hfi1/pcie.c

@@ -68,7 +68,7 @@
 /*
  * Code to adjust PCIe capabilities.
  */
-static int tune_pcie_caps(struct hfi1_devdata *);
+static void tune_pcie_caps(struct hfi1_devdata *);
 
 /*
  * Do all the common PCIe setup and initialization.
@@ -351,7 +351,7 @@ int pcie_speeds(struct hfi1_devdata *dd)
  */
 int request_msix(struct hfi1_devdata *dd, u32 msireq)
 {
-	int nvec, ret;
+	int nvec;
 
 	nvec = pci_alloc_irq_vectors(dd->pcidev, 1, msireq,
 				     PCI_IRQ_MSIX | PCI_IRQ_LEGACY);
@@ -360,12 +360,7 @@ int request_msix(struct hfi1_devdata *dd, u32 msireq)
 		return nvec;
 	}
 
-	ret = tune_pcie_caps(dd);
+	tune_pcie_caps(dd);
-	if (ret) {
-		dd_dev_err(dd, "tune_pcie_caps() failed: %d\n", ret);
-		pci_free_irq_vectors(dd->pcidev);
-		return ret;
-	}
 
 	/* check for legacy IRQ */
 	if (nvec == 1 && !dd->pcidev->msix_enabled)
@@ -502,7 +497,7 @@ uint aspm_mode = ASPM_MODE_DISABLED;
 module_param_named(aspm, aspm_mode, uint, S_IRUGO);
 MODULE_PARM_DESC(aspm, "PCIe ASPM: 0: disable, 1: enable, 2: dynamic");
 
-static int tune_pcie_caps(struct hfi1_devdata *dd)
+static void tune_pcie_caps(struct hfi1_devdata *dd)
 {
 	struct pci_dev *parent;
 	u16 rc_mpss, rc_mps, ep_mpss, ep_mps;
@@ -513,22 +508,14 @@ static int tune_pcie_caps(struct hfi1_devdata *dd)
 	 * Turn on extended tags in DevCtl in case the BIOS has turned it off
 	 * to improve WFR SDMA bandwidth
 	 */
-	ret = pcie_capability_read_word(dd->pcidev,
+	ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &ectl);
-					PCI_EXP_DEVCTL, &ectl);
+	if ((!ret) && !(ectl & PCI_EXP_DEVCTL_EXT_TAG)) {
-	if (ret) {
-		dd_dev_err(dd, "Unable to read from PCI config\n");
-		return ret;
-	}
-
-	if (!(ectl & PCI_EXP_DEVCTL_EXT_TAG)) {
 		dd_dev_info(dd, "Enabling PCIe extended tags\n");
 		ectl |= PCI_EXP_DEVCTL_EXT_TAG;
 		ret = pcie_capability_write_word(dd->pcidev,
 						 PCI_EXP_DEVCTL, ectl);
-		if (ret) {
+		if (ret)
-			dd_dev_err(dd, "Unable to write to PCI config\n");
+			dd_dev_info(dd, "Unable to write to PCI config\n");
-			return ret;
-		}
 	}
 	/* Find out supported and configured values for parent (root) */
 	parent = dd->pcidev->bus->self;
@@ -536,15 +523,22 @@ static int tune_pcie_caps(struct hfi1_devdata *dd)
 	 * The driver cannot perform the tuning if it does not have
 	 * access to the upstream component.
 	 */
-	if (!parent)
+	if (!parent) {
-		return -EINVAL;
+		dd_dev_info(dd, "Parent not found\n");
+		return;
+	}
 	if (!pci_is_root_bus(parent->bus)) {
 		dd_dev_info(dd, "Parent not root\n");
-		return -EINVAL;
+		return;
+	}
+	if (!pci_is_pcie(parent)) {
+		dd_dev_info(dd, "Parent is not PCI Express capable\n");
+		return;
+	}
+	if (!pci_is_pcie(dd->pcidev)) {
+		dd_dev_info(dd, "PCI device is not PCI Express capable\n");
+		return;
 	}
-
-	if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev))
-		return -EINVAL;
 	rc_mpss = parent->pcie_mpss;
 	rc_mps = ffs(pcie_get_mps(parent)) - 8;
 	/* Find out supported and configured values for endpoint (us) */
@@ -590,8 +584,6 @@ static int tune_pcie_caps(struct hfi1_devdata *dd)
 		ep_mrrs = max_mrrs;
 		pcie_set_readrq(dd->pcidev, ep_mrrs);
 	}
-
-	return 0;
 }
 
 /* End of PCIe capability tuning */

drivers/infiniband/hw/hfi1/platform.c

@@ -790,7 +790,9 @@ static int tune_active_qsfp(struct hfi1_pportdata *ppd, u32 *ptr_tx_preset,
 	 * reuse of stale settings established in our previous pass through.
 	 */
 	if (ppd->qsfp_info.reset_needed) {
-		reset_qsfp(ppd);
+		ret = reset_qsfp(ppd);
+		if (ret)
+			return ret;
 		refresh_qsfp_cache(ppd, &ppd->qsfp_info);
 	} else {
 		ppd->qsfp_info.reset_needed = 1;

drivers/infiniband/hw/mlx5/main.c

@@ -778,13 +778,13 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	}
 
 	if (MLX5_CAP_GEN(mdev, tag_matching)) {
-		props->xrq_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE;
+		props->tm_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE;
-		props->xrq_caps.max_num_tags =
+		props->tm_caps.max_num_tags =
 			(1 << MLX5_CAP_GEN(mdev, log_tag_matching_list_sz)) - 1;
-		props->xrq_caps.flags = IB_TM_CAP_RC;
+		props->tm_caps.flags = IB_TM_CAP_RC;
-		props->xrq_caps.max_ops =
+		props->tm_caps.max_ops =
 			1 << MLX5_CAP_GEN(mdev, log_max_qp_sz);
-		props->xrq_caps.max_sge = MLX5_TM_MAX_SGE;
+		props->tm_caps.max_sge = MLX5_TM_MAX_SGE;
 	}
 
 	if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {

drivers/infiniband/hw/mlx5/mem.c

@@ -50,13 +50,9 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr,
 {
 	unsigned long tmp;
 	unsigned long m;
-	int i, k;
+	u64 base = ~0, p = 0;
-	u64 base = 0;
+	u64 len, pfn;
-	int p = 0;
+	int i = 0;
-	int skip;
-	int mask;
-	u64 len;
-	u64 pfn;
 	struct scatterlist *sg;
 	int entry;
 	unsigned long page_shift = umem->page_shift;
@@ -76,33 +72,24 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr,
 	m = find_first_bit(&tmp, BITS_PER_LONG);
 	if (max_page_shift)
 		m = min_t(unsigned long, max_page_shift - page_shift, m);
-	skip = 1 << m;
+
-	mask = skip - 1;
-	i = 0;
 	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
 		len = sg_dma_len(sg) >> page_shift;
 		pfn = sg_dma_address(sg) >> page_shift;
-		for (k = 0; k < len; k++) {
+		if (base + p != pfn) {
-			if (!(i & mask)) {
+			/* If either the offset or the new
-				tmp = (unsigned long)pfn;
+			 * base are unaligned update m
-				m = min_t(unsigned long, m, find_first_bit(&tmp, BITS_PER_LONG));
+			 */
-				skip = 1 << m;
+			tmp = (unsigned long)(pfn | p);
-				mask = skip - 1;
+			if (!IS_ALIGNED(tmp, 1 << m))
-				base = pfn;
+				m = find_first_bit(&tmp, BITS_PER_LONG);
-				p = 0;
+
-			} else {
+			base = pfn;
-				if (base + p != pfn) {
+			p = 0;
-					tmp = (unsigned long)p;
-					m = find_first_bit(&tmp, BITS_PER_LONG);
-					skip = 1 << m;
-					mask = skip - 1;
-					base = pfn;
-					p = 0;
-				}
-			}
-			p++;
-			i++;
 		}
+
+		p += len;
+		i += len;
 	}
 
 	if (i) {

drivers/infiniband/hw/mlx5/mr.c

@@ -47,7 +47,8 @@ enum {
 
 #define MLX5_UMR_ALIGN 2048
 
-static int clean_mr(struct mlx5_ib_mr *mr);
+static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
+static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
 static int mr_cache_max_order(struct mlx5_ib_dev *dev);
 static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
 
@@ -1270,8 +1271,9 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 		err = mlx5_ib_update_xlt(mr, 0, ncont, page_shift,
 					 update_xlt_flags);
+
 		if (err) {
-			mlx5_ib_dereg_mr(&mr->ibmr);
+			dereg_mr(dev, mr);
 			return ERR_PTR(err);
 		}
 	}
@@ -1356,7 +1358,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 		err = mr_umem_get(pd, addr, len, access_flags, &mr->umem,
 				  &npages, &page_shift, &ncont, &order);
 		if (err < 0) {
-			clean_mr(mr);
+			clean_mr(dev, mr);
 			return err;
 		}
 	}
@@ -1410,7 +1412,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 		if (err) {
 			mlx5_ib_warn(dev, "Failed to rereg UMR\n");
 			ib_umem_release(mr->umem);
-			clean_mr(mr);
+			clean_mr(dev, mr);
 			return err;
 		}
 	}
@@ -1469,9 +1471,8 @@ mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
 	}
 }
 
-static int clean_mr(struct mlx5_ib_mr *mr)
+static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 {
-	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
 	int allocated_from_cache = mr->allocated_from_cache;
 	int err;
 
@@ -1507,10 +1508,8 @@ static int clean_mr(struct mlx5_ib_mr *mr)
 	return 0;
 }
 
-int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
+static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 {
-	struct mlx5_ib_dev *dev = to_mdev(ibmr->device);
-	struct mlx5_ib_mr *mr = to_mmr(ibmr);
 	int npages = mr->npages;
 	struct ib_umem *umem = mr->umem;
 
@@ -1539,7 +1538,7 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
 	}
 #endif
 
-	clean_mr(mr);
+	clean_mr(dev, mr);
 
 	if (umem) {
 		ib_umem_release(umem);
@@ -1549,6 +1548,14 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
 	return 0;
 }
 
+int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibmr->device);
+	struct mlx5_ib_mr *mr = to_mmr(ibmr);
+
+	return dereg_mr(dev, mr);
+}
+
 struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd,
 			       enum ib_mr_type mr_type,
 			       u32 max_num_sg)

drivers/infiniband/hw/nes/nes_verbs.c

@@ -3232,7 +3232,7 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr,
 					    mr->ibmr.iova);
 			set_wqe_32bit_value(wqe->wqe_words,
 					    NES_IWARP_SQ_FMR_WQE_LENGTH_LOW_IDX,
-					    mr->ibmr.length);
+					    lower_32_bits(mr->ibmr.length));
 			set_wqe_32bit_value(wqe->wqe_words,
 					    NES_IWARP_SQ_FMR_WQE_LENGTH_HIGH_IDX, 0);
 			set_wqe_32bit_value(wqe->wqe_words,
@@ -3274,7 +3274,7 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr,
 					    mr->npages * 8);
 
 			nes_debug(NES_DBG_IW_TX, "SQ_REG_MR: iova_start: %llx, "
-				  "length: %d, rkey: %0x, pgl_paddr: %llx, "
+				  "length: %lld, rkey: %0x, pgl_paddr: %llx, "
 				  "page_list_len: %u, wqe_misc: %x\n",
 				  (unsigned long long) mr->ibmr.iova,
 				  mr->ibmr.length,

drivers/infiniband/ulp/ipoib/ipoib_ib.c

@@ -1000,19 +1000,6 @@ static inline int update_parent_pkey(struct ipoib_dev_priv *priv)
 		 */
 		priv->dev->broadcast[8] = priv->pkey >> 8;
 		priv->dev->broadcast[9] = priv->pkey & 0xff;
-
-		/*
-		 * Update the broadcast address in the priv->broadcast object,
-		 * in case it already exists, otherwise no one will do that.
-		 */
-		if (priv->broadcast) {
-			spin_lock_irq(&priv->lock);
-			memcpy(priv->broadcast->mcmember.mgid.raw,
-			       priv->dev->broadcast + 4,
-			sizeof(union ib_gid));
-			spin_unlock_irq(&priv->lock);
-		}
-
 		return 0;
 	}
 

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -2180,6 +2180,7 @@ static struct net_device *ipoib_add_port(const char *format,
 {
 	struct ipoib_dev_priv *priv;
 	struct ib_port_attr attr;
+	struct rdma_netdev *rn;
 	int result = -ENOMEM;
 
 	priv = ipoib_intf_alloc(hca, port, format);
@@ -2279,7 +2280,8 @@ static struct net_device *ipoib_add_port(const char *format,
 	ipoib_dev_cleanup(priv->dev);
 
 device_init_failed:
-	free_netdev(priv->dev);
+	rn = netdev_priv(priv->dev);
+	rn->free_rdma_netdev(priv->dev);
 	kfree(priv);
 
 alloc_mem_failed:
@@ -2328,7 +2330,7 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data)
 		return;
 
 	list_for_each_entry_safe(priv, tmp, dev_list, list) {
-		struct rdma_netdev *rn = netdev_priv(priv->dev);
+		struct rdma_netdev *parent_rn = netdev_priv(priv->dev);
 
 		ib_unregister_event_handler(&priv->event_handler);
 		flush_workqueue(ipoib_workqueue);
@@ -2350,10 +2352,15 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data)
 		unregister_netdev(priv->dev);
 		mutex_unlock(&priv->sysfs_mutex);
 
-		rn->free_rdma_netdev(priv->dev);
+		parent_rn->free_rdma_netdev(priv->dev);
 
-		list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list)
+		list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) {
+			struct rdma_netdev *child_rn;
+
+			child_rn = netdev_priv(cpriv->dev);
+			child_rn->free_rdma_netdev(cpriv->dev);
 			kfree(cpriv);
+		}
 
 		kfree(priv);
 	}

drivers/infiniband/ulp/ipoib/ipoib_vlan.c

@@ -141,14 +141,17 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 		return restart_syscall();
 	}
 
-	priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name);
+	if (!down_write_trylock(&ppriv->vlan_rwsem)) {
-	if (!priv) {
 		rtnl_unlock();
 		mutex_unlock(&ppriv->sysfs_mutex);
-		return -ENOMEM;
+		return restart_syscall();
 	}
 
-	down_write(&ppriv->vlan_rwsem);
+	priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name);
+	if (!priv) {
+		result = -ENOMEM;
+		goto out;
+	}
 
 	/*
 	 * First ensure this isn't a duplicate. We check the parent device and
@@ -175,8 +178,11 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 	rtnl_unlock();
 	mutex_unlock(&ppriv->sysfs_mutex);
 
-	if (result) {
+	if (result && priv) {
-		free_netdev(priv->dev);
+		struct rdma_netdev *rn;
+
+		rn = netdev_priv(priv->dev);
+		rn->free_rdma_netdev(priv->dev);
 		kfree(priv);
 	}
 
@@ -204,7 +210,12 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 		return restart_syscall();
 	}
 
-	down_write(&ppriv->vlan_rwsem);
+	if (!down_write_trylock(&ppriv->vlan_rwsem)) {
+		rtnl_unlock();
+		mutex_unlock(&ppriv->sysfs_mutex);
+		return restart_syscall();
+	}
+
 	list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) {
 		if (priv->pkey == pkey &&
 		    priv->child_type == IPOIB_LEGACY_CHILD) {
@@ -224,7 +235,10 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 	mutex_unlock(&ppriv->sysfs_mutex);
 
 	if (dev) {
-		free_netdev(dev);
+		struct rdma_netdev *rn;
+
+		rn = netdev_priv(dev);
+		rn->free_rdma_netdev(priv->dev);
 		kfree(priv);
 		return 0;
 	}

drivers/infiniband/ulp/iser/iser_memory.c

@@ -154,7 +154,7 @@ static void iser_dump_page_vec(struct iser_page_vec *page_vec)
 {
 	int i;
 
-	iser_err("page vec npages %d data length %d\n",
+	iser_err("page vec npages %d data length %lld\n",
 		 page_vec->npages, page_vec->fake_mr.length);
 	for (i = 0; i < page_vec->npages; i++)
 		iser_err("vec[%d]: %llx\n", i, page_vec->pages[i]);

drivers/iommu/amd_iommu_init.c

@@ -874,7 +874,7 @@ static bool copy_device_table(void)
 		hi = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET + 4);
 		entry = (((u64) hi) << 32) + lo;
 		if (last_entry && last_entry != entry) {
-			pr_err("IOMMU:%d should use the same dev table as others!/n",
+			pr_err("IOMMU:%d should use the same dev table as others!\n",
 				iommu->index);
 			return false;
 		}
@@ -882,7 +882,7 @@ static bool copy_device_table(void)
 
 		old_devtb_size = ((entry & ~PAGE_MASK) + 1) << 12;
 		if (old_devtb_size != dev_table_size) {
-			pr_err("The device table size of IOMMU:%d is not expected!/n",
+			pr_err("The device table size of IOMMU:%d is not expected!\n",
 				iommu->index);
 			return false;
 		}
@@ -890,7 +890,7 @@ static bool copy_device_table(void)
 
 	old_devtb_phys = entry & PAGE_MASK;
 	if (old_devtb_phys >= 0x100000000ULL) {
-		pr_err("The address of old device table is above 4G, not trustworthy!/n");
+		pr_err("The address of old device table is above 4G, not trustworthy!\n");
 		return false;
 	}
 	old_devtb = memremap(old_devtb_phys, dev_table_size, MEMREMAP_WB);
@@ -901,7 +901,7 @@ static bool copy_device_table(void)
 	old_dev_tbl_cpy = (void *)__get_free_pages(gfp_flag,
 				get_order(dev_table_size));
 	if (old_dev_tbl_cpy == NULL) {
-		pr_err("Failed to allocate memory for copying old device table!/n");
+		pr_err("Failed to allocate memory for copying old device table!\n");
 		return false;
 	}
 

drivers/iommu/io-pgtable-arm-v7s.c

@@ -245,7 +245,7 @@ static void __arm_v7s_free_table(void *table, int lvl,
 static void __arm_v7s_pte_sync(arm_v7s_iopte *ptep, int num_entries,
 			       struct io_pgtable_cfg *cfg)
 {
-	if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA))
+	if (cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)
 		return;
 
 	dma_sync_single_for_device(cfg->iommu_dev, __arm_v7s_dma_addr(ptep),

drivers/iommu/mtk_iommu.c

@@ -371,7 +371,8 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
 	int ret;
 
 	spin_lock_irqsave(&dom->pgtlock, flags);
-	ret = dom->iop->map(dom->iop, iova, paddr, size, prot);
+	ret = dom->iop->map(dom->iop, iova, paddr & DMA_BIT_MASK(32),
+			    size, prot);
 	spin_unlock_irqrestore(&dom->pgtlock, flags);
 
 	return ret;

drivers/irqchip/irq-mips-gic.c

@@ -175,14 +175,13 @@ static void gic_mask_irq(struct irq_data *d)
 
 static void gic_unmask_irq(struct irq_data *d)
 {
-	struct cpumask *affinity = irq_data_get_affinity_mask(d);
 	unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq);
 	unsigned int cpu;
 
 	write_gic_smask(intr);
 
 	gic_clear_pcpu_masks(intr);
-	cpu = cpumask_first_and(affinity, cpu_online_mask);
+	cpu = cpumask_first(irq_data_get_effective_affinity_mask(d));
 	set_bit(intr, per_cpu_ptr(pcpu_masks, cpu));
 }
 
@@ -420,13 +419,17 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq,
 				     irq_hw_number_t hw, unsigned int cpu)
 {
 	int intr = GIC_HWIRQ_TO_SHARED(hw);
+	struct irq_data *data;
 	unsigned long flags;
 
+	data = irq_get_irq_data(virq);
+
 	spin_lock_irqsave(&gic_lock, flags);
 	write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin);
 	write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu)));
 	gic_clear_pcpu_masks(intr);
 	set_bit(intr, per_cpu_ptr(pcpu_masks, cpu));
+	irq_data_update_effective_affinity(data, cpumask_of(cpu));
 	spin_unlock_irqrestore(&gic_lock, flags);
 
 	return 0;
@@ -645,7 +648,7 @@ static int __init gic_of_init(struct device_node *node,
 
 	/* Find the first available CPU vector. */
 	i = 0;
-	reserved = (C_SW0 | C_SW1) >> __fls(C_SW0);
+	reserved = (C_SW0 | C_SW1) >> __ffs(C_SW0);
 	while (!of_property_read_u32_index(node, "mti,reserved-cpu-vectors",
 					   i++, &cpu_vec))
 		reserved |= BIT(cpu_vec);
@@ -684,11 +687,11 @@ static int __init gic_of_init(struct device_node *node,
 
 	gicconfig = read_gic_config();
 	gic_shared_intrs = gicconfig & GIC_CONFIG_NUMINTERRUPTS;
-	gic_shared_intrs >>= __fls(GIC_CONFIG_NUMINTERRUPTS);
+	gic_shared_intrs >>= __ffs(GIC_CONFIG_NUMINTERRUPTS);
 	gic_shared_intrs = (gic_shared_intrs + 1) * 8;
 
 	gic_vpes = gicconfig & GIC_CONFIG_PVPS;
-	gic_vpes >>= __fls(GIC_CONFIG_PVPS);
+	gic_vpes >>= __ffs(GIC_CONFIG_PVPS);
 	gic_vpes = gic_vpes + 1;
 
 	if (cpu_has_veic) {

drivers/leds/leds-as3645a.c

@@ -112,6 +112,10 @@
 #define AS_PEAK_mA_TO_REG(a) \
 	((min_t(u32, AS_PEAK_mA_MAX, a) - 1250) / 250)
 
+/* LED numbers for Devicetree */
+#define AS_LED_FLASH				0
+#define AS_LED_INDICATOR			1
+
 enum as_mode {
 	AS_MODE_EXT_TORCH = 0 << AS_CONTROL_MODE_SETTING_SHIFT,
 	AS_MODE_INDICATOR = 1 << AS_CONTROL_MODE_SETTING_SHIFT,
@@ -491,10 +495,29 @@ static int as3645a_parse_node(struct as3645a *flash,
 			      struct device_node *node)
 {
 	struct as3645a_config *cfg = &flash->cfg;
+	struct device_node *child;
 	const char *name;
 	int rval;
 
-	flash->flash_node = of_get_child_by_name(node, "flash");
+	for_each_child_of_node(node, child) {
+		u32 id = 0;
+
+		of_property_read_u32(child, "reg", &id);
+
+		switch (id) {
+		case AS_LED_FLASH:
+			flash->flash_node = of_node_get(child);
+			break;
+		case AS_LED_INDICATOR:
+			flash->indicator_node = of_node_get(child);
+			break;
+		default:
+			dev_warn(&flash->client->dev,
+				 "unknown LED %u encountered, ignoring\n", id);
+			break;
+		}
+	}
+
 	if (!flash->flash_node) {
 		dev_err(&flash->client->dev, "can't find flash node\n");
 		return -ENODEV;
@@ -534,11 +557,10 @@ static int as3645a_parse_node(struct as3645a *flash,
 	of_property_read_u32(flash->flash_node, "voltage-reference",
 			     &cfg->voltage_reference);
 
-	of_property_read_u32(flash->flash_node, "peak-current-limit",
+	of_property_read_u32(flash->flash_node, "ams,input-max-microamp",
 			     &cfg->peak);
 	cfg->peak = AS_PEAK_mA_TO_REG(cfg->peak);
 
-	flash->indicator_node = of_get_child_by_name(node, "indicator");
 	if (!flash->indicator_node) {
 		dev_warn(&flash->client->dev,
 			 "can't find indicator node\n");
@@ -721,6 +743,7 @@ static int as3645a_remove(struct i2c_client *client)
 	as3645a_set_control(flash, AS_MODE_EXT_TORCH, false);
 
 	v4l2_flash_release(flash->vf);
+	v4l2_flash_release(flash->vfind);
 
 	led_classdev_flash_unregister(&flash->fled);
 	led_classdev_unregister(&flash->iled_cdev);

drivers/md/dm-raid.c

@@ -3238,7 +3238,7 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
 	if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
 		return DM_MAPIO_REQUEUE;
 
-	mddev->pers->make_request(mddev, bio);
+	md_handle_request(mddev, bio);
 
 	return DM_MAPIO_SUBMITTED;
 }

drivers/md/md.c

@@ -266,6 +266,37 @@ static DEFINE_SPINLOCK(all_mddevs_lock);
  * call has finished, the bio has been linked into some internal structure
  * and so is visible to ->quiesce(), so we don't need the refcount any more.
  */
+void md_handle_request(struct mddev *mddev, struct bio *bio)
+{
+check_suspended:
+	rcu_read_lock();
+	if (mddev->suspended) {
+		DEFINE_WAIT(__wait);
+		for (;;) {
+			prepare_to_wait(&mddev->sb_wait, &__wait,
+					TASK_UNINTERRUPTIBLE);
+			if (!mddev->suspended)
+				break;
+			rcu_read_unlock();
+			schedule();
+			rcu_read_lock();
+		}
+		finish_wait(&mddev->sb_wait, &__wait);
+	}
+	atomic_inc(&mddev->active_io);
+	rcu_read_unlock();
+
+	if (!mddev->pers->make_request(mddev, bio)) {
+		atomic_dec(&mddev->active_io);
+		wake_up(&mddev->sb_wait);
+		goto check_suspended;
+	}
+
+	if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
+		wake_up(&mddev->sb_wait);
+}
+EXPORT_SYMBOL(md_handle_request);
+
 static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
@@ -285,23 +316,6 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 		bio_endio(bio);
 		return BLK_QC_T_NONE;
 	}
-check_suspended:
-	rcu_read_lock();
-	if (mddev->suspended) {
-		DEFINE_WAIT(__wait);
-		for (;;) {
-			prepare_to_wait(&mddev->sb_wait, &__wait,
-					TASK_UNINTERRUPTIBLE);
-			if (!mddev->suspended)
-				break;
-			rcu_read_unlock();
-			schedule();
-			rcu_read_lock();
-		}
-		finish_wait(&mddev->sb_wait, &__wait);
-	}
-	atomic_inc(&mddev->active_io);
-	rcu_read_unlock();
 
 	/*
 	 * save the sectors now since our bio can
@@ -310,20 +324,14 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 	sectors = bio_sectors(bio);
 	/* bio could be mergeable after passing to underlayer */
 	bio->bi_opf &= ~REQ_NOMERGE;
-	if (!mddev->pers->make_request(mddev, bio)) {
+
-		atomic_dec(&mddev->active_io);
+	md_handle_request(mddev, bio);
-		wake_up(&mddev->sb_wait);
-		goto check_suspended;
-	}
 
 	cpu = part_stat_lock();
 	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
 	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
 	part_stat_unlock();
 
-	if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
-		wake_up(&mddev->sb_wait);
-
 	return BLK_QC_T_NONE;
 }
 
@@ -439,16 +447,22 @@ static void md_submit_flush_data(struct work_struct *ws)
 	struct mddev *mddev = container_of(ws, struct mddev, flush_work);
 	struct bio *bio = mddev->flush_bio;
 
+	/*
+	 * must reset flush_bio before calling into md_handle_request to avoid a
+	 * deadlock, because other bios passed md_handle_request suspend check
+	 * could wait for this and below md_handle_request could wait for those
+	 * bios because of suspend check
+	 */
+	mddev->flush_bio = NULL;
+	wake_up(&mddev->sb_wait);
+
 	if (bio->bi_iter.bi_size == 0)
 		/* an empty barrier - all done */
 		bio_endio(bio);
 	else {
 		bio->bi_opf &= ~REQ_PREFLUSH;
-		mddev->pers->make_request(mddev, bio);
+		md_handle_request(mddev, bio);
 	}
-
-	mddev->flush_bio = NULL;
-	wake_up(&mddev->sb_wait);
 }
 
 void md_flush_request(struct mddev *mddev, struct bio *bio)

drivers/md/md.h

@@ -692,6 +692,7 @@ extern void md_stop_writes(struct mddev *mddev);
 extern int md_rdev_init(struct md_rdev *rdev);
 extern void md_rdev_clear(struct md_rdev *rdev);
 
+extern void md_handle_request(struct mddev *mddev, struct bio *bio);
 extern void mddev_suspend(struct mddev *mddev);
 extern void mddev_resume(struct mddev *mddev);
 extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,

drivers/md/raid5.c

@@ -6575,14 +6575,17 @@ static ssize_t
 raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
 {
 	struct r5conf *conf;
-	unsigned long new;
+	unsigned int new;
 	int err;
 	struct r5worker_group *new_groups, *old_groups;
 	int group_cnt, worker_cnt_per_group;
 
 	if (len >= PAGE_SIZE)
 		return -EINVAL;
-	if (kstrtoul(page, 10, &new))
+	if (kstrtouint(page, 10, &new))
+		return -EINVAL;
+	/* 8192 should be big enough */
+	if (new > 8192)
 		return -EINVAL;
 
 	err = mddev_lock(mddev);

drivers/mmc/host/sdhci-pci-core.c

@@ -392,6 +392,7 @@ static const struct sdhci_pci_fixes sdhci_intel_pch_sdio = {
 
 enum {
 	INTEL_DSM_FNS		=  0,
+	INTEL_DSM_V18_SWITCH	=  3,
 	INTEL_DSM_DRV_STRENGTH	=  9,
 	INTEL_DSM_D3_RETUNE	= 10,
 };
@@ -557,6 +558,19 @@ static void intel_hs400_enhanced_strobe(struct mmc_host *mmc,
 	sdhci_writel(host, val, INTEL_HS400_ES_REG);
 }
 
+static void sdhci_intel_voltage_switch(struct sdhci_host *host)
+{
+	struct sdhci_pci_slot *slot = sdhci_priv(host);
+	struct intel_host *intel_host = sdhci_pci_priv(slot);
+	struct device *dev = &slot->chip->pdev->dev;
+	u32 result = 0;
+	int err;
+
+	err = intel_dsm(intel_host, dev, INTEL_DSM_V18_SWITCH, &result);
+	pr_debug("%s: %s DSM error %d result %u\n",
+		 mmc_hostname(host->mmc), __func__, err, result);
+}
+
 static const struct sdhci_ops sdhci_intel_byt_ops = {
 	.set_clock		= sdhci_set_clock,
 	.set_power		= sdhci_intel_set_power,
@@ -565,6 +579,7 @@ static const struct sdhci_ops sdhci_intel_byt_ops = {
 	.reset			= sdhci_reset,
 	.set_uhs_signaling	= sdhci_set_uhs_signaling,
 	.hw_reset		= sdhci_pci_hw_reset,
+	.voltage_switch		= sdhci_intel_voltage_switch,
 };
 
 static void byt_read_dsm(struct sdhci_pci_slot *slot)

drivers/mmc/host/tmio_mmc_core.c

@@ -129,50 +129,6 @@ static int tmio_mmc_next_sg(struct tmio_mmc_host *host)
 
 #define CMDREQ_TIMEOUT	5000
 
-#ifdef CONFIG_MMC_DEBUG
-
-#define STATUS_TO_TEXT(a, status, i) \
-	do { \
-		if ((status) & TMIO_STAT_##a) { \
-			if ((i)++) \
-				printk(KERN_DEBUG " | "); \
-			printk(KERN_DEBUG #a); \
-		} \
-	} while (0)
-
-static void pr_debug_status(u32 status)
-{
-	int i = 0;
-
-	pr_debug("status: %08x = ", status);
-	STATUS_TO_TEXT(CARD_REMOVE, status, i);
-	STATUS_TO_TEXT(CARD_INSERT, status, i);
-	STATUS_TO_TEXT(SIGSTATE, status, i);
-	STATUS_TO_TEXT(WRPROTECT, status, i);
-	STATUS_TO_TEXT(CARD_REMOVE_A, status, i);
-	STATUS_TO_TEXT(CARD_INSERT_A, status, i);
-	STATUS_TO_TEXT(SIGSTATE_A, status, i);
-	STATUS_TO_TEXT(CMD_IDX_ERR, status, i);
-	STATUS_TO_TEXT(STOPBIT_ERR, status, i);
-	STATUS_TO_TEXT(ILL_FUNC, status, i);
-	STATUS_TO_TEXT(CMD_BUSY, status, i);
-	STATUS_TO_TEXT(CMDRESPEND, status, i);
-	STATUS_TO_TEXT(DATAEND, status, i);
-	STATUS_TO_TEXT(CRCFAIL, status, i);
-	STATUS_TO_TEXT(DATATIMEOUT, status, i);
-	STATUS_TO_TEXT(CMDTIMEOUT, status, i);
-	STATUS_TO_TEXT(RXOVERFLOW, status, i);
-	STATUS_TO_TEXT(TXUNDERRUN, status, i);
-	STATUS_TO_TEXT(RXRDY, status, i);
-	STATUS_TO_TEXT(TXRQ, status, i);
-	STATUS_TO_TEXT(ILL_ACCESS, status, i);
-	printk("\n");
-}
-
-#else
-#define pr_debug_status(s)  do { } while (0)
-#endif
-
 static void tmio_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
 {
 	struct tmio_mmc_host *host = mmc_priv(mmc);
@@ -762,9 +718,6 @@ irqreturn_t tmio_mmc_irq(int irq, void *devid)
 	status = sd_ctrl_read16_and_16_as_32(host, CTL_STATUS);
 	ireg = status & TMIO_MASK_IRQ & ~host->sdcard_irq_mask;
 
-	pr_debug_status(status);
-	pr_debug_status(ireg);
-
 	/* Clear the status except the interrupt status */
 	sd_ctrl_write32_as_16_and_16(host, CTL_STATUS, TMIO_MASK_IRQ);
 

drivers/mtd/mtdpart.c

@@ -581,6 +581,14 @@ static struct mtd_part *allocate_partition(struct mtd_info *parent,
 		slave->mtd.erasesize = parent->erasesize;
 	}
 
+	/*
+	 * Slave erasesize might differ from the master one if the master
+	 * exposes several regions with different erasesize. Adjust
+	 * wr_alignment accordingly.
+	 */
+	if (!(slave->mtd.flags & MTD_NO_ERASE))
+		wr_alignment = slave->mtd.erasesize;
+
 	tmp = slave->offset;
 	remainder = do_div(tmp, wr_alignment);
 	if ((slave->mtd.flags & MTD_WRITEABLE) && remainder) {

drivers/mtd/nand/atmel/pmecc.c

@@ -363,7 +363,7 @@ atmel_pmecc_create_user(struct atmel_pmecc *pmecc,
 	size += (req->ecc.strength + 1) * sizeof(u16);
 	/* Reserve space for mu, dmu and delta. */
 	size = ALIGN(size, sizeof(s32));
-	size += (req->ecc.strength + 1) * sizeof(s32);
+	size += (req->ecc.strength + 1) * sizeof(s32) * 3;
 
 	user = kzalloc(size, GFP_KERNEL);
 	if (!user)

drivers/nvme/host/core.c

@@ -134,8 +134,6 @@ static inline bool nvme_req_needs_retry(struct request *req)
 		return false;
 	if (nvme_req(req)->status & NVME_SC_DNR)
 		return false;
-	if (jiffies - req->start_time >= req->timeout)
-		return false;
 	if (nvme_req(req)->retries >= nvme_max_retries)
 		return false;
 	return true;
@@ -2590,7 +2588,7 @@ static void nvme_async_event_work(struct work_struct *work)
 		container_of(work, struct nvme_ctrl, async_event_work);
 
 	spin_lock_irq(&ctrl->lock);
-	while (ctrl->event_limit > 0) {
+	while (ctrl->state == NVME_CTRL_LIVE && ctrl->event_limit > 0) {
 		int aer_idx = --ctrl->event_limit;
 
 		spin_unlock_irq(&ctrl->lock);
@@ -2677,7 +2675,8 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 		/*FALLTHRU*/
 	case NVME_SC_ABORT_REQ:
 		++ctrl->event_limit;
-		queue_work(nvme_wq, &ctrl->async_event_work);
+		if (ctrl->state == NVME_CTRL_LIVE)
+			queue_work(nvme_wq, &ctrl->async_event_work);
 		break;
 	default:
 		break;
@@ -2692,7 +2691,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 		nvme_queue_scan(ctrl);
 		break;
 	case NVME_AER_NOTICE_FW_ACT_STARTING:
-		schedule_work(&ctrl->fw_act_work);
+		queue_work(nvme_wq, &ctrl->fw_act_work);
 		break;
 	default:
 		dev_warn(ctrl->device, "async event result %08x\n", result);

drivers/nvme/host/fabrics.c

@@ -565,6 +565,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	opts->queue_size = NVMF_DEF_QUEUE_SIZE;
 	opts->nr_io_queues = num_online_cpus();
 	opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY;
+	opts->kato = NVME_DEFAULT_KATO;
 
 	options = o = kstrdup(buf, GFP_KERNEL);
 	if (!options)
@@ -655,21 +656,22 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				goto out;
 			}
 
-			if (opts->discovery_nqn) {
-				pr_err("Discovery controllers cannot accept keep_alive_tmo != 0\n");
-				ret = -EINVAL;
-				goto out;
-			}
-
 			if (token < 0) {
 				pr_err("Invalid keep_alive_tmo %d\n", token);
 				ret = -EINVAL;
 				goto out;
-			} else if (token == 0) {
+			} else if (token == 0 && !opts->discovery_nqn) {
 				/* Allowed for debug */
 				pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n");
 			}
 			opts->kato = token;
+
+			if (opts->discovery_nqn && opts->kato) {
+				pr_err("Discovery controllers cannot accept KATO != 0\n");
+				ret = -EINVAL;
+				goto out;
+			}
+
 			break;
 		case NVMF_OPT_CTRL_LOSS_TMO:
 			if (match_int(args, &token)) {
@@ -762,8 +764,6 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	uuid_copy(&opts->host->id, &hostid);
 
 out:
-	if (!opts->discovery_nqn && !opts->kato)
-		opts->kato = NVME_DEFAULT_KATO;
 	kfree(options);
 	return ret;
 }

drivers/nvme/host/fc.c

@@ -1376,7 +1376,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 	if (atomic_read(&op->state) == FCPOP_STATE_ABORTED)
 		status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1);
 	else if (freq->status)
-		status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+		status = cpu_to_le16(NVME_SC_INTERNAL << 1);
 
 	/*
 	 * For the linux implementation, if we have an unsuccesful
@@ -1404,7 +1404,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 		 */
 		if (freq->transferred_length !=
 			be32_to_cpu(op->cmd_iu.data_len)) {
-			status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+			status = cpu_to_le16(NVME_SC_INTERNAL << 1);
 			goto done;
 		}
 		result.u64 = 0;
@@ -1421,7 +1421,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 					freq->transferred_length ||
 			     op->rsp_iu.status_code ||
 			     sqe->common.command_id != cqe->command_id)) {
-			status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+			status = cpu_to_le16(NVME_SC_INTERNAL << 1);
 			goto done;
 		}
 		result = cqe->result;
@@ -1429,7 +1429,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 		break;
 
 	default:
-		status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+		status = cpu_to_le16(NVME_SC_INTERNAL << 1);
 		goto done;
 	}
 
@@ -1989,16 +1989,17 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 	 * as well as those by FC-NVME spec.
 	 */
 	WARN_ON_ONCE(sqe->common.metadata);
-	WARN_ON_ONCE(sqe->common.dptr.prp1);
-	WARN_ON_ONCE(sqe->common.dptr.prp2);
 	sqe->common.flags |= NVME_CMD_SGL_METABUF;
 
 	/*
-	 * format SQE DPTR field per FC-NVME rules
+	 * format SQE DPTR field per FC-NVME rules:
-	 *    type=data block descr; subtype=offset;
+	 *    type=0x5     Transport SGL Data Block Descriptor
-	 *    offset is currently 0.
+	 *    subtype=0xA  Transport-specific value
+	 *    address=0
+	 *    length=length of the data series
 	 */
-	sqe->rw.dptr.sgl.type = NVME_SGL_FMT_OFFSET;
+	sqe->rw.dptr.sgl.type = (NVME_TRANSPORT_SGL_DATA_DESC << 4) |
+					NVME_SGL_FMT_TRANSPORT_A;
 	sqe->rw.dptr.sgl.length = cpu_to_le32(data_len);
 	sqe->rw.dptr.sgl.addr = 0;
 

drivers/nvme/host/pci.c

@@ -24,6 +24,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/once.h>
 #include <linux/pci.h>
 #include <linux/poison.h>
 #include <linux/t10-pi.h>
@@ -540,6 +541,20 @@ static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
 }
 #endif
 
+static void nvme_print_sgl(struct scatterlist *sgl, int nents)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sgl, sg, nents, i) {
+		dma_addr_t phys = sg_phys(sg);
+		pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d "
+			"dma_address:%pad dma_length:%d\n",
+			i, &phys, sg->offset, sg->length, &sg_dma_address(sg),
+			sg_dma_len(sg));
+	}
+}
+
 static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
@@ -622,19 +637,10 @@ static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req)
 	return BLK_STS_OK;
 
  bad_sgl:
-	if (WARN_ONCE(1, "Invalid SGL for payload:%d nents:%d\n",
+	WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents),
-				blk_rq_payload_bytes(req), iod->nents)) {
+			"Invalid SGL for payload:%d nents:%d\n",
-		for_each_sg(iod->sg, sg, iod->nents, i) {
+			blk_rq_payload_bytes(req), iod->nents);
-			dma_addr_t phys = sg_phys(sg);
-			pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d "
-			       "dma_address:%pad dma_length:%d\n", i, &phys,
-					sg->offset, sg->length,
-					&sg_dma_address(sg),
-					sg_dma_len(sg));
-		}
-	}
 	return BLK_STS_IOERR;
-
 }
 
 static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
@@ -1313,11 +1319,11 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	if (result < 0)
 		goto release_cq;
 
+	nvme_init_queue(nvmeq, qid);
 	result = queue_request_irq(nvmeq);
 	if (result < 0)
 		goto release_sq;
 
-	nvme_init_queue(nvmeq, qid);
 	return result;
 
  release_sq:
@@ -1464,6 +1470,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev)
 		return result;
 
 	nvmeq->cq_vector = 0;
+	nvme_init_queue(nvmeq, 0);
 	result = queue_request_irq(nvmeq);
 	if (result) {
 		nvmeq->cq_vector = -1;
@@ -2156,7 +2163,6 @@ static void nvme_reset_work(struct work_struct *work)
 	if (result)
 		goto out;
 
-	nvme_init_queue(dev->queues[0], 0);
 	result = nvme_alloc_admin_tags(dev);
 	if (result)
 		goto out;