Linux 5.15-rc4

-----BEGIN PGP SIGNATURE-----
 
 iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAmFaG98eHHRvcnZhbGRz
 QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGosAH/jqy5B2BIEE39O+8
 QTr3vO54SyRRuY/d98wZ+O4SPjfqfpCHuyjKt9YJpEdmzH754NC9gSPOOBegnvHI
 DfrWaivmJ5mdjN2h7+JVqjs58krUv98wWNa5xfvqUp5H7wF3WQg3AxsaMKS1PePD
 kFHfeFbxsg2gYhyhPK6gHtwLn6dEsx9bGny2bKvCh6KuJQEiUXoEcgnFzjFgLNxp
 T5zI1cNSCNUzwRIe+vqQRlfVR2JlSI4tiy0zNJWy9dQ5Z4HOSbFcEz5Df2N7qNYn
 /MqruaASmyREgo9yLHpR1BSyzrea8MCckY04ycYqKZb7gDwcrpAe4QVw2I/Fuzu9
 q//PV4I=
 =+mYg
 -----END PGP SIGNATURE-----

Merge tag 'v5.15-rc4' into media_tree

Linux 5.15-rc4

* tag 'v5.15-rc4': (320 commits)
  Linux 5.15-rc4
  elf: don't use MAP_FIXED_NOREPLACE for elf interpreter mappings
  objtool: print out the symbol type when complaining about it
  kvm: fix objtool relocation warning
  cachefiles: Fix oops in trace_cachefiles_mark_buried due to NULL object
  drm/i915: fix blank screen booting crashes
  hwmon: (w83793) Fix NULL pointer dereference by removing unnecessary structure field
  hwmon: (w83792d) Fix NULL pointer dereference by removing unnecessary structure field
  hwmon: (w83791d) Fix NULL pointer dereference by removing unnecessary structure field
  hwmon: (pmbus/mp2975) Add missed POUT attribute for page 1 mp2975 controller
  hwmon: (pmbus/ibm-cffps) max_power_out swap changes
  hwmon: (occ) Fix P10 VRM temp sensors
  thermal: Update information in MAINTAINERS
  io_uring: kill fasync
  sched: Always inline is_percpu_thread()
  sched/fair: Null terminate buffer when updating tunable_scaling
  sched/fair: Add ancestors of unthrottled undecayed cfs_rq
  perf/core: fix userpage->time_enabled of inactive events
  perf/x86/intel: Update event constraints for ICX
  perf/x86: Reset destroy callback on event init failure
  ...

Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml

@@ -31,11 +31,11 @@ properties:
 
   clocks:
     minItems: 1
-    maxItems: 3
+    maxItems: 7
 
   clock-names:
     minItems: 1
-    maxItems: 3
+    maxItems: 7
 
 required:
   - compatible
@@ -72,6 +72,32 @@ allOf:
           contains:
             enum:
               - qcom,sdm660-a2noc
+    then:
+      properties:
+        clocks:
+          items:
+            - description: Bus Clock.
+            - description: Bus A Clock.
+            - description: IPA Clock.
+            - description: UFS AXI Clock.
+            - description: Aggregate2 UFS AXI Clock.
+            - description: Aggregate2 USB3 AXI Clock.
+            - description: Config NoC USB2 AXI Clock.
+        clock-names:
+          items:
+            - const: bus
+            - const: bus_a
+            - const: ipa
+            - const: ufs_axi
+            - const: aggre2_ufs_axi
+            - const: aggre2_usb3_axi
+            - const: cfg_noc_usb2_axi
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
               - qcom,sdm660-bimc
               - qcom,sdm660-cnoc
               - qcom,sdm660-gnoc
@@ -91,6 +117,7 @@ examples:
   - |
       #include <dt-bindings/clock/qcom,rpmcc.h>
       #include <dt-bindings/clock/qcom,mmcc-sdm660.h>
+      #include <dt-bindings/clock/qcom,gcc-sdm660.h>
 
       bimc: interconnect@1008000 {
               compatible = "qcom,sdm660-bimc";
@@ -123,9 +150,20 @@ examples:
               compatible = "qcom,sdm660-a2noc";
               reg = <0x01704000 0xc100>;
               #interconnect-cells = <1>;
-              clock-names = "bus", "bus_a";
+              clock-names = "bus",
+                            "bus_a",
+                            "ipa",
+                            "ufs_axi",
+                            "aggre2_ufs_axi",
+                            "aggre2_usb3_axi",
+                            "cfg_noc_usb2_axi";
               clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>,
-                       <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>;
+                       <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>,
+                       <&rpmcc RPM_SMD_IPA_CLK>,
+                       <&gcc GCC_UFS_AXI_CLK>,
+                       <&gcc GCC_AGGRE2_UFS_AXI_CLK>,
+                       <&gcc GCC_AGGRE2_USB3_AXI_CLK>,
+                       <&gcc GCC_CFG_NOC_USB2_AXI_CLK>;
       };
 
       mnoc: interconnect@1745000 {

Documentation/hwmon/k10temp.rst

@@ -132,20 +132,3 @@ On Family 17h and Family 18h CPUs, additional temperature sensors may report
 Core Complex Die (CCD) temperatures. Up to 8 such temperatures are reported
 as temp{3..10}_input, labeled Tccd{1..8}. Actual support depends on the CPU
 variant.
-
-Various Family 17h and 18h CPUs report voltage and current telemetry
-information. The following attributes may be reported.
-
-Attribute	Label	Description
-===============	=======	================
-in0_input	Vcore	Core voltage
-in1_input	Vsoc	SoC voltage
-curr1_input	Icore	Core current
-curr2_input	Isoc	SoC current
-===============	=======	================
-
-Current values are raw (unscaled) as reported by the CPU. Core current is
-reported as multiples of 1A / LSB. SoC is reported as multiples of 0.25A
-/ LSB. The real current is board specific. Reported currents should be seen
-as rough guidance, and should be scaled using sensors3.conf as appropriate
-for a given board.

MAINTAINERS

@@ -414,7 +414,8 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
 F:	drivers/acpi/pmic/
 
 ACPI THERMAL DRIVER
-M:	Zhang Rui <rui.zhang@intel.com>
+M:	Rafael J. Wysocki <rafael@kernel.org>
+R:	Zhang Rui <rui.zhang@intel.com>
 L:	linux-acpi@vger.kernel.org
 S:	Supported
 W:	https://01.org/linux-acpi
@@ -810,7 +811,7 @@ F:	Documentation/devicetree/bindings/dma/altr,msgdma.yaml
 F:	drivers/dma/altera-msgdma.c
 
 ALTERA PIO DRIVER
-M:	Joyce Ooi <joyce.ooi@intel.com>
+M:	Mun Yew Tham <mun.yew.tham@intel.com>
 L:	linux-gpio@vger.kernel.org
 S:	Maintained
 F:	drivers/gpio/gpio-altera.c
@@ -2961,7 +2962,7 @@ F:	crypto/async_tx/
 F:	include/linux/async_tx.h
 
 AT24 EEPROM DRIVER
-M:	Bartosz Golaszewski <bgolaszewski@baylibre.com>
+M:	Bartosz Golaszewski <brgl@bgdev.pl>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git
@@ -3384,9 +3385,11 @@ F:	Documentation/networking/filter.rst
 F:	Documentation/userspace-api/ebpf/
 F:	arch/*/net/*
 F:	include/linux/bpf*
+F:	include/linux/btf*
 F:	include/linux/filter.h
 F:	include/trace/events/xdp.h
 F:	include/uapi/linux/bpf*
+F:	include/uapi/linux/btf*
 F:	include/uapi/linux/filter.h
 F:	kernel/bpf/
 F:	kernel/trace/bpf_trace.c
@@ -3820,7 +3823,6 @@ F:	drivers/scsi/mpi3mr/
 
 BROADCOM NETXTREME-E ROCE DRIVER
 M:	Selvin Xavier <selvin.xavier@broadcom.com>
-M:	Naresh Kumar PBS <nareshkumar.pbs@broadcom.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.broadcom.com
@@ -4655,7 +4657,7 @@ W:	http://linux-cifs.samba.org/
 T:	git git://git.samba.org/sfrench/cifs-2.6.git
 F:	Documentation/admin-guide/cifs/
 F:	fs/cifs/
-F:	fs/cifs_common/
+F:	fs/smbfs_common/
 
 COMPACTPCI HOTPLUG CORE
 M:	Scott Murray <scott@spiteful.org>
@@ -7985,7 +7987,7 @@ F:	include/linux/gpio/regmap.h
 
 GPIO SUBSYSTEM
 M:	Linus Walleij <linus.walleij@linaro.org>
-M:	Bartosz Golaszewski <bgolaszewski@baylibre.com>
+M:	Bartosz Golaszewski <brgl@bgdev.pl>
 L:	linux-gpio@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git
@@ -10194,8 +10196,8 @@ M:	Hyunchul Lee <hyc.lee@gmail.com>
 L:	linux-cifs@vger.kernel.org
 S:	Maintained
 T:	git git://git.samba.org/ksmbd.git
-F:	fs/cifs_common/
 F:	fs/ksmbd/
+F:	fs/smbfs_common/
 
 KERNEL UNIT TESTING FRAMEWORK (KUnit)
 M:	Brendan Higgins <brendanhiggins@google.com>
@@ -11367,7 +11369,7 @@ F:	Documentation/devicetree/bindings/iio/proximity/maxbotix,mb1232.yaml
 F:	drivers/iio/proximity/mb1232.c
 
 MAXIM MAX77650 PMIC MFD DRIVER
-M:	Bartosz Golaszewski <bgolaszewski@baylibre.com>
+M:	Bartosz Golaszewski <brgl@bgdev.pl>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/*/*max77650.yaml
@@ -17892,7 +17894,8 @@ M:	Olivier Moysan <olivier.moysan@foss.st.com>
 M:	Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Maintained
-F:	Documentation/devicetree/bindings/iio/adc/st,stm32-*.yaml
+F:	Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml
+F:	Documentation/devicetree/bindings/sound/st,stm32-*.yaml
 F:	sound/soc/stm/
 
 STM32 TIMER/LPTIMER DRIVERS
@@ -18556,13 +18559,14 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/radio/radio-raremono.c
 
 THERMAL
-M:	Zhang Rui <rui.zhang@intel.com>
+M:	Rafael J. Wysocki <rafael@kernel.org>
 M:	Daniel Lezcano <daniel.lezcano@linaro.org>
 R:	Amit Kucheria <amitk@kernel.org>
+R:	Zhang Rui <rui.zhang@intel.com>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 Q:	https://patchwork.kernel.org/project/linux-pm/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/thermal/linux.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git thermal
 F:	Documentation/devicetree/bindings/thermal/
 F:	drivers/thermal/
 F:	include/linux/cpu_cooling.h
@@ -18691,7 +18695,7 @@ F:	include/linux/clk/ti.h
 
 TI DAVINCI MACHINE SUPPORT
 M:	Sekhar Nori <nsekhar@ti.com>
-R:	Bartosz Golaszewski <bgolaszewski@baylibre.com>
+R:	Bartosz Golaszewski <brgl@bgdev.pl>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nsekhar/linux-davinci.git

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Opossums on Parade
 
 # *DOCUMENTATION*

arch/arm64/kvm/hyp/nvhe/Makefile

@@ -54,7 +54,7 @@ $(obj)/kvm_nvhe.tmp.o: $(obj)/hyp.lds $(addprefix $(obj)/,$(hyp-obj)) FORCE
 #    runtime. Because the hypervisor is part of the kernel binary, relocations
 #    produce a kernel VA. We enumerate relocations targeting hyp at build time
 #    and convert the kernel VAs at those positions to hyp VAs.
-$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel
+$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel FORCE
 	$(call if_changed,hyprel)
 
 # 5) Compile hyp-reloc.S and link it into the existing partially linked object.

arch/arm64/kvm/perf.c

@@ -50,9 +50,6 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = {
 
 int kvm_perf_init(void)
 {
-	if (kvm_pmu_probe_pmuver() != ID_AA64DFR0_PMUVER_IMP_DEF && !is_protected_kvm_enabled())
-		static_branch_enable(&kvm_arm_pmu_available);
-
 	return perf_register_guest_info_callbacks(&kvm_guest_cbs);
 }
 

arch/arm64/kvm/pmu-emul.c

@@ -740,7 +740,14 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	kvm_pmu_create_perf_event(vcpu, select_idx);
 }
 
-int kvm_pmu_probe_pmuver(void)
+void kvm_host_pmu_init(struct arm_pmu *pmu)
+{
+	if (pmu->pmuver != 0 && pmu->pmuver != ID_AA64DFR0_PMUVER_IMP_DEF &&
+	    !kvm_arm_support_pmu_v3() && !is_protected_kvm_enabled())
+		static_branch_enable(&kvm_arm_pmu_available);
+}
+
+static int kvm_pmu_probe_pmuver(void)
 {
 	struct perf_event_attr attr = { };
 	struct perf_event *event;

arch/m68k/68000/entry.S

@@ -15,7 +15,6 @@
 #include <asm/unistd.h>
 #include <asm/errno.h>
 #include <asm/setup.h>
-#include <asm/segment.h>
 #include <asm/traps.h>
 #include <asm/asm-offsets.h>
 #include <asm/entry.h>
@@ -25,7 +24,6 @@
 .globl system_call
 .globl resume
 .globl ret_from_exception
-.globl ret_from_signal
 .globl sys_call_table
 .globl bad_interrupt
 .globl inthandler1
@@ -59,8 +57,6 @@ do_trace:
 	subql	#4,%sp			/* dummy return address */
 	SAVE_SWITCH_STACK
 	jbsr	syscall_trace_leave
-
-ret_from_signal:
 	RESTORE_SWITCH_STACK
 	addql	#4,%sp
 	jra	ret_from_exception

arch/m68k/Kconfig

@@ -29,7 +29,6 @@ config M68K
 	select NO_DMA if !MMU && !COLDFIRE
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3
-	select SET_FS
 	select UACCESS_MEMCPY if !MMU
 	select VIRT_TO_BUS
 	select ZONE_DMA

arch/m68k/coldfire/entry.S

@@ -31,7 +31,6 @@
 #include <asm/thread_info.h>
 #include <asm/errno.h>
 #include <asm/setup.h>
-#include <asm/segment.h>
 #include <asm/asm-offsets.h>
 #include <asm/entry.h>
 
@@ -51,7 +50,6 @@ sw_usp:
 .globl system_call
 .globl resume
 .globl ret_from_exception
-.globl ret_from_signal
 .globl sys_call_table
 .globl inthandler
 
@@ -98,8 +96,6 @@ ENTRY(system_call)
 	subql	#4,%sp			/* dummy return address */
 	SAVE_SWITCH_STACK
 	jbsr	syscall_trace_leave
-
-ret_from_signal:
 	RESTORE_SWITCH_STACK
 	addql	#4,%sp
 

arch/m68k/include/asm/processor.h

@@ -9,7 +9,6 @@
 #define __ASM_M68K_PROCESSOR_H
 
 #include <linux/thread_info.h>
-#include <asm/segment.h>
 #include <asm/fpu.h>
 #include <asm/ptrace.h>
 
@@ -75,11 +74,37 @@ static inline void wrusp(unsigned long usp)
 #define TASK_UNMAPPED_BASE	0
 #endif
 
+/* Address spaces (or Function Codes in Motorola lingo) */
+#define USER_DATA     1
+#define USER_PROGRAM  2
+#define SUPER_DATA    5
+#define SUPER_PROGRAM 6
+#define CPU_SPACE     7
+
+#ifdef CONFIG_CPU_HAS_ADDRESS_SPACES
+/*
+ * Set the SFC/DFC registers for special MM operations.  For most normal
+ * operation these remain set to USER_DATA for the uaccess routines.
+ */
+static inline void set_fc(unsigned long val)
+{
+	WARN_ON_ONCE(in_interrupt());
+
+	__asm__ __volatile__ ("movec %0,%/sfc\n\t"
+			      "movec %0,%/dfc\n\t"
+			      : /* no outputs */ : "r" (val) : "memory");
+}
+#else
+static inline void set_fc(unsigned long val)
+{
+}
+#endif /* CONFIG_CPU_HAS_ADDRESS_SPACES */
+
 struct thread_struct {
 	unsigned long  ksp;		/* kernel stack pointer */
 	unsigned long  usp;		/* user stack pointer */
 	unsigned short sr;		/* saved status register */
-	unsigned short fs;		/* saved fs (sfc, dfc) */
+	unsigned short fc;		/* saved fc (sfc, dfc) */
 	unsigned long  crp[2];		/* cpu root pointer */
 	unsigned long  esp0;		/* points to SR of stack frame */
 	unsigned long  faddr;		/* info about last fault */
@@ -92,7 +117,7 @@ struct thread_struct {
 #define INIT_THREAD  {							\
 	.ksp	= sizeof(init_stack) + (unsigned long) init_stack,	\
 	.sr	= PS_S,							\
-	.fs	= __KERNEL_DS,						\
+	.fc	= USER_DATA,						\
 }
 
 /*

arch/m68k/include/asm/segment.h

@@ -1,59 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _M68K_SEGMENT_H
-#define _M68K_SEGMENT_H
-
-/* define constants */
-/* Address spaces (FC0-FC2) */
-#define USER_DATA     (1)
-#ifndef __USER_DS
-#define __USER_DS     (USER_DATA)
-#endif
-#define USER_PROGRAM  (2)
-#define SUPER_DATA    (5)
-#ifndef __KERNEL_DS
-#define __KERNEL_DS   (SUPER_DATA)
-#endif
-#define SUPER_PROGRAM (6)
-#define CPU_SPACE     (7)
-
-#ifndef __ASSEMBLY__
-
-typedef struct {
-	unsigned long seg;
-} mm_segment_t;
-
-#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
-
-#ifdef CONFIG_CPU_HAS_ADDRESS_SPACES
-/*
- * Get/set the SFC/DFC registers for MOVES instructions
- */
-#define USER_DS		MAKE_MM_SEG(__USER_DS)
-#define KERNEL_DS	MAKE_MM_SEG(__KERNEL_DS)
-
-static inline mm_segment_t get_fs(void)
-{
-	mm_segment_t _v;
-	__asm__ ("movec %/dfc,%0":"=r" (_v.seg):);
-	return _v;
-}
-
-static inline void set_fs(mm_segment_t val)
-{
-	__asm__ __volatile__ ("movec %0,%/sfc\n\t"
-			      "movec %0,%/dfc\n\t"
-			      : /* no outputs */ : "r" (val.seg) : "memory");
-}
-
-#else
-#define USER_DS		MAKE_MM_SEG(TASK_SIZE)
-#define KERNEL_DS	MAKE_MM_SEG(0xFFFFFFFF)
-#define get_fs()	(current_thread_info()->addr_limit)
-#define set_fs(x)	(current_thread_info()->addr_limit = (x))
-#endif
-
-#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _M68K_SEGMENT_H */

arch/m68k/include/asm/thread_info.h

@@ -4,7 +4,6 @@
 
 #include <asm/types.h>
 #include <asm/page.h>
-#include <asm/segment.h>
 
 /*
  * On machines with 4k pages we default to an 8k thread size, though we
@@ -27,7 +26,6 @@
 struct thread_info {
 	struct task_struct	*task;		/* main task structure */
 	unsigned long		flags;
-	mm_segment_t		addr_limit;	/* thread address space */
 	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
 	__u32			cpu;		/* should always be 0 on m68k */
 	unsigned long		tp_value;	/* thread pointer */
@@ -37,7 +35,6 @@ struct thread_info {
 #define INIT_THREAD_INFO(tsk)			\
 {						\
 	.task		= &tsk,			\
-	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 }
 

arch/m68k/include/asm/tlbflush.h

@@ -13,13 +13,12 @@ static inline void flush_tlb_kernel_page(void *addr)
 	if (CPU_IS_COLDFIRE) {
 		mmu_write(MMUOR, MMUOR_CNL);
 	} else if (CPU_IS_040_OR_060) {
-		mm_segment_t old_fs = get_fs();
+		set_fc(SUPER_DATA);
-		set_fs(KERNEL_DS);
 		__asm__ __volatile__(".chip 68040\n\t"
 				     "pflush (%0)\n\t"
 				     ".chip 68k"
 				     : : "a" (addr));
-		set_fs(old_fs);
+		set_fc(USER_DATA);
 	} else if (CPU_IS_020_OR_030)
 		__asm__ __volatile__("pflush #4,#4,(%0)" : : "a" (addr));
 }
@@ -84,12 +83,8 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 
 static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
-	if (vma->vm_mm == current->active_mm) {
+	if (vma->vm_mm == current->active_mm)
-		mm_segment_t old_fs = force_uaccess_begin();
-
 		__flush_tlb_one(addr);
-		force_uaccess_end(old_fs);
-	}
 }
 
 static inline void flush_tlb_range(struct vm_area_struct *vma,

arch/m68k/include/asm/traps.h

@@ -267,6 +267,10 @@ struct frame {
     } un;
 };
 
+#ifdef CONFIG_M68040
+asmlinkage void berr_040cleanup(struct frame *fp);
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _M68K_TRAPS_H */

arch/m68k/include/asm/uaccess.h

@@ -9,13 +9,16 @@
  */
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/segment.h>
 #include <asm/extable.h>
 
 /* We let the MMU do all checking */
 static inline int access_ok(const void __user *addr,
 			    unsigned long size)
 {
+	/*
+	 * XXX: for !CONFIG_CPU_HAS_ADDRESS_SPACES this really needs to check
+	 * for TASK_SIZE!
+	 */
 	return 1;
 }
 
@@ -35,12 +38,9 @@ static inline int access_ok(const void __user *addr,
 #define	MOVES	"move"
 #endif
 
-extern int __put_user_bad(void);
+#define __put_user_asm(inst, res, x, ptr, bwl, reg, err) \
-extern int __get_user_bad(void);
-
-#define __put_user_asm(res, x, ptr, bwl, reg, err)	\
 asm volatile ("\n"					\
-	"1:	"MOVES"."#bwl"	%2,%1\n"		\
+	"1:	"inst"."#bwl"	%2,%1\n"		\
 	"2:\n"						\
 	"	.section .fixup,\"ax\"\n"		\
 	"	.even\n"				\
@@ -56,6 +56,31 @@ asm volatile ("\n"					\
 	: "+d" (res), "=m" (*(ptr))			\
 	: #reg (x), "i" (err))
 
+#define __put_user_asm8(inst, res, x, ptr)			\
+do {								\
+	const void *__pu_ptr = (const void __force *)(ptr);	\
+								\
+	asm volatile ("\n"					\
+		"1:	"inst".l %2,(%1)+\n"			\
+		"2:	"inst".l %R2,(%1)\n"			\
+		"3:\n"						\
+		"	.section .fixup,\"ax\"\n"		\
+		"	.even\n"				\
+		"10:	movel %3,%0\n"				\
+		"	jra 3b\n"				\
+		"	.previous\n"				\
+		"\n"						\
+		"	.section __ex_table,\"a\"\n"		\
+		"	.align 4\n"				\
+		"	.long 1b,10b\n"				\
+		"	.long 2b,10b\n"				\
+		"	.long 3b,10b\n"				\
+		"	.previous"				\
+		: "+d" (res), "+a" (__pu_ptr)			\
+		: "r" (x), "i" (-EFAULT)			\
+		: "memory");					\
+} while (0)
+
 /*
  * These are the main single-value transfer routines.  They automatically
  * use the right size if we just have the right pointer type.
@@ -68,51 +93,29 @@ asm volatile ("\n"					\
 	__chk_user_ptr(ptr);						\
 	switch (sizeof (*(ptr))) {					\
 	case 1:								\
-		__put_user_asm(__pu_err, __pu_val, ptr, b, d, -EFAULT);	\
+		__put_user_asm(MOVES, __pu_err, __pu_val, ptr, b, d, -EFAULT); \
 		break;							\
 	case 2:								\
-		__put_user_asm(__pu_err, __pu_val, ptr, w, r, -EFAULT);	\
+		__put_user_asm(MOVES, __pu_err, __pu_val, ptr, w, r, -EFAULT); \
 		break;							\
 	case 4:								\
-		__put_user_asm(__pu_err, __pu_val, ptr, l, r, -EFAULT);	\
+		__put_user_asm(MOVES, __pu_err, __pu_val, ptr, l, r, -EFAULT); \
 		break;							\
 	case 8:								\
- 	    {								\
+		__put_user_asm8(MOVES, __pu_err, __pu_val, ptr);	\
- 		const void __user *__pu_ptr = (ptr);			\
-		asm volatile ("\n"					\
-			"1:	"MOVES".l	%2,(%1)+\n"		\
-			"2:	"MOVES".l	%R2,(%1)\n"		\
-			"3:\n"						\
-			"	.section .fixup,\"ax\"\n"		\
-			"	.even\n"				\
-			"10:	movel %3,%0\n"				\
-			"	jra 3b\n"				\
-			"	.previous\n"				\
-			"\n"						\
-			"	.section __ex_table,\"a\"\n"		\
-			"	.align 4\n"				\
-			"	.long 1b,10b\n"				\
-			"	.long 2b,10b\n"				\
-			"	.long 3b,10b\n"				\
-			"	.previous"				\
-			: "+d" (__pu_err), "+a" (__pu_ptr)		\
-			: "r" (__pu_val), "i" (-EFAULT)			\
-			: "memory");					\
 		break;							\
-	    }								\
 	default:							\
-		__pu_err = __put_user_bad();				\
+		BUILD_BUG();						\
-		break;							\
 	}								\
 	__pu_err;							\
 })
 #define put_user(x, ptr)	__put_user(x, ptr)
 
 
-#define __get_user_asm(res, x, ptr, type, bwl, reg, err) ({		\
+#define __get_user_asm(inst, res, x, ptr, type, bwl, reg, err) ({	\
 	type __gu_val;							\
 	asm volatile ("\n"						\
-		"1:	"MOVES"."#bwl"	%2,%1\n"			\
+		"1:	"inst"."#bwl"	%2,%1\n"			\
 		"2:\n"							\
 		"	.section .fixup,\"ax\"\n"			\
 		"	.even\n"					\
@@ -130,53 +133,57 @@ asm volatile ("\n"					\
 	(x) = (__force typeof(*(ptr)))(__force unsigned long)__gu_val;	\
 })
 
+#define __get_user_asm8(inst, res, x, ptr) 				\
+do {									\
+	const void *__gu_ptr = (const void __force *)(ptr);		\
+	union {								\
+		u64 l;							\
+		__typeof__(*(ptr)) t;					\
+	} __gu_val;							\
+									\
+	asm volatile ("\n"						\
+		"1:	"inst".l (%2)+,%1\n"				\
+		"2:	"inst".l (%2),%R1\n"				\
+		"3:\n"							\
+		"	.section .fixup,\"ax\"\n"			\
+		"	.even\n"					\
+		"10:	move.l	%3,%0\n"				\
+		"	sub.l	%1,%1\n"				\
+		"	sub.l	%R1,%R1\n"				\
+		"	jra	3b\n"					\
+		"	.previous\n"					\
+		"\n"							\
+		"	.section __ex_table,\"a\"\n"			\
+		"	.align	4\n"					\
+		"	.long	1b,10b\n"				\
+		"	.long	2b,10b\n"				\
+		"	.previous"					\
+		: "+d" (res), "=&r" (__gu_val.l),			\
+		  "+a" (__gu_ptr)					\
+		: "i" (-EFAULT)						\
+		: "memory");						\
+	(x) = __gu_val.t;						\
+} while (0)
+
 #define __get_user(x, ptr)						\
 ({									\
 	int __gu_err = 0;						\
 	__chk_user_ptr(ptr);						\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
-		__get_user_asm(__gu_err, x, ptr, u8, b, d, -EFAULT);	\
+		__get_user_asm(MOVES, __gu_err, x, ptr, u8, b, d, -EFAULT); \
 		break;							\
 	case 2:								\
-		__get_user_asm(__gu_err, x, ptr, u16, w, r, -EFAULT);	\
+		__get_user_asm(MOVES, __gu_err, x, ptr, u16, w, r, -EFAULT); \
 		break;							\
 	case 4:								\
-		__get_user_asm(__gu_err, x, ptr, u32, l, r, -EFAULT);	\
+		__get_user_asm(MOVES, __gu_err, x, ptr, u32, l, r, -EFAULT); \
 		break;							\
-	case 8: {							\
+	case 8:								\
-		const void __user *__gu_ptr = (ptr);			\
+		__get_user_asm8(MOVES, __gu_err, x, ptr);		\
-		union {							\
-			u64 l;						\
-			__typeof__(*(ptr)) t;				\
-		} __gu_val;						\
-		asm volatile ("\n"					\
-			"1:	"MOVES".l	(%2)+,%1\n"		\
-			"2:	"MOVES".l	(%2),%R1\n"		\
-			"3:\n"						\
-			"	.section .fixup,\"ax\"\n"		\
-			"	.even\n"				\
-			"10:	move.l	%3,%0\n"			\
-			"	sub.l	%1,%1\n"			\
-			"	sub.l	%R1,%R1\n"			\
-			"	jra	3b\n"				\
-			"	.previous\n"				\
-			"\n"						\
-			"	.section __ex_table,\"a\"\n"		\
-			"	.align	4\n"				\
-			"	.long	1b,10b\n"			\
-			"	.long	2b,10b\n"			\
-			"	.previous"				\
-			: "+d" (__gu_err), "=&r" (__gu_val.l),		\
-			  "+a" (__gu_ptr)				\
-			: "i" (-EFAULT)					\
-			: "memory");					\
-		(x) = __gu_val.t;					\
 		break;							\
-	}								\
 	default:							\
-		__gu_err = __get_user_bad();				\
+		BUILD_BUG();						\
-		break;							\
 	}								\
 	__gu_err;							\
 })
@@ -322,16 +329,19 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n)
 
 	switch (n) {
 	case 1:
-		__put_user_asm(res, *(u8 *)from, (u8 __user *)to, b, d, 1);
+		__put_user_asm(MOVES, res, *(u8 *)from, (u8 __user *)to,
+				b, d, 1);
 		break;
 	case 2:
-		__put_user_asm(res, *(u16 *)from, (u16 __user *)to, w, r, 2);
+		__put_user_asm(MOVES, res, *(u16 *)from, (u16 __user *)to,
+				w, r, 2);
 		break;
 	case 3:
 		__constant_copy_to_user_asm(res, to, from, tmp, 3, w, b,);
 		break;
 	case 4:
-		__put_user_asm(res, *(u32 *)from, (u32 __user *)to, l, r, 4);
+		__put_user_asm(MOVES, res, *(u32 *)from, (u32 __user *)to,
+				l, r, 4);
 		break;
 	case 5:
 		__constant_copy_to_user_asm(res, to, from, tmp, 5, l, b,);
@@ -380,8 +390,65 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 #define INLINE_COPY_FROM_USER
 #define INLINE_COPY_TO_USER
 
-#define user_addr_max() \
+#define HAVE_GET_KERNEL_NOFAULT
-	(uaccess_kernel() ? ~0UL : TASK_SIZE)
+
+#define __get_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	type *__gk_dst = (type *)(dst);					\
+	type *__gk_src = (type *)(src);					\
+	int __gk_err = 0;						\
+									\
+	switch (sizeof(type)) {						\
+	case 1:								\
+		__get_user_asm("move", __gk_err, *__gk_dst, __gk_src,	\
+				u8, b, d, -EFAULT);			\
+		break;							\
+	case 2:								\
+		__get_user_asm("move", __gk_err, *__gk_dst, __gk_src,	\
+				u16, w, r, -EFAULT);			\
+		break;							\
+	case 4:								\
+		__get_user_asm("move", __gk_err, *__gk_dst, __gk_src,	\
+				u32, l, r, -EFAULT);			\
+		break;							\
+	case 8:								\
+		__get_user_asm8("move", __gk_err, *__gk_dst, __gk_src);	\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	if (unlikely(__gk_err))						\
+		goto err_label;						\
+} while (0)
+
+#define __put_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	type __pk_src = *(type *)(src);					\
+	type *__pk_dst = (type *)(dst);					\
+	int __pk_err = 0;						\
+									\
+	switch (sizeof(type)) {						\
+	case 1:								\
+		__put_user_asm("move", __pk_err, __pk_src, __pk_dst,	\
+				b, d, -EFAULT);				\
+		break;							\
+	case 2:								\
+		__put_user_asm("move", __pk_err, __pk_src, __pk_dst,	\
+				w, r, -EFAULT);				\
+		break;							\
+	case 4:								\
+		__put_user_asm("move", __pk_err, __pk_src, __pk_dst,	\
+				l, r, -EFAULT);				\
+		break;							\
+	case 8:								\
+		__put_user_asm8("move", __pk_err, __pk_src, __pk_dst);	\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	if (unlikely(__pk_err))						\
+		goto err_label;						\
+} while (0)
 
 extern long strncpy_from_user(char *dst, const char __user *src, long count);
 extern __must_check long strnlen_user(const char __user *str, long n);

arch/m68k/kernel/asm-offsets.c

@@ -31,7 +31,7 @@ int main(void)
 	DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp));
 	DEFINE(THREAD_USP, offsetof(struct thread_struct, usp));
 	DEFINE(THREAD_SR, offsetof(struct thread_struct, sr));
-	DEFINE(THREAD_FS, offsetof(struct thread_struct, fs));
+	DEFINE(THREAD_FC, offsetof(struct thread_struct, fc));
 	DEFINE(THREAD_CRP, offsetof(struct thread_struct, crp));
 	DEFINE(THREAD_ESP0, offsetof(struct thread_struct, esp0));
 	DEFINE(THREAD_FPREG, offsetof(struct thread_struct, fp));

arch/m68k/kernel/entry.S

@@ -36,7 +36,6 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/setup.h>
-#include <asm/segment.h>
 #include <asm/traps.h>
 #include <asm/unistd.h>
 #include <asm/asm-offsets.h>
@@ -78,20 +77,38 @@ ENTRY(__sys_clone3)
 
 ENTRY(sys_sigreturn)
 	SAVE_SWITCH_STACK
-	movel	%sp,%sp@-		  | switch_stack pointer
+	movel	%sp,%a1			  	| switch_stack pointer
-	pea	%sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer
+	lea	%sp@(SWITCH_STACK_SIZE),%a0	| pt_regs pointer
+	lea     %sp@(-84),%sp			| leave a gap
+	movel	%a1,%sp@-
+	movel	%a0,%sp@-
 	jbsr	do_sigreturn
-	addql	#8,%sp
+	jra	1f				| shared with rt_sigreturn()
-	RESTORE_SWITCH_STACK
-	rts
 
 ENTRY(sys_rt_sigreturn)
 	SAVE_SWITCH_STACK
-	movel	%sp,%sp@-		  | switch_stack pointer
+	movel	%sp,%a1			  	| switch_stack pointer
-	pea	%sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer
+	lea	%sp@(SWITCH_STACK_SIZE),%a0	| pt_regs pointer
+	lea     %sp@(-84),%sp			| leave a gap
+	movel	%a1,%sp@-
+	movel	%a0,%sp@-
+	| stack contents:
+	|   [original pt_regs address] [original switch_stack address]
+	|   [gap] [switch_stack] [pt_regs] [exception frame]
 	jbsr	do_rt_sigreturn
-	addql	#8,%sp
+
+1:
+	| stack contents now:
+	|   [original pt_regs address] [original switch_stack address]
+	|   [unused part of the gap] [moved switch_stack] [moved pt_regs]
+	|   [replacement exception frame]
+	| return value of do_{rt_,}sigreturn() points to moved switch_stack.
+
+	movel	%d0,%sp				| discard the leftover junk
 	RESTORE_SWITCH_STACK
+	| stack contents now is just [syscall return address] [pt_regs] [frame]
+	| return pt_regs.d0
+	movel	%sp@(PT_OFF_D0+4),%d0
 	rts
 
 ENTRY(buserr)
@@ -182,25 +199,6 @@ do_trace_exit:
 	addql	#4,%sp
 	jra	.Lret_from_exception
 
-ENTRY(ret_from_signal)
-	movel	%curptr@(TASK_STACK),%a1
-	tstb	%a1@(TINFO_FLAGS+2)
-	jge	1f
-	jbsr	syscall_trace
-1:	RESTORE_SWITCH_STACK
-	addql	#4,%sp
-/* on 68040 complete pending writebacks if any */
-#ifdef CONFIG_M68040
-	bfextu	%sp@(PT_OFF_FORMATVEC){#0,#4},%d0
-	subql	#7,%d0				| bus error frame ?
-	jbne	1f
-	movel	%sp,%sp@-
-	jbsr	berr_040cleanup
-	addql	#4,%sp
-1:
-#endif
-	jra	.Lret_from_exception
-
 ENTRY(system_call)
 	SAVE_ALL_SYS
 
@@ -338,7 +336,7 @@ resume:
 
 	/* save fs (sfc,%dfc) (may be pointing to kernel memory) */
 	movec	%sfc,%d0
-	movew	%d0,%a0@(TASK_THREAD+THREAD_FS)
+	movew	%d0,%a0@(TASK_THREAD+THREAD_FC)
 
 	/* save usp */
 	/* it is better to use a movel here instead of a movew 8*) */
@@ -424,7 +422,7 @@ resume:
 	movel	%a0,%usp
 
 	/* restore fs (sfc,%dfc) */
-	movew	%a1@(TASK_THREAD+THREAD_FS),%a0
+	movew	%a1@(TASK_THREAD+THREAD_FC),%a0
 	movec	%a0,%sfc
 	movec	%a0,%dfc
 

arch/m68k/kernel/process.c

@@ -92,7 +92,7 @@ void show_regs(struct pt_regs * regs)
 
 void flush_thread(void)
 {
-	current->thread.fs = __USER_DS;
+	current->thread.fc = USER_DATA;
 #ifdef CONFIG_FPU
 	if (!FPU_IS_EMU) {
 		unsigned long zero = 0;
@@ -155,7 +155,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
 	 * Must save the current SFC/DFC value, NOT the value when
 	 * the parent was last descheduled - RGH  10-08-96
 	 */
-	p->thread.fs = get_fs().seg;
+	p->thread.fc = USER_DATA;
 
 	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
 		/* kernel thread */

arch/m68k/kernel/signal.c

@@ -447,7 +447,7 @@ static inline void save_fpu_state(struct sigcontext *sc, struct pt_regs *regs)
 
 	if (CPU_IS_060 ? sc->sc_fpstate[2] : sc->sc_fpstate[0]) {
 		fpu_version = sc->sc_fpstate[0];
-		if (CPU_IS_020_OR_030 &&
+		if (CPU_IS_020_OR_030 && !regs->stkadj &&
 		    regs->vector >= (VEC_FPBRUC * 4) &&
 		    regs->vector <= (VEC_FPNAN * 4)) {
 			/* Clear pending exception in 68882 idle frame */
@@ -510,7 +510,7 @@ static inline int rt_save_fpu_state(struct ucontext __user *uc, struct pt_regs *
 		if (!(CPU_IS_060 || CPU_IS_COLDFIRE))
 			context_size = fpstate[1];
 		fpu_version = fpstate[0];
-		if (CPU_IS_020_OR_030 &&
+		if (CPU_IS_020_OR_030 && !regs->stkadj &&
 		    regs->vector >= (VEC_FPBRUC * 4) &&
 		    regs->vector <= (VEC_FPNAN * 4)) {
 			/* Clear pending exception in 68882 idle frame */
@@ -641,56 +641,35 @@ static inline void siginfo_build_tests(void)
 static int mangle_kernel_stack(struct pt_regs *regs, int formatvec,
 			       void __user *fp)
 {
-	int fsize = frame_extra_sizes(formatvec >> 12);
+	int extra = frame_extra_sizes(formatvec >> 12);
-	if (fsize < 0) {
+	char buf[sizeof_field(struct frame, un)];
+
+	if (extra < 0) {
 		/*
 		 * user process trying to return with weird frame format
 		 */
 		pr_debug("user process returning with weird frame format\n");
-		return 1;
+		return -1;
 	}
-	if (!fsize) {
+	if (extra && copy_from_user(buf, fp, extra))
-		regs->format = formatvec >> 12;
+		return -1;
-		regs->vector = formatvec & 0xfff;
+	regs->format = formatvec >> 12;
-	} else {
+	regs->vector = formatvec & 0xfff;
-		struct switch_stack *sw = (struct switch_stack *)regs - 1;
+	if (extra) {
-		/* yes, twice as much as max(sizeof(frame.un.fmt<x>)) */
+		void *p = (struct switch_stack *)regs - 1;
-		unsigned long buf[sizeof_field(struct frame, un) / 2];
+		struct frame *new = (void *)regs - extra;
+		int size = sizeof(struct pt_regs)+sizeof(struct switch_stack);
 
-		/* that'll make sure that expansion won't crap over data */
+		memmove(p - extra, p, size);
-		if (copy_from_user(buf + fsize / 4, fp, fsize))
+		memcpy(p - extra + size, buf, extra);
-			return 1;
+		current->thread.esp0 = (unsigned long)&new->ptregs;
-
+#ifdef CONFIG_M68040
-		/* point of no return */
+		/* on 68040 complete pending writebacks if any */
-		regs->format = formatvec >> 12;
+		if (new->ptregs.format == 7) // bus error frame
-		regs->vector = formatvec & 0xfff;
+			berr_040cleanup(new);
-#define frame_offset (sizeof(struct pt_regs)+sizeof(struct switch_stack))
-		__asm__ __volatile__ (
-#ifdef CONFIG_COLDFIRE
-			 "   movel %0,%/sp\n\t"
-			 "   bra ret_from_signal\n"
-#else
-			 "   movel %0,%/a0\n\t"
-			 "   subl %1,%/a0\n\t"     /* make room on stack */
-			 "   movel %/a0,%/sp\n\t"  /* set stack pointer */
-			 /* move switch_stack and pt_regs */
-			 "1: movel %0@+,%/a0@+\n\t"
-			 "   dbra %2,1b\n\t"
-			 "   lea %/sp@(%c3),%/a0\n\t" /* add offset of fmt */
-			 "   lsrl  #2,%1\n\t"
-			 "   subql #1,%1\n\t"
-			 /* copy to the gap we'd made */
-			 "2: movel %4@+,%/a0@+\n\t"
-			 "   dbra %1,2b\n\t"
-			 "   bral ret_from_signal\n"
 #endif
-			 : /* no outputs, it doesn't ever return */
-			 : "a" (sw), "d" (fsize), "d" (frame_offset/4-1),
-			   "n" (frame_offset), "a" (buf + fsize/4)
-			 : "a0");
-#undef frame_offset
 	}
-	return 0;
+	return extra;
 }
 
 static inline int
@@ -698,7 +677,6 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, void __u
 {
 	int formatvec;
 	struct sigcontext context;
-	int err = 0;
 
 	siginfo_build_tests();
 
@@ -707,7 +685,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, void __u
 
 	/* get previous context */
 	if (copy_from_user(&context, usc, sizeof(context)))
-		goto badframe;
+		return -1;
 
 	/* restore passed registers */
 	regs->d0 = context.sc_d0;
@@ -720,15 +698,10 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, void __u
 	wrusp(context.sc_usp);
 	formatvec = context.sc_formatvec;
 
-	err = restore_fpu_state(&context);
+	if (restore_fpu_state(&context))
+		return -1;
 
-	if (err || mangle_kernel_stack(regs, formatvec, fp))
+	return mangle_kernel_stack(regs, formatvec, fp);
-		goto badframe;
-
-	return 0;
-
-badframe:
-	return 1;
 }
 
 static inline int
@@ -745,7 +718,7 @@ rt_restore_ucontext(struct pt_regs *regs, struct switch_stack *sw,
 
 	err = __get_user(temp, &uc->uc_mcontext.version);
 	if (temp != MCONTEXT_VERSION)
-		goto badframe;
+		return -1;
 	/* restore passed registers */
 	err |= __get_user(regs->d0, &gregs[0]);
 	err |= __get_user(regs->d1, &gregs[1]);
@@ -774,22 +747,17 @@ rt_restore_ucontext(struct pt_regs *regs, struct switch_stack *sw,
 	err |= restore_altstack(&uc->uc_stack);
 
 	if (err)
-		goto badframe;
+		return -1;
 
-	if (mangle_kernel_stack(regs, temp, &uc->uc_extra))
+	return mangle_kernel_stack(regs, temp, &uc->uc_extra);
-		goto badframe;
-
-	return 0;
-
-badframe:
-	return 1;
 }
 
-asmlinkage int do_sigreturn(struct pt_regs *regs, struct switch_stack *sw)
+asmlinkage void *do_sigreturn(struct pt_regs *regs, struct switch_stack *sw)
 {
 	unsigned long usp = rdusp();
 	struct sigframe __user *frame = (struct sigframe __user *)(usp - 4);
 	sigset_t set;
+	int size;
 
 	if (!access_ok(frame, sizeof(*frame)))
 		goto badframe;
@@ -801,20 +769,22 @@ asmlinkage int do_sigreturn(struct pt_regs *regs, struct switch_stack *sw)
 
 	set_current_blocked(&set);
 
-	if (restore_sigcontext(regs, &frame->sc, frame + 1))
+	size = restore_sigcontext(regs, &frame->sc, frame + 1);
+	if (size < 0)
 		goto badframe;
-	return regs->d0;
+	return (void *)sw - size;
 
 badframe:
 	force_sig(SIGSEGV);
-	return 0;
+	return sw;
 }
 
-asmlinkage int do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw)
+asmlinkage void *do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw)
 {
 	unsigned long usp = rdusp();
 	struct rt_sigframe __user *frame = (struct rt_sigframe __user *)(usp - 4);
 	sigset_t set;
+	int size;
 
 	if (!access_ok(frame, sizeof(*frame)))
 		goto badframe;
@@ -823,27 +793,34 @@ asmlinkage int do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw)
 
 	set_current_blocked(&set);
 
-	if (rt_restore_ucontext(regs, sw, &frame->uc))
+	size = rt_restore_ucontext(regs, sw, &frame->uc);
+	if (size < 0)
 		goto badframe;
-	return regs->d0;
+	return (void *)sw - size;
 
 badframe:
 	force_sig(SIGSEGV);
-	return 0;
+	return sw;
+}
+
+static inline struct pt_regs *rte_regs(struct pt_regs *regs)
+{
+	return (void *)regs + regs->stkadj;
 }
 
 static void setup_sigcontext(struct sigcontext *sc, struct pt_regs *regs,
 			     unsigned long mask)
 {
+	struct pt_regs *tregs = rte_regs(regs);
 	sc->sc_mask = mask;
 	sc->sc_usp = rdusp();
 	sc->sc_d0 = regs->d0;
 	sc->sc_d1 = regs->d1;
 	sc->sc_a0 = regs->a0;
 	sc->sc_a1 = regs->a1;
-	sc->sc_sr = regs->sr;
+	sc->sc_sr = tregs->sr;
-	sc->sc_pc = regs->pc;
+	sc->sc_pc = tregs->pc;
-	sc->sc_formatvec = regs->format << 12 | regs->vector;
+	sc->sc_formatvec = tregs->format << 12 | tregs->vector;
 	save_a5_state(sc, regs);
 	save_fpu_state(sc, regs);
 }
@@ -851,6 +828,7 @@ static void setup_sigcontext(struct sigcontext *sc, struct pt_regs *regs,
 static inline int rt_setup_ucontext(struct ucontext __user *uc, struct pt_regs *regs)
 {
 	struct switch_stack *sw = (struct switch_stack *)regs - 1;
+	struct pt_regs *tregs = rte_regs(regs);
 	greg_t __user *gregs = uc->uc_mcontext.gregs;
 	int err = 0;
 
@@ -871,9 +849,9 @@ static inline int rt_setup_ucontext(struct ucontext __user *uc, struct pt_regs *
 	err |= __put_user(sw->a5, &gregs[13]);
 	err |= __put_user(sw->a6, &gregs[14]);
 	err |= __put_user(rdusp(), &gregs[15]);
-	err |= __put_user(regs->pc, &gregs[16]);
+	err |= __put_user(tregs->pc, &gregs[16]);
-	err |= __put_user(regs->sr, &gregs[17]);
+	err |= __put_user(tregs->sr, &gregs[17]);
-	err |= __put_user((regs->format << 12) | regs->vector, &uc->uc_formatvec);
+	err |= __put_user((tregs->format << 12) | tregs->vector, &uc->uc_formatvec);
 	err |= rt_save_fpu_state(uc, regs);
 	return err;
 }
@@ -890,13 +868,14 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 			struct pt_regs *regs)
 {
 	struct sigframe __user *frame;
-	int fsize = frame_extra_sizes(regs->format);
+	struct pt_regs *tregs = rte_regs(regs);
+	int fsize = frame_extra_sizes(tregs->format);
 	struct sigcontext context;
 	int err = 0, sig = ksig->sig;
 
 	if (fsize < 0) {
 		pr_debug("setup_frame: Unknown frame format %#x\n",
-			 regs->format);
+			 tregs->format);
 		return -EFAULT;
 	}
 
@@ -907,7 +886,7 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 
 	err |= __put_user(sig, &frame->sig);
 
-	err |= __put_user(regs->vector, &frame->code);
+	err |= __put_user(tregs->vector, &frame->code);
 	err |= __put_user(&frame->sc, &frame->psc);
 
 	if (_NSIG_WORDS > 1)
@@ -933,34 +912,28 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 
 	push_cache ((unsigned long) &frame->retcode);
 
-	/*
-	 * Set up registers for signal handler.  All the state we are about
-	 * to destroy is successfully copied to sigframe.
-	 */
-	wrusp ((unsigned long) frame);
-	regs->pc = (unsigned long) ksig->ka.sa.sa_handler;
-	adjustformat(regs);
-
 	/*
 	 * This is subtle; if we build more than one sigframe, all but the
 	 * first one will see frame format 0 and have fsize == 0, so we won't
 	 * screw stkadj.
 	 */
-	if (fsize)
+	if (fsize) {
 		regs->stkadj = fsize;
-
+		tregs = rte_regs(regs);
-	/* Prepare to skip over the extra stuff in the exception frame.  */
-	if (regs->stkadj) {
-		struct pt_regs *tregs =
-			(struct pt_regs *)((ulong)regs + regs->stkadj);
 		pr_debug("Performing stackadjust=%04lx\n", regs->stkadj);
-		/* This must be copied with decreasing addresses to
-                   handle overlaps.  */
 		tregs->vector = 0;
 		tregs->format = 0;
-		tregs->pc = regs->pc;
 		tregs->sr = regs->sr;
 	}
+
+	/*
+	 * Set up registers for signal handler.  All the state we are about
+	 * to destroy is successfully copied to sigframe.
+	 */
+	wrusp ((unsigned long) frame);
+	tregs->pc = (unsigned long) ksig->ka.sa.sa_handler;
+	adjustformat(regs);
+
 	return 0;
 }
 
@@ -968,7 +941,8 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 			   struct pt_regs *regs)
 {
 	struct rt_sigframe __user *frame;
-	int fsize = frame_extra_sizes(regs->format);
+	struct pt_regs *tregs = rte_regs(regs);
+	int fsize = frame_extra_sizes(tregs->format);
 	int err = 0, sig = ksig->sig;
 
 	if (fsize < 0) {
@@ -1018,34 +992,27 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 
 	push_cache ((unsigned long) &frame->retcode);
 
-	/*
-	 * Set up registers for signal handler.  All the state we are about
-	 * to destroy is successfully copied to sigframe.
-	 */
-	wrusp ((unsigned long) frame);
-	regs->pc = (unsigned long) ksig->ka.sa.sa_handler;
-	adjustformat(regs);
-
 	/*
 	 * This is subtle; if we build more than one sigframe, all but the
 	 * first one will see frame format 0 and have fsize == 0, so we won't
 	 * screw stkadj.
 	 */
-	if (fsize)
+	if (fsize) {
 		regs->stkadj = fsize;
-
+		tregs = rte_regs(regs);
-	/* Prepare to skip over the extra stuff in the exception frame.  */
-	if (regs->stkadj) {
-		struct pt_regs *tregs =
-			(struct pt_regs *)((ulong)regs + regs->stkadj);
 		pr_debug("Performing stackadjust=%04lx\n", regs->stkadj);
-		/* This must be copied with decreasing addresses to
-                   handle overlaps.  */
 		tregs->vector = 0;
 		tregs->format = 0;
-		tregs->pc = regs->pc;
 		tregs->sr = regs->sr;
 	}
+
+	/*
+	 * Set up registers for signal handler.  All the state we are about
+	 * to destroy is successfully copied to sigframe.
+	 */
+	wrusp ((unsigned long) frame);
+	tregs->pc = (unsigned long) ksig->ka.sa.sa_handler;
+	adjustformat(regs);
 	return 0;
 }
 

arch/m68k/kernel/traps.c

@@ -181,9 +181,8 @@ static inline void access_error060 (struct frame *fp)
 static inline unsigned long probe040(int iswrite, unsigned long addr, int wbs)
 {
 	unsigned long mmusr;
-	mm_segment_t old_fs = get_fs();
 
-	set_fs(MAKE_MM_SEG(wbs));
+	set_fc(wbs);
 
 	if (iswrite)
 		asm volatile (".chip 68040; ptestw (%0); .chip 68k" : : "a" (addr));
@@ -192,7 +191,7 @@ static inline unsigned long probe040(int iswrite, unsigned long addr, int wbs)
 
 	asm volatile (".chip 68040; movec %%mmusr,%0; .chip 68k" : "=r" (mmusr));
 
-	set_fs(old_fs);
+	set_fc(USER_DATA);
 
 	return mmusr;
 }
@@ -201,10 +200,8 @@ static inline int do_040writeback1(unsigned short wbs, unsigned long wba,
 				   unsigned long wbd)
 {
 	int res = 0;
-	mm_segment_t old_fs = get_fs();
 
-	/* set_fs can not be moved, otherwise put_user() may oops */
+	set_fc(wbs);
-	set_fs(MAKE_MM_SEG(wbs));
 
 	switch (wbs & WBSIZ_040) {
 	case BA_SIZE_BYTE:
@@ -218,9 +215,7 @@ static inline int do_040writeback1(unsigned short wbs, unsigned long wba,
 		break;
 	}
 
-	/* set_fs can not be moved, otherwise put_user() may oops */
+	set_fc(USER_DATA);
-	set_fs(old_fs);
-
 
 	pr_debug("do_040writeback1, res=%d\n", res);
 

arch/m68k/mac/misc.c

@@ -18,7 +18,6 @@
 
 #include <linux/uaccess.h>
 #include <asm/io.h>
-#include <asm/segment.h>
 #include <asm/setup.h>
 #include <asm/macintosh.h>
 #include <asm/mac_via.h>

arch/m68k/mm/cache.c

@@ -49,24 +49,7 @@ static unsigned long virt_to_phys_slow(unsigned long vaddr)
 		if (mmusr & MMU_R_040)
 			return (mmusr & PAGE_MASK) | (vaddr & ~PAGE_MASK);
 	} else {
-		unsigned short mmusr;
+		WARN_ON_ONCE(!CPU_IS_040_OR_060);
-		unsigned long *descaddr;
-
-		asm volatile ("ptestr %3,%2@,#7,%0\n\t"
-			      "pmove %%psr,%1"
-			      : "=a&" (descaddr), "=m" (mmusr)
-			      : "a" (vaddr), "d" (get_fs().seg));
-		if (mmusr & (MMU_I|MMU_B|MMU_L))
-			return 0;
-		descaddr = phys_to_virt((unsigned long)descaddr);
-		switch (mmusr & MMU_NUM) {
-		case 1:
-			return (*descaddr & 0xfe000000) | (vaddr & 0x01ffffff);
-		case 2:
-			return (*descaddr & 0xfffc0000) | (vaddr & 0x0003ffff);
-		case 3:
-			return (*descaddr & PAGE_MASK) | (vaddr & ~PAGE_MASK);
-		}
 	}
 	return 0;
 }
@@ -107,11 +90,9 @@ void flush_icache_user_range(unsigned long address, unsigned long endaddr)
 
 void flush_icache_range(unsigned long address, unsigned long endaddr)
 {
-	mm_segment_t old_fs = get_fs();
+	set_fc(SUPER_DATA);
-
-	set_fs(KERNEL_DS);
 	flush_icache_user_range(address, endaddr);
-	set_fs(old_fs);
+	set_fc(USER_DATA);
 }
 EXPORT_SYMBOL(flush_icache_range);
 

arch/m68k/mm/init.c

@@ -72,12 +72,6 @@ void __init paging_init(void)
 	if (!empty_zero_page)
 		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
 		      __func__, PAGE_SIZE, PAGE_SIZE);
-
-	/*
-	 * Set up SFC/DFC registers (user data space).
-	 */
-	set_fs (USER_DS);
-
 	max_zone_pfn[ZONE_DMA] = end_mem >> PAGE_SHIFT;
 	free_area_init(max_zone_pfn);
 }

arch/m68k/mm/kmap.c

@@ -17,7 +17,6 @@
 #include <linux/vmalloc.h>
 
 #include <asm/setup.h>
-#include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/io.h>
 #include <asm/tlbflush.h>

arch/m68k/mm/memory.c

@@ -15,7 +15,6 @@
 #include <linux/gfp.h>
 
 #include <asm/setup.h>
-#include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/traps.h>
 #include <asm/machdep.h>

arch/m68k/mm/motorola.c

@@ -467,7 +467,7 @@ void __init paging_init(void)
 	/*
 	 * Set up SFC/DFC registers
 	 */
-	set_fs(KERNEL_DS);
+	set_fc(USER_DATA);
 
 #ifdef DEBUG
 	printk ("before free_area_init\n");

arch/m68k/sun3/config.c

@@ -31,7 +31,6 @@
 #include <asm/intersil.h>
 #include <asm/irq.h>
 #include <asm/sections.h>
-#include <asm/segment.h>
 #include <asm/sun3ints.h>
 
 char sun3_reserved_pmeg[SUN3_PMEGS_NUM];
@@ -89,7 +88,7 @@ void __init sun3_init(void)
 	sun3_reserved_pmeg[249] = 1;
 	sun3_reserved_pmeg[252] = 1;
 	sun3_reserved_pmeg[253] = 1;
-	set_fs(KERNEL_DS);
+	set_fc(USER_DATA);
 }
 
 /* Without this, Bad Things happen when something calls arch_reset. */

arch/m68k/sun3/mmu_emu.c

@@ -23,7 +23,6 @@
 #include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/sun3mmu.h>
-#include <asm/segment.h>
 #include <asm/oplib.h>
 #include <asm/mmu_context.h>
 #include <asm/dvma.h>
@@ -191,14 +190,13 @@ void __init mmu_emu_init(unsigned long bootmem_end)
 	for(seg = 0; seg < PAGE_OFFSET; seg += SUN3_PMEG_SIZE)
 		sun3_put_segmap(seg, SUN3_INVALID_PMEG);
 
-	set_fs(MAKE_MM_SEG(3));
+	set_fc(3);
 	for(seg = 0; seg < 0x10000000; seg += SUN3_PMEG_SIZE) {
 		i = sun3_get_segmap(seg);
 		for(j = 1; j < CONTEXTS_NUM; j++)
 			(*(romvec->pv_setctxt))(j, (void *)seg, i);
 	}
-	set_fs(KERNEL_DS);
+	set_fc(USER_DATA);
-
 }
 
 /* erase the mappings for a dead context.  Uses the pg_dir for hints

arch/m68k/sun3/sun3ints.c

@@ -11,7 +11,6 @@
 #include <linux/sched.h>
 #include <linux/kernel_stat.h>
 #include <linux/interrupt.h>
-#include <asm/segment.h>
 #include <asm/intersil.h>
 #include <asm/oplib.h>
 #include <asm/sun3ints.h>

arch/m68k/sun3x/prom.c

@@ -14,7 +14,6 @@
 #include <asm/traps.h>
 #include <asm/sun3xprom.h>
 #include <asm/idprom.h>
-#include <asm/segment.h>
 #include <asm/sun3ints.h>
 #include <asm/openprom.h>
 #include <asm/machines.h>

arch/mips/net/bpf_jit.c

@@ -662,6 +662,11 @@ static void build_epilogue(struct jit_ctx *ctx)
 	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative : func) : \
 	 func##_positive)
 
+static bool is_bad_offset(int b_off)
+{
+	return b_off > 0x1ffff || b_off < -0x20000;
+}
+
 static int build_body(struct jit_ctx *ctx)
 {
 	const struct bpf_prog *prog = ctx->skf;
@@ -728,7 +733,10 @@ load_common:
 			/* Load return register on DS for failures */
 			emit_reg_move(r_ret, r_zero, ctx);
 			/* Return with error */
-			emit_b(b_imm(prog->len, ctx), ctx);
+			b_off = b_imm(prog->len, ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_b(b_off, ctx);
 			emit_nop(ctx);
 			break;
 		case BPF_LD | BPF_W | BPF_IND:
@@ -775,8 +783,10 @@ load_ind:
 			emit_jalr(MIPS_R_RA, r_s0, ctx);
 			emit_reg_move(MIPS_R_A0, r_skb, ctx); /* delay slot */
 			/* Check the error value */
-			emit_bcond(MIPS_COND_NE, r_ret, 0,
+			b_off = b_imm(prog->len, ctx);
-				   b_imm(prog->len, ctx), ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_bcond(MIPS_COND_NE, r_ret, 0, b_off, ctx);
 			emit_reg_move(r_ret, r_zero, ctx);
 			/* We are good */
 			/* X <- P[1:K] & 0xf */
@@ -855,8 +865,10 @@ load_ind:
 			/* A /= X */
 			ctx->flags |= SEEN_X | SEEN_A;
 			/* Check if r_X is zero */
-			emit_bcond(MIPS_COND_EQ, r_X, r_zero,
+			b_off = b_imm(prog->len, ctx);
-				   b_imm(prog->len, ctx), ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_bcond(MIPS_COND_EQ, r_X, r_zero, b_off, ctx);
 			emit_load_imm(r_ret, 0, ctx); /* delay slot */
 			emit_div(r_A, r_X, ctx);
 			break;
@@ -864,8 +876,10 @@ load_ind:
 			/* A %= X */
 			ctx->flags |= SEEN_X | SEEN_A;
 			/* Check if r_X is zero */
-			emit_bcond(MIPS_COND_EQ, r_X, r_zero,
+			b_off = b_imm(prog->len, ctx);
-				   b_imm(prog->len, ctx), ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_bcond(MIPS_COND_EQ, r_X, r_zero, b_off, ctx);
 			emit_load_imm(r_ret, 0, ctx); /* delay slot */
 			emit_mod(r_A, r_X, ctx);
 			break;
@@ -926,7 +940,10 @@ load_ind:
 			break;
 		case BPF_JMP | BPF_JA:
 			/* pc += K */
-			emit_b(b_imm(i + k + 1, ctx), ctx);
+			b_off = b_imm(i + k + 1, ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_b(b_off, ctx);
 			emit_nop(ctx);
 			break;
 		case BPF_JMP | BPF_JEQ | BPF_K:
@@ -1056,12 +1073,16 @@ jmp_cmp:
 			break;
 		case BPF_RET | BPF_A:
 			ctx->flags |= SEEN_A;
-			if (i != prog->len - 1)
+			if (i != prog->len - 1) {
 				/*
 				 * If this is not the last instruction
 				 * then jump to the epilogue
 				 */
-				emit_b(b_imm(prog->len, ctx), ctx);
+				b_off = b_imm(prog->len, ctx);
+				if (is_bad_offset(b_off))
+					return -E2BIG;
+				emit_b(b_off, ctx);
+			}
 			emit_reg_move(r_ret, r_A, ctx); /* delay slot */
 			break;
 		case BPF_RET | BPF_K:
@@ -1075,7 +1096,10 @@ jmp_cmp:
 				 * If this is not the last instruction
 				 * then jump to the epilogue
 				 */
-				emit_b(b_imm(prog->len, ctx), ctx);
+				b_off = b_imm(prog->len, ctx);
+				if (is_bad_offset(b_off))
+					return -E2BIG;
+				emit_b(b_off, ctx);
 				emit_nop(ctx);
 			}
 			break;
@@ -1133,8 +1157,10 @@ jmp_cmp:
 			/* Load *dev pointer */
 			emit_load_ptr(r_s0, r_skb, off, ctx);
 			/* error (0) in the delay slot */
-			emit_bcond(MIPS_COND_EQ, r_s0, r_zero,
+			b_off = b_imm(prog->len, ctx);
-				   b_imm(prog->len, ctx), ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_bcond(MIPS_COND_EQ, r_s0, r_zero, b_off, ctx);
 			emit_reg_move(r_ret, r_zero, ctx);
 			if (code == (BPF_ANC | SKF_AD_IFINDEX)) {
 				BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4);
@@ -1244,7 +1270,10 @@ void bpf_jit_compile(struct bpf_prog *fp)
 
 	/* Generate the actual JIT code */
 	build_prologue(&ctx);
-	build_body(&ctx);
+	if (build_body(&ctx)) {
+		module_memfree(ctx.target);
+		goto out;
+	}
 	build_epilogue(&ctx);
 
 	/* Update the icache */

arch/nios2/Kconfig.debug

@@ -3,9 +3,10 @@
 config EARLY_PRINTK
 	bool "Activate early kernel debugging"
 	default y
+	depends on TTY
 	select SERIAL_CORE_CONSOLE
 	help
-	  Enable early printk on console
+	  Enable early printk on console.
 	  This is useful for kernel debugging when your machine crashes very
 	  early before the console code is initialized.
 	  You should normally say N here, unless you want to debug such a crash.

arch/nios2/kernel/setup.c

@@ -149,8 +149,6 @@ static void __init find_limits(unsigned long *min, unsigned long *max_low,
 
 void __init setup_arch(char **cmdline_p)
 {
-	int dram_start;
-
 	console_verbose();
 
 	memory_start = memblock_start_of_DRAM();

arch/s390/kvm/interrupt.c

@@ -419,13 +419,13 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
 static void __set_cpu_idle(struct kvm_vcpu *vcpu)
 {
 	kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT);
-	set_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask);
+	set_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask);
 }
 
 static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
 {
 	kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT);
-	clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask);
+	clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask);
 }
 
 static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)

arch/s390/kvm/kvm-s390.c

@@ -4066,7 +4066,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
 		kvm_s390_patch_guest_per_regs(vcpu);
 	}
 
-	clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.gisa_int.kicked_mask);
+	clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask);
 
 	vcpu->arch.sie_block->icptcode = 0;
 	cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);

arch/s390/kvm/kvm-s390.h

@@ -79,7 +79,7 @@ static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
 
 static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
 {
-	return test_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask);
+	return test_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask);
 }
 
 static inline int kvm_is_ucontrol(struct kvm *kvm)

arch/x86/crypto/sm4-aesni-avx-asm_64.S

@@ -367,10 +367,11 @@ SYM_FUNC_START(sm4_aesni_avx_crypt8)
 	 *	%rdx: src (1..8 blocks)
 	 *	%rcx: num blocks (1..8)
 	 */
-	FRAME_BEGIN
-
 	cmpq $5, %rcx;
 	jb sm4_aesni_avx_crypt4;
+
+	FRAME_BEGIN
+
 	vmovdqu (0 * 16)(%rdx), RA0;
 	vmovdqu (1 * 16)(%rdx), RA1;
 	vmovdqu (2 * 16)(%rdx), RA2;

arch/x86/events/core.c

@@ -2465,6 +2465,7 @@ static int x86_pmu_event_init(struct perf_event *event)
 	if (err) {
 		if (event->destroy)
 			event->destroy(event);
+		event->destroy = NULL;
 	}
 
 	if (READ_ONCE(x86_pmu.attr_rdpmc) &&

arch/x86/events/intel/core.c

@@ -263,6 +263,7 @@ static struct event_constraint intel_icl_event_constraints[] = {
 	INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf),
 	INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf),
 	INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf),
+	INTEL_EVENT_CONSTRAINT(0xef, 0xf),
 	INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf),
 	EVENT_CONSTRAINT_END
 };

arch/x86/include/asm/kvm_page_track.h

@@ -46,7 +46,7 @@ struct kvm_page_track_notifier_node {
 			    struct kvm_page_track_notifier_node *node);
 };
 
-void kvm_page_track_init(struct kvm *kvm);
+int kvm_page_track_init(struct kvm *kvm);
 void kvm_page_track_cleanup(struct kvm *kvm);
 
 void kvm_page_track_free_memslot(struct kvm_memory_slot *slot);

arch/x86/include/asm/kvmclock.h

@@ -2,6 +2,20 @@
 #ifndef _ASM_X86_KVM_CLOCK_H
 #define _ASM_X86_KVM_CLOCK_H
 
+#include <linux/percpu.h>
+
 extern struct clocksource kvm_clock;
 
+DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+
+static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
+{
+	return &this_cpu_read(hv_clock_per_cpu)->pvti;
+}
+
+static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
+{
+	return this_cpu_read(hv_clock_per_cpu);
+}
+
 #endif /* _ASM_X86_KVM_CLOCK_H */

arch/x86/kernel/kvmclock.c

@@ -49,18 +49,9 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
 static struct pvclock_vsyscall_time_info
 			hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE);
 static struct pvclock_wall_clock wall_clock __bss_decrypted;
-static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
 static struct pvclock_vsyscall_time_info *hvclock_mem;
-
+DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
-static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
+EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu);
-{
-	return &this_cpu_read(hv_clock_per_cpu)->pvti;
-}
-
-static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
-{
-	return this_cpu_read(hv_clock_per_cpu);
-}
 
 /*
  * The wallclock is the time of day when we booted. Since then, some time may

arch/x86/kvm/cpuid.c

@@ -65,8 +65,8 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find(
 	for (i = 0; i < nent; i++) {
 		e = &entries[i];
 
-		if (e->function == function && (e->index == index ||
+		if (e->function == function &&
-		    !(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX)))
+		    (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index))
 			return e;
 	}
 

arch/x86/kvm/emulate.c

@@ -435,7 +435,6 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	__FOP_RET(#op)
 
 asm(".pushsection .fixup, \"ax\"\n"
-    ".global kvm_fastop_exception \n"
     "kvm_fastop_exception: xor %esi, %esi; ret\n"
     ".popsection");
 
@@ -4206,7 +4205,7 @@ static int check_rdtsc(struct x86_emulate_ctxt *ctxt)
 	u64 cr4 = ctxt->ops->get_cr(ctxt, 4);
 
 	if (cr4 & X86_CR4_TSD && ctxt->ops->cpl(ctxt))
-		return emulate_ud(ctxt);
+		return emulate_gp(ctxt, 0);
 
 	return X86EMUL_CONTINUE;
 }

arch/x86/kvm/hyperv.c

@@ -939,7 +939,7 @@ static int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
 	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
 		stimer_init(&hv_vcpu->stimer[i], i);
 
-	hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu);
+	hv_vcpu->vp_index = vcpu->vcpu_idx;
 
 	return 0;
 }
@@ -1444,7 +1444,6 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 	switch (msr) {
 	case HV_X64_MSR_VP_INDEX: {
 		struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
-		int vcpu_idx = kvm_vcpu_get_idx(vcpu);
 		u32 new_vp_index = (u32)data;
 
 		if (!host || new_vp_index >= KVM_MAX_VCPUS)
@@ -1459,9 +1458,9 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 		 * VP index is changing, adjust num_mismatched_vp_indexes if
 		 * it now matches or no longer matches vcpu_idx.
 		 */
-		if (hv_vcpu->vp_index == vcpu_idx)
+		if (hv_vcpu->vp_index == vcpu->vcpu_idx)
 			atomic_inc(&hv->num_mismatched_vp_indexes);
-		else if (new_vp_index == vcpu_idx)
+		else if (new_vp_index == vcpu->vcpu_idx)
 			atomic_dec(&hv->num_mismatched_vp_indexes);
 
 		hv_vcpu->vp_index = new_vp_index;

arch/x86/kvm/hyperv.h

@@ -83,7 +83,7 @@ static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
 
-	return hv_vcpu ? hv_vcpu->vp_index : kvm_vcpu_get_idx(vcpu);
+	return hv_vcpu ? hv_vcpu->vp_index : vcpu->vcpu_idx;
 }
 
 int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host);

arch/x86/kvm/ioapic.c

@@ -319,8 +319,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 	unsigned index;
 	bool mask_before, mask_after;
 	union kvm_ioapic_redirect_entry *e;
-	unsigned long vcpu_bitmap;
 	int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode;
+	DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
 
 	switch (ioapic->ioregsel) {
 	case IOAPIC_REG_VERSION:
@@ -384,9 +384,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 			irq.shorthand = APIC_DEST_NOSHORT;
 			irq.dest_id = e->fields.dest_id;
 			irq.msi_redir_hint = false;
-			bitmap_zero(&vcpu_bitmap, 16);
+			bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
 			kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
-						 &vcpu_bitmap);
+						 vcpu_bitmap);
 			if (old_dest_mode != e->fields.dest_mode ||
 			    old_dest_id != e->fields.dest_id) {
 				/*
@@ -399,10 +399,10 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 				    kvm_lapic_irq_dest_mode(
 					!!e->fields.dest_mode);
 				kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
-							 &vcpu_bitmap);
+							 vcpu_bitmap);
 			}
 			kvm_make_scan_ioapic_request_mask(ioapic->kvm,
-							  &vcpu_bitmap);
+							  vcpu_bitmap);
 		} else {
 			kvm_make_scan_ioapic_request(ioapic->kvm);
 		}

arch/x86/kvm/mmu/mmu.c

@@ -2027,8 +2027,8 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents)
 	} while (!sp->unsync_children);
 }
 
-static void mmu_sync_children(struct kvm_vcpu *vcpu,
+static int mmu_sync_children(struct kvm_vcpu *vcpu,
-			      struct kvm_mmu_page *parent)
+			     struct kvm_mmu_page *parent, bool can_yield)
 {
 	int i;
 	struct kvm_mmu_page *sp;
@@ -2055,12 +2055,18 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu,
 		}
 		if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) {
 			kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+			if (!can_yield) {
+				kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
+				return -EINTR;
+			}
+
 			cond_resched_rwlock_write(&vcpu->kvm->mmu_lock);
 			flush = false;
 		}
 	}
 
 	kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+	return 0;
 }
 
 static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
@@ -2146,9 +2152,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 		}
 
-		if (sp->unsync_children)
-			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
-
 		__clear_sp_write_flooding_count(sp);
 
 trace_get_page:
@@ -3684,7 +3687,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 		write_lock(&vcpu->kvm->mmu_lock);
 		kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
 
-		mmu_sync_children(vcpu, sp);
+		mmu_sync_children(vcpu, sp, true);
 
 		kvm_mmu_audit(vcpu, AUDIT_POST_SYNC);
 		write_unlock(&vcpu->kvm->mmu_lock);
@@ -3700,7 +3703,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 		if (IS_VALID_PAE_ROOT(root)) {
 			root &= PT64_BASE_ADDR_MASK;
 			sp = to_shadow_page(root);
-			mmu_sync_children(vcpu, sp);
+			mmu_sync_children(vcpu, sp, true);
 		}
 	}
 

arch/x86/kvm/mmu/page_track.c

@@ -164,13 +164,13 @@ void kvm_page_track_cleanup(struct kvm *kvm)
 	cleanup_srcu_struct(&head->track_srcu);
 }
 
-void kvm_page_track_init(struct kvm *kvm)
+int kvm_page_track_init(struct kvm *kvm)
 {
 	struct kvm_page_track_notifier_head *head;
 
 	head = &kvm->arch.track_notifier_head;
-	init_srcu_struct(&head->track_srcu);
 	INIT_HLIST_HEAD(&head->track_notifier_list);
+	return init_srcu_struct(&head->track_srcu);
 }
 
 /*

arch/x86/kvm/mmu/paging_tmpl.h

@@ -707,8 +707,27 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 		if (!is_shadow_present_pte(*it.sptep)) {
 			table_gfn = gw->table_gfn[it.level - 2];
 			access = gw->pt_access[it.level - 2];
-			sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1,
+			sp = kvm_mmu_get_page(vcpu, table_gfn, addr,
-					      false, access);
+					      it.level-1, false, access);
+			/*
+			 * We must synchronize the pagetable before linking it
+			 * because the guest doesn't need to flush tlb when
+			 * the gpte is changed from non-present to present.
+			 * Otherwise, the guest may use the wrong mapping.
+			 *
+			 * For PG_LEVEL_4K, kvm_mmu_get_page() has already
+			 * synchronized it transiently via kvm_sync_page().
+			 *
+			 * For higher level pagetable, we synchronize it via
+			 * the slower mmu_sync_children().  If it needs to
+			 * break, some progress has been made; return
+			 * RET_PF_RETRY and retry on the next #PF.
+			 * KVM_REQ_MMU_SYNC is not necessary but it
+			 * expedites the process.
+			 */
+			if (sp->unsync_children &&
+			    mmu_sync_children(vcpu, sp, false))
+				return RET_PF_RETRY;
 		}
 
 		/*
@@ -1047,14 +1066,6 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr,
  * Using the cached information from sp->gfns is safe because:
  * - The spte has a reference to the struct page, so the pfn for a given gfn
  *   can't change unless all sptes pointing to it are nuked first.
- *
- * Note:
- *   We should flush all tlbs if spte is dropped even though guest is
- *   responsible for it. Since if we don't, kvm_mmu_notifier_invalidate_page
- *   and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't
- *   used by guest then tlbs are not flushed, so guest is allowed to access the
- *   freed pages.
- *   And we increase kvm->tlbs_dirty to delay tlbs flush in this case.
  */
 static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
@@ -1107,13 +1118,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 			return 0;
 
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
-			/*
+			set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
-			 * Update spte before increasing tlbs_dirty to make
-			 * sure no tlb flush is lost after spte is zapped; see
-			 * the comments in kvm_flush_remote_tlbs().
-			 */
-			smp_wmb();
-			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}
 
@@ -1128,12 +1133,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		if (gfn != sp->gfns[i]) {
 			drop_spte(vcpu->kvm, &sp->spt[i]);
-			/*
+			set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
-			 * The same as above where we are doing
-			 * prefetch_invalid_gpte().
-			 */
-			smp_wmb();
-			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}
 

arch/x86/kvm/svm/nested.c

@@ -545,7 +545,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 		(svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) |
 		(svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits);
 
-	svm->vmcb->control.virt_ext            = svm->nested.ctl.virt_ext;
 	svm->vmcb->control.int_vector          = svm->nested.ctl.int_vector;
 	svm->vmcb->control.int_state           = svm->nested.ctl.int_state;
 	svm->vmcb->control.event_inj           = svm->nested.ctl.event_inj;
@@ -579,7 +578,7 @@ static void nested_svm_copy_common_state(struct vmcb *from_vmcb, struct vmcb *to
 }
 
 int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
-			 struct vmcb *vmcb12)
+			 struct vmcb *vmcb12, bool from_vmrun)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	int ret;
@@ -609,13 +608,16 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
 	nested_vmcb02_prepare_save(svm, vmcb12);
 
 	ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3,
-				  nested_npt_enabled(svm), true);
+				  nested_npt_enabled(svm), from_vmrun);
 	if (ret)
 		return ret;
 
 	if (!npt_enabled)
 		vcpu->arch.mmu->inject_page_fault = svm_inject_page_fault_nested;
 
+	if (!from_vmrun)
+		kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
+
 	svm_set_gif(svm, true);
 
 	return 0;
@@ -681,7 +683,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 
 	svm->nested.nested_run_pending = 1;
 
-	if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12))
+	if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true))
 		goto out_exit_err;
 
 	if (nested_svm_vmrun_msrpm(svm))

arch/x86/kvm/svm/sev.c

@@ -595,43 +595,50 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 	return 0;
 }
 
+static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
+				    int *error)
+{
+	struct sev_data_launch_update_vmsa vmsa;
+	struct vcpu_svm *svm = to_svm(vcpu);
+	int ret;
+
+	/* Perform some pre-encryption checks against the VMSA */
+	ret = sev_es_sync_vmsa(svm);
+	if (ret)
+		return ret;
+
+	/*
+	 * The LAUNCH_UPDATE_VMSA command will perform in-place encryption of
+	 * the VMSA memory content (i.e it will write the same memory region
+	 * with the guest's key), so invalidate it first.
+	 */
+	clflush_cache_range(svm->vmsa, PAGE_SIZE);
+
+	vmsa.reserved = 0;
+	vmsa.handle = to_kvm_svm(kvm)->sev_info.handle;
+	vmsa.address = __sme_pa(svm->vmsa);
+	vmsa.len = PAGE_SIZE;
+	return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+}
+
 static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-	struct sev_data_launch_update_vmsa vmsa;
 	struct kvm_vcpu *vcpu;
 	int i, ret;
 
 	if (!sev_es_guest(kvm))
 		return -ENOTTY;
 
-	vmsa.reserved = 0;
-
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		struct vcpu_svm *svm = to_svm(vcpu);
+		ret = mutex_lock_killable(&vcpu->mutex);
-
-		/* Perform some pre-encryption checks against the VMSA */
-		ret = sev_es_sync_vmsa(svm);
 		if (ret)
 			return ret;
 
-		/*
+		ret = __sev_launch_update_vmsa(kvm, vcpu, &argp->error);
-		 * The LAUNCH_UPDATE_VMSA command will perform in-place
-		 * encryption of the VMSA memory content (i.e it will write
-		 * the same memory region with the guest's key), so invalidate
-		 * it first.
-		 */
-		clflush_cache_range(svm->vmsa, PAGE_SIZE);
 
-		vmsa.handle = sev->handle;
+		mutex_unlock(&vcpu->mutex);
-		vmsa.address = __sme_pa(svm->vmsa);
-		vmsa.len = PAGE_SIZE;
-		ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa,
-				    &argp->error);
 		if (ret)
 			return ret;
-
-		svm->vcpu.arch.guest_state_protected = true;
 	}
 
 	return 0;
@@ -1397,8 +1404,10 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	/* Bind ASID to this guest */
 	ret = sev_bind_asid(kvm, start.handle, error);
-	if (ret)
+	if (ret) {
+		sev_decommission(start.handle);
 		goto e_free_session;
+	}
 
 	params.handle = start.handle;
 	if (copy_to_user((void __user *)(uintptr_t)argp->data,
@@ -1464,7 +1473,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	/* Pin guest memory */
 	guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
-				    PAGE_SIZE, &n, 0);
+				    PAGE_SIZE, &n, 1);
 	if (IS_ERR(guest_page)) {
 		ret = PTR_ERR(guest_page);
 		goto e_free_trans;
@@ -1501,6 +1510,20 @@ static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error);
 }
 
+static bool cmd_allowed_from_miror(u32 cmd_id)
+{
+	/*
+	 * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES
+	 * active mirror VMs. Also allow the debugging and status commands.
+	 */
+	if (cmd_id == KVM_SEV_LAUNCH_UPDATE_VMSA ||
+	    cmd_id == KVM_SEV_GUEST_STATUS || cmd_id == KVM_SEV_DBG_DECRYPT ||
+	    cmd_id == KVM_SEV_DBG_ENCRYPT)
+		return true;
+
+	return false;
+}
+
 int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;
@@ -1517,8 +1540,9 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 
 	mutex_lock(&kvm->lock);
 
-	/* enc_context_owner handles all memory enc operations */
+	/* Only the enc_context_owner handles some memory enc operations. */
-	if (is_mirroring_enc_context(kvm)) {
+	if (is_mirroring_enc_context(kvm) &&
+	    !cmd_allowed_from_miror(sev_cmd.id)) {
 		r = -EINVAL;
 		goto out;
 	}
@@ -1715,8 +1739,7 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 {
 	struct file *source_kvm_file;
 	struct kvm *source_kvm;
-	struct kvm_sev_info *mirror_sev;
+	struct kvm_sev_info source_sev, *mirror_sev;
-	unsigned int asid;
 	int ret;
 
 	source_kvm_file = fget(source_fd);
@@ -1739,7 +1762,8 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 		goto e_source_unlock;
 	}
 
-	asid = to_kvm_svm(source_kvm)->sev_info.asid;
+	memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info,
+	       sizeof(source_sev));
 
 	/*
 	 * The mirror kvm holds an enc_context_owner ref so its asid can't
@@ -1759,8 +1783,16 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 	/* Set enc_context_owner and copy its encryption context over */
 	mirror_sev = &to_kvm_svm(kvm)->sev_info;
 	mirror_sev->enc_context_owner = source_kvm;
-	mirror_sev->asid = asid;
 	mirror_sev->active = true;
+	mirror_sev->asid = source_sev.asid;
+	mirror_sev->fd = source_sev.fd;
+	mirror_sev->es_active = source_sev.es_active;
+	mirror_sev->handle = source_sev.handle;
+	/*
+	 * Do not copy ap_jump_table. Since the mirror does not share the same
+	 * KVM contexts as the original, and they may have different
+	 * memory-views.
+	 */
 
 	mutex_unlock(&kvm->lock);
 	return 0;

arch/x86/kvm/svm/svm.c

@@ -1566,6 +1566,8 @@ static void svm_clear_vintr(struct vcpu_svm *svm)
 
 		svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl &
 			V_IRQ_INJECTION_BITS_MASK;
+
+		svm->vmcb->control.int_vector = svm->nested.ctl.int_vector;
 	}
 
 	vmcb_mark_dirty(svm->vmcb, VMCB_INTR);
@@ -2222,6 +2224,10 @@ static int gp_interception(struct kvm_vcpu *vcpu)
 	if (error_code)
 		goto reinject;
 
+	/* All SVM instructions expect page aligned RAX */
+	if (svm->vmcb->save.rax & ~PAGE_MASK)
+		goto reinject;
+
 	/* Decode the instruction for usage later */
 	if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK)
 		goto reinject;
@@ -4285,43 +4291,44 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 	struct kvm_host_map map_save;
 	int ret;
 
-	if (is_guest_mode(vcpu)) {
+	if (!is_guest_mode(vcpu))
-		/* FED8h - SVM Guest */
+		return 0;
-		put_smstate(u64, smstate, 0x7ed8, 1);
-		/* FEE0h - SVM Guest VMCB Physical Address */
-		put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
 
-		svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
+	/* FED8h - SVM Guest */
-		svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
+	put_smstate(u64, smstate, 0x7ed8, 1);
-		svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
+	/* FEE0h - SVM Guest VMCB Physical Address */
+	put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
 
-		ret = nested_svm_vmexit(svm);
+	svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
-		if (ret)
+	svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
-			return ret;
+	svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
 
-		/*
+	ret = nested_svm_vmexit(svm);
-		 * KVM uses VMCB01 to store L1 host state while L2 runs but
+	if (ret)
-		 * VMCB01 is going to be used during SMM and thus the state will
+		return ret;
-		 * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save
-		 * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the
-		 * format of the area is identical to guest save area offsetted
-		 * by 0x400 (matches the offset of 'struct vmcb_save_area'
-		 * within 'struct vmcb'). Note: HSAVE area may also be used by
-		 * L1 hypervisor to save additional host context (e.g. KVM does
-		 * that, see svm_prepare_guest_switch()) which must be
-		 * preserved.
-		 */
-		if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
-				 &map_save) == -EINVAL)
-			return 1;
 
-		BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
+	/*
+	 * KVM uses VMCB01 to store L1 host state while L2 runs but
+	 * VMCB01 is going to be used during SMM and thus the state will
+	 * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save
+	 * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the
+	 * format of the area is identical to guest save area offsetted
+	 * by 0x400 (matches the offset of 'struct vmcb_save_area'
+	 * within 'struct vmcb'). Note: HSAVE area may also be used by
+	 * L1 hypervisor to save additional host context (e.g. KVM does
+	 * that, see svm_prepare_guest_switch()) which must be
+	 * preserved.
+	 */
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
+			 &map_save) == -EINVAL)
+		return 1;
 
-		svm_copy_vmrun_state(map_save.hva + 0x400,
+	BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
-				     &svm->vmcb01.ptr->save);
 
-		kvm_vcpu_unmap(vcpu, &map_save, true);
+	svm_copy_vmrun_state(map_save.hva + 0x400,
-	}
+			     &svm->vmcb01.ptr->save);
+
+	kvm_vcpu_unmap(vcpu, &map_save, true);
 	return 0;
 }
 
@@ -4329,50 +4336,54 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct kvm_host_map map, map_save;
-	int ret = 0;
+	u64 saved_efer, vmcb12_gpa;
+	struct vmcb *vmcb12;
+	int ret;
 
-	if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
-		u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
+		return 0;
-		u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
-		u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
-		struct vmcb *vmcb12;
 
-		if (guest) {
+	/* Non-zero if SMI arrived while vCPU was in guest mode. */
-			if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+	if (!GET_SMSTATE(u64, smstate, 0x7ed8))
-				return 1;
+		return 0;
 
-			if (!(saved_efer & EFER_SVME))
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
-				return 1;
+		return 1;
 
-			if (kvm_vcpu_map(vcpu,
+	saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
-					 gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
+	if (!(saved_efer & EFER_SVME))
-				return 1;
+		return 1;
 
-			if (svm_allocate_nested(svm))
+	vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
-				return 1;
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
+		return 1;
 
-			vmcb12 = map.hva;
+	ret = 1;
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL)
+		goto unmap_map;
 
-			nested_load_control_from_vmcb12(svm, &vmcb12->control);
+	if (svm_allocate_nested(svm))
+		goto unmap_save;
 
-			ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12);
+	/*
-			kvm_vcpu_unmap(vcpu, &map, true);
+	 * Restore L1 host state from L1 HSAVE area as VMCB01 was
+	 * used during SMM (see svm_enter_smm())
+	 */
 
-			/*
+	svm_copy_vmrun_state(&svm->vmcb01.ptr->save, map_save.hva + 0x400);
-			 * Restore L1 host state from L1 HSAVE area as VMCB01 was
-			 * used during SMM (see svm_enter_smm())
-			 */
-			if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
-					 &map_save) == -EINVAL)
-				return 1;
 
-			svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
+	/*
-					     map_save.hva + 0x400);
+	 * Enter the nested guest now
+	 */
 
-			kvm_vcpu_unmap(vcpu, &map_save, true);
+	vmcb12 = map.hva;
-		}
+	nested_load_control_from_vmcb12(svm, &vmcb12->control);
-	}
+	ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false);
 
+unmap_save:
+	kvm_vcpu_unmap(vcpu, &map_save, true);
+unmap_map:
+	kvm_vcpu_unmap(vcpu, &map, true);
 	return ret;
 }
 

arch/x86/kvm/svm/svm.h

@@ -459,7 +459,8 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm)
 	return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI);
 }
 
-int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb_gpa, struct vmcb *vmcb12);
+int enter_svm_guest_mode(struct kvm_vcpu *vcpu,
+			 u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun);
 void svm_leave_nested(struct vcpu_svm *svm);
 void svm_free_nested(struct vcpu_svm *svm);
 int svm_allocate_nested(struct vcpu_svm *svm);

arch/x86/kvm/vmx/evmcs.c

@@ -353,14 +353,20 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata)
 	switch (msr_index) {
 	case MSR_IA32_VMX_EXIT_CTLS:
 	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
-		ctl_high &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+		ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
 		break;
 	case MSR_IA32_VMX_ENTRY_CTLS:
 	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
-		ctl_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+		ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
 		break;
 	case MSR_IA32_VMX_PROCBASED_CTLS2:
-		ctl_high &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+		ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
+		break;
+	case MSR_IA32_VMX_PINBASED_CTLS:
+		ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
+		break;
+	case MSR_IA32_VMX_VMFUNC:
+		ctl_low &= ~EVMCS1_UNSUPPORTED_VMFUNC;
 		break;
 	}
 

arch/x86/kvm/vmx/nested.c

@@ -2583,8 +2583,13 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 * Guest state is invalid and unrestricted guest is disabled,
 	 * which means L1 attempted VMEntry to L2 with invalid state.
 	 * Fail the VMEntry.
+	 *
+	 * However when force loading the guest state (SMM exit or
+	 * loading nested state after migration, it is possible to
+	 * have invalid guest state now, which will be later fixed by
+	 * restoring L2 register state
 	 */
-	if (CC(!vmx_guest_state_valid(vcpu))) {
+	if (CC(from_vmentry && !vmx_guest_state_valid(vcpu))) {
 		*entry_failure_code = ENTRY_FAIL_DEFAULT;
 		return -EINVAL;
 	}
@@ -4351,6 +4356,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
 				vmcs12->vm_exit_msr_load_count))
 		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
+
+	to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
 }
 
 static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
@@ -4899,14 +4906,7 @@ out_vmcs02:
 	return -ENOMEM;
 }
 
-/*
+/* Emulate the VMXON instruction. */
- * Emulate the VMXON instruction.
- * Currently, we just remember that VMX is active, and do not save or even
- * inspect the argument to VMXON (the so-called "VMXON pointer") because we
- * do not currently need to store anything in that guest-allocated memory
- * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their
- * argument is different from the VMXON pointer (which the spec says they do).
- */
 static int handle_vmon(struct kvm_vcpu *vcpu)
 {
 	int ret;
@@ -5903,6 +5903,12 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
 	case EXIT_REASON_VMFUNC:
 		/* VM functions are emulated through L2->L0 vmexits. */
 		return true;
+	case EXIT_REASON_BUS_LOCK:
+		/*
+		 * At present, bus lock VM exit is never exposed to L1.
+		 * Handle L2's bus locks in L0 directly.
+		 */
+		return true;
 	default:
 		break;
 	}

arch/x86/kvm/vmx/vmx.c

@@ -1323,7 +1323,7 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 	vmx_prepare_switch_to_host(to_vmx(vcpu));
 }
 
-static bool emulation_required(struct kvm_vcpu *vcpu)
+bool vmx_emulation_required(struct kvm_vcpu *vcpu)
 {
 	return emulate_invalid_guest_state && !vmx_guest_state_valid(vcpu);
 }
@@ -1367,7 +1367,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 	vmcs_writel(GUEST_RFLAGS, rflags);
 
 	if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM)
-		vmx->emulation_required = emulation_required(vcpu);
+		vmx->emulation_required = vmx_emulation_required(vcpu);
 }
 
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
@@ -1837,10 +1837,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 				    &msr_info->data))
 			return 1;
 		/*
-		 * Enlightened VMCS v1 doesn't have certain fields, but buggy
+		 * Enlightened VMCS v1 doesn't have certain VMCS fields but
-		 * Hyper-V versions are still trying to use corresponding
+		 * instead of just ignoring the features, different Hyper-V
-		 * features when they are exposed. Filter out the essential
+		 * versions are either trying to use them and fail or do some
-		 * minimum.
+		 * sanity checking and refuse to boot. Filter all unsupported
+		 * features out.
 		 */
 		if (!msr_info->host_initiated &&
 		    vmx->nested.enlightened_vmcs_enabled)
@@ -3077,7 +3078,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	}
 
 	/* depends on vcpu->arch.cr0 to be set to a new value */
-	vmx->emulation_required = emulation_required(vcpu);
+	vmx->emulation_required = vmx_emulation_required(vcpu);
 }
 
 static int vmx_get_max_tdp_level(void)
@@ -3330,7 +3331,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int
 {
 	__vmx_set_segment(vcpu, var, seg);
 
-	to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
+	to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
 }
 
 static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
@@ -6621,10 +6622,24 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		     vmx->loaded_vmcs->soft_vnmi_blocked))
 		vmx->loaded_vmcs->entry_time = ktime_get();
 
-	/* Don't enter VMX if guest state is invalid, let the exit handler
+	/*
-	   start emulation until we arrive back to a valid state */
+	 * Don't enter VMX if guest state is invalid, let the exit handler
-	if (vmx->emulation_required)
+	 * start emulation until we arrive back to a valid state.  Synthesize a
+	 * consistency check VM-Exit due to invalid guest state and bail.
+	 */
+	if (unlikely(vmx->emulation_required)) {
+
+		/* We don't emulate invalid state of a nested guest */
+		vmx->fail = is_guest_mode(vcpu);
+
+		vmx->exit_reason.full = EXIT_REASON_INVALID_STATE;
+		vmx->exit_reason.failed_vmentry = 1;
+		kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1);
+		vmx->exit_qualification = ENTRY_FAIL_DEFAULT;
+		kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2);
+		vmx->exit_intr_info = 0;
 		return EXIT_FASTPATH_NONE;
+	}
 
 	trace_kvm_entry(vcpu);
 
@@ -6833,7 +6848,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 		 */
 		tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL);
 		if (tsx_ctrl)
-			vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
+			tsx_ctrl->mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
 	}
 
 	err = alloc_loaded_vmcs(&vmx->vmcs01);

arch/x86/kvm/vmx/vmx.h

@@ -248,12 +248,8 @@ struct vcpu_vmx {
 	 * only loaded into hardware when necessary, e.g. SYSCALL #UDs outside
 	 * of 64-bit mode or if EFER.SCE=1, thus the SYSCALL MSRs don't need to
 	 * be loaded into hardware if those conditions aren't met.
-	 * nr_active_uret_msrs tracks the number of MSRs that need to be loaded
-	 * into hardware when running the guest.  guest_uret_msrs[] is resorted
-	 * whenever the number of "active" uret MSRs is modified.
 	 */
 	struct vmx_uret_msr   guest_uret_msrs[MAX_NR_USER_RETURN_MSRS];
-	int                   nr_active_uret_msrs;
 	bool                  guest_uret_msrs_loaded;
 #ifdef CONFIG_X86_64
 	u64		      msr_host_kernel_gs_base;
@@ -359,6 +355,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
 void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
 			unsigned long fs_base, unsigned long gs_base);
 int vmx_get_cpl(struct kvm_vcpu *vcpu);
+bool vmx_emulation_required(struct kvm_vcpu *vcpu);
 unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu);
 void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu);

arch/x86/kvm/x86.c

@@ -1332,6 +1332,13 @@ static const u32 msrs_to_save_all[] = {
 	MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
+
+	MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3,
+	MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3,
+	MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2,
+	MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5,
+	MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2,
+	MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5,
 };
 
 static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
@@ -2969,7 +2976,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 				       offsetof(struct compat_vcpu_info, time));
 	if (vcpu->xen.vcpu_time_info_set)
 		kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0);
-	if (v == kvm_get_vcpu(v->kvm, 0))
+	if (!v->vcpu_idx)
 		kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
 	return 0;
 }
@@ -7658,6 +7665,13 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
 
 		/* Process a latched INIT or SMI, if any.  */
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+		/*
+		 * Even if KVM_SET_SREGS2 loaded PDPTRs out of band,
+		 * on SMM exit we still need to reload them from
+		 * guest memory
+		 */
+		vcpu->arch.pdptrs_from_userspace = false;
 	}
 
 	kvm_mmu_reset_context(vcpu);
@@ -10652,6 +10666,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	int r;
 
 	vcpu->arch.last_vmentry_cpu = -1;
+	vcpu->arch.regs_avail = ~0;
+	vcpu->arch.regs_dirty = ~0;
 
 	if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -10893,6 +10909,9 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
 	kvm_rip_write(vcpu, 0xfff0);
 
+	vcpu->arch.cr3 = 0;
+	kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);
+
 	/*
 	 * CR0.CD/NW are set on RESET, preserved on INIT.  Note, some versions
 	 * of Intel's SDM list CD/NW as being set on INIT, but they contradict
@@ -11139,9 +11158,15 @@ void kvm_arch_free_vm(struct kvm *kvm)
 
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
+	int ret;
+
 	if (type)
 		return -EINVAL;
 
+	ret = kvm_page_track_init(kvm);
+	if (ret)
+		return ret;
+
 	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
@@ -11174,7 +11199,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	kvm_apicv_init(kvm);
 	kvm_hv_init_vm(kvm);
-	kvm_page_track_init(kvm);
 	kvm_mmu_init_vm(kvm);
 	kvm_xen_init_vm(kvm);
 

arch/x86/net/bpf_jit_comp.c

@@ -1341,9 +1341,10 @@ st:			if (is_imm8(insn->off))
 			if (insn->imm == (BPF_AND | BPF_FETCH) ||
 			    insn->imm == (BPF_OR | BPF_FETCH) ||
 			    insn->imm == (BPF_XOR | BPF_FETCH)) {
-				u8 *branch_target;
 				bool is64 = BPF_SIZE(insn->code) == BPF_DW;
 				u32 real_src_reg = src_reg;
+				u32 real_dst_reg = dst_reg;
+				u8 *branch_target;
 
 				/*
 				 * Can't be implemented with a single x86 insn.
@@ -1354,11 +1355,13 @@ st:			if (is_imm8(insn->off))
 				emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0);
 				if (src_reg == BPF_REG_0)
 					real_src_reg = BPF_REG_AX;
+				if (dst_reg == BPF_REG_0)
+					real_dst_reg = BPF_REG_AX;
 
 				branch_target = prog;
 				/* Load old value */
 				emit_ldx(&prog, BPF_SIZE(insn->code),
-					 BPF_REG_0, dst_reg, insn->off);
+					 BPF_REG_0, real_dst_reg, insn->off);
 				/*
 				 * Perform the (commutative) operation locally,
 				 * put the result in the AUX_REG.
@@ -1369,7 +1372,8 @@ st:			if (is_imm8(insn->off))
 				      add_2reg(0xC0, AUX_REG, real_src_reg));
 				/* Attempt to swap in new value */
 				err = emit_atomic(&prog, BPF_CMPXCHG,
-						  dst_reg, AUX_REG, insn->off,
+						  real_dst_reg, AUX_REG,
+						  insn->off,
 						  BPF_SIZE(insn->code));
 				if (WARN_ON(err))
 					return err;
@@ -1383,11 +1387,10 @@ st:			if (is_imm8(insn->off))
 				/* Restore R0 after clobbering RAX */
 				emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX);
 				break;
-
 			}
 
 			err = emit_atomic(&prog, insn->imm, dst_reg, src_reg,
-						  insn->off, BPF_SIZE(insn->code));
+					  insn->off, BPF_SIZE(insn->code));
 			if (err)
 				return err;
 			break;
@@ -1744,7 +1747,7 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
 }
 
 static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
-			   struct bpf_prog *p, int stack_size, bool mod_ret)
+			   struct bpf_prog *p, int stack_size, bool save_ret)
 {
 	u8 *prog = *pprog;
 	u8 *jmp_insn;
@@ -1777,11 +1780,15 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	if (emit_call(&prog, p->bpf_func, prog))
 		return -EINVAL;
 
-	/* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return
+	/*
+	 * BPF_TRAMP_MODIFY_RETURN trampolines can modify the return
 	 * of the previous call which is then passed on the stack to
 	 * the next BPF program.
+	 *
+	 * BPF_TRAMP_FENTRY trampoline may need to return the return
+	 * value of BPF_PROG_TYPE_STRUCT_OPS prog.
 	 */
-	if (mod_ret)
+	if (save_ret)
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 
 	/* replace 2 nops with JE insn, since jmp target is known */
@@ -1828,13 +1835,15 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
 }
 
 static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
-		      struct bpf_tramp_progs *tp, int stack_size)
+		      struct bpf_tramp_progs *tp, int stack_size,
+		      bool save_ret)
 {
 	int i;
 	u8 *prog = *pprog;
 
 	for (i = 0; i < tp->nr_progs; i++) {
-		if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, false))
+		if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size,
+				    save_ret))
 			return -EINVAL;
 	}
 	*pprog = prog;
@@ -1877,6 +1886,23 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
 	return 0;
 }
 
+static bool is_valid_bpf_tramp_flags(unsigned int flags)
+{
+	if ((flags & BPF_TRAMP_F_RESTORE_REGS) &&
+	    (flags & BPF_TRAMP_F_SKIP_FRAME))
+		return false;
+
+	/*
+	 * BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops,
+	 * and it must be used alone.
+	 */
+	if ((flags & BPF_TRAMP_F_RET_FENTRY_RET) &&
+	    (flags & ~BPF_TRAMP_F_RET_FENTRY_RET))
+		return false;
+
+	return true;
+}
+
 /* Example:
  * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
  * its 'struct btf_func_model' will be nr_args=2
@@ -1949,17 +1975,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN];
 	u8 **branches = NULL;
 	u8 *prog;
+	bool save_ret;
 
 	/* x86-64 supports up to 6 arguments. 7+ can be added in the future */
 	if (nr_args > 6)
 		return -ENOTSUPP;
 
-	if ((flags & BPF_TRAMP_F_RESTORE_REGS) &&
+	if (!is_valid_bpf_tramp_flags(flags))
-	    (flags & BPF_TRAMP_F_SKIP_FRAME))
 		return -EINVAL;
 
-	if (flags & BPF_TRAMP_F_CALL_ORIG)
+	/* room for return value of orig_call or fentry prog */
-		stack_size += 8; /* room for return value of orig_call */
+	save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET);
+	if (save_ret)
+		stack_size += 8;
 
 	if (flags & BPF_TRAMP_F_IP_ARG)
 		stack_size += 8; /* room for IP address argument */
@@ -2005,7 +2033,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	}
 
 	if (fentry->nr_progs)
-		if (invoke_bpf(m, &prog, fentry, stack_size))
+		if (invoke_bpf(m, &prog, fentry, stack_size,
+			       flags & BPF_TRAMP_F_RET_FENTRY_RET))
 			return -EINVAL;
 
 	if (fmod_ret->nr_progs) {
@@ -2052,7 +2081,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	}
 
 	if (fexit->nr_progs)
-		if (invoke_bpf(m, &prog, fexit, stack_size)) {
+		if (invoke_bpf(m, &prog, fexit, stack_size, false)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
@@ -2072,9 +2101,10 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 			ret = -EINVAL;
 			goto cleanup;
 		}
-		/* restore original return value back into RAX */
-		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
 	}
+	/* restore return value of orig_call or fentry prog back into RAX */
+	if (save_ret)
+		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
 
 	EMIT1(0x5B); /* pop rbx */
 	EMIT1(0xC9); /* leave */

block/bfq-iosched.c

@@ -2662,15 +2662,6 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
 	 * are likely to increase the throughput.
 	 */
 	bfqq->new_bfqq = new_bfqq;
-	/*
-	 * The above assignment schedules the following redirections:
-	 * each time some I/O for bfqq arrives, the process that
-	 * generated that I/O is disassociated from bfqq and
-	 * associated with new_bfqq. Here we increases new_bfqq->ref
-	 * in advance, adding the number of processes that are
-	 * expected to be associated with new_bfqq as they happen to
-	 * issue I/O.
-	 */
 	new_bfqq->ref += process_refs;
 	return new_bfqq;
 }
@@ -2733,10 +2724,6 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 {
 	struct bfq_queue *in_service_bfqq, *new_bfqq;
 
-	/* if a merge has already been setup, then proceed with that first */
-	if (bfqq->new_bfqq)
-		return bfqq->new_bfqq;
-
 	/*
 	 * Check delayed stable merge for rotational or non-queueing
 	 * devs. For this branch to be executed, bfqq must not be
@@ -2838,6 +2825,9 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	if (bfq_too_late_for_merging(bfqq))
 		return NULL;
 
+	if (bfqq->new_bfqq)
+		return bfqq->new_bfqq;
+
 	if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq))
 		return NULL;
 

drivers/acpi/nfit/core.c

@@ -3007,6 +3007,18 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 		ndr_desc->target_node = NUMA_NO_NODE;
 	}
 
+	/* Fallback to address based numa information if node lookup failed */
+	if (ndr_desc->numa_node == NUMA_NO_NODE) {
+		ndr_desc->numa_node = memory_add_physaddr_to_nid(spa->address);
+		dev_info(acpi_desc->dev, "changing numa node from %d to %d for nfit region [%pa-%pa]",
+			NUMA_NO_NODE, ndr_desc->numa_node, &res.start, &res.end);
+	}
+	if (ndr_desc->target_node == NUMA_NO_NODE) {
+		ndr_desc->target_node = phys_to_target_node(spa->address);
+		dev_info(acpi_desc->dev, "changing target node from %d to %d for nfit region [%pa-%pa]",
+			NUMA_NO_NODE, ndr_desc->numa_node, &res.start, &res.end);
+	}
+
 	/*
 	 * Persistence domain bits are hierarchical, if
 	 * ACPI_NFIT_CAPABILITY_CACHE_FLUSH is set then

drivers/base/core.c

@@ -95,12 +95,29 @@ int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup)
 
 	list_add(&link->s_hook, &sup->consumers);
 	list_add(&link->c_hook, &con->suppliers);
+	pr_debug("%pfwP Linked as a fwnode consumer to %pfwP\n",
+		 con, sup);
 out:
 	mutex_unlock(&fwnode_link_lock);
 
 	return ret;
 }
 
+/**
+ * __fwnode_link_del - Delete a link between two fwnode_handles.
+ * @link: the fwnode_link to be deleted
+ *
+ * The fwnode_link_lock needs to be held when this function is called.
+ */
+static void __fwnode_link_del(struct fwnode_link *link)
+{
+	pr_debug("%pfwP Dropping the fwnode link to %pfwP\n",
+		 link->consumer, link->supplier);
+	list_del(&link->s_hook);
+	list_del(&link->c_hook);
+	kfree(link);
+}
+
 /**
  * fwnode_links_purge_suppliers - Delete all supplier links of fwnode_handle.
  * @fwnode: fwnode whose supplier links need to be deleted
@@ -112,11 +129,8 @@ static void fwnode_links_purge_suppliers(struct fwnode_handle *fwnode)
 	struct fwnode_link *link, *tmp;
 
 	mutex_lock(&fwnode_link_lock);
-	list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) {
+	list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook)
-		list_del(&link->s_hook);
+		__fwnode_link_del(link);
-		list_del(&link->c_hook);
-		kfree(link);
-	}
 	mutex_unlock(&fwnode_link_lock);
 }
 
@@ -131,11 +145,8 @@ static void fwnode_links_purge_consumers(struct fwnode_handle *fwnode)
 	struct fwnode_link *link, *tmp;
 
 	mutex_lock(&fwnode_link_lock);
-	list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) {
+	list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook)
-		list_del(&link->s_hook);
+		__fwnode_link_del(link);
-		list_del(&link->c_hook);
-		kfree(link);
-	}
 	mutex_unlock(&fwnode_link_lock);
 }
 
@@ -975,6 +986,7 @@ int device_links_check_suppliers(struct device *dev)
 {
 	struct device_link *link;
 	int ret = 0;
+	struct fwnode_handle *sup_fw;
 
 	/*
 	 * Device waiting for supplier to become available is not allowed to
@@ -983,10 +995,11 @@ int device_links_check_suppliers(struct device *dev)
 	mutex_lock(&fwnode_link_lock);
 	if (dev->fwnode && !list_empty(&dev->fwnode->suppliers) &&
 	    !fw_devlink_is_permissive()) {
-		dev_dbg(dev, "probe deferral - wait for supplier %pfwP\n",
+		sup_fw = list_first_entry(&dev->fwnode->suppliers,
-			list_first_entry(&dev->fwnode->suppliers,
+					  struct fwnode_link,
-			struct fwnode_link,
+					  c_hook)->supplier;
-			c_hook)->supplier);
+		dev_err_probe(dev, -EPROBE_DEFER, "wait for supplier %pfwP\n",
+			      sup_fw);
 		mutex_unlock(&fwnode_link_lock);
 		return -EPROBE_DEFER;
 	}
@@ -1001,8 +1014,9 @@ int device_links_check_suppliers(struct device *dev)
 		if (link->status != DL_STATE_AVAILABLE &&
 		    !(link->flags & DL_FLAG_SYNC_STATE_ONLY)) {
 			device_links_missing_supplier(dev);
-			dev_dbg(dev, "probe deferral - supplier %s not ready\n",
+			dev_err_probe(dev, -EPROBE_DEFER,
-				dev_name(link->supplier));
+				      "supplier %s not ready\n",
+				      dev_name(link->supplier));
 			ret = -EPROBE_DEFER;
 			break;
 		}
@@ -1722,6 +1736,25 @@ static int fw_devlink_create_devlink(struct device *con,
 	struct device *sup_dev;
 	int ret = 0;
 
+	/*
+	 * In some cases, a device P might also be a supplier to its child node
+	 * C. However, this would defer the probe of C until the probe of P
+	 * completes successfully. This is perfectly fine in the device driver
+	 * model. device_add() doesn't guarantee probe completion of the device
+	 * by the time it returns.
+	 *
+	 * However, there are a few drivers that assume C will finish probing
+	 * as soon as it's added and before P finishes probing. So, we provide
+	 * a flag to let fw_devlink know not to delay the probe of C until the
+	 * probe of P completes successfully.
+	 *
+	 * When such a flag is set, we can't create device links where P is the
+	 * supplier of C as that would delay the probe of C.
+	 */
+	if (sup_handle->flags & FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD &&
+	    fwnode_is_ancestor_of(sup_handle, con->fwnode))
+		return -EINVAL;
+
 	sup_dev = get_dev_from_fwnode(sup_handle);
 	if (sup_dev) {
 		/*
@@ -1772,14 +1805,21 @@ static int fw_devlink_create_devlink(struct device *con,
 	 * be broken by applying logic. Check for these types of cycles and
 	 * break them so that devices in the cycle probe properly.
 	 *
-	 * If the supplier's parent is dependent on the consumer, then
+	 * If the supplier's parent is dependent on the consumer, then the
-	 * the consumer-supplier dependency is a false dependency. So,
+	 * consumer and supplier have a cyclic dependency. Since fw_devlink
-	 * treat it as an invalid link.
+	 * can't tell which of the inferred dependencies are incorrect, don't
+	 * enforce probe ordering between any of the devices in this cyclic
+	 * dependency. Do this by relaxing all the fw_devlink device links in
+	 * this cycle and by treating the fwnode link between the consumer and
+	 * the supplier as an invalid dependency.
 	 */
 	sup_dev = fwnode_get_next_parent_dev(sup_handle);
 	if (sup_dev && device_is_dependent(con, sup_dev)) {
-		dev_dbg(con, "Not linking to %pfwP - False link\n",
+		dev_info(con, "Fixing up cyclic dependency with %pfwP (%s)\n",
-			sup_handle);
+			 sup_handle, dev_name(sup_dev));
+		device_links_write_lock();
+		fw_devlink_relax_cycle(con, sup_dev);
+		device_links_write_unlock();
 		ret = -EINVAL;
 	} else {
 		/*
@@ -1858,9 +1898,7 @@ static void __fw_devlink_link_to_consumers(struct device *dev)
 		if (!own_link || ret == -EAGAIN)
 			continue;
 
-		list_del(&link->s_hook);
+		__fwnode_link_del(link);
-		list_del(&link->c_hook);
-		kfree(link);
 	}
 }
 
@@ -1912,9 +1950,7 @@ static void __fw_devlink_link_to_suppliers(struct device *dev,
 		if (!own_link || ret == -EAGAIN)
 			continue;
 
-		list_del(&link->s_hook);
+		__fwnode_link_del(link);
-		list_del(&link->c_hook);
-		kfree(link);
 
 		/* If no device link was created, nothing more to do. */
 		if (ret)

drivers/block/nbd.c

@@ -97,13 +97,18 @@ struct nbd_config {
 
 	atomic_t recv_threads;
 	wait_queue_head_t recv_wq;
-	loff_t blksize;
+	unsigned int blksize_bits;
 	loff_t bytesize;
 #if IS_ENABLED(CONFIG_DEBUG_FS)
 	struct dentry *dbg_dir;
 #endif
 };
 
+static inline unsigned int nbd_blksize(struct nbd_config *config)
+{
+	return 1u << config->blksize_bits;
+}
+
 struct nbd_device {
 	struct blk_mq_tag_set tag_set;
 
@@ -146,7 +151,7 @@ static struct dentry *nbd_dbg_dir;
 
 #define NBD_MAGIC 0x68797548
 
-#define NBD_DEF_BLKSIZE 1024
+#define NBD_DEF_BLKSIZE_BITS 10
 
 static unsigned int nbds_max = 16;
 static int max_part = 16;
@@ -317,12 +322,12 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 		loff_t blksize)
 {
 	if (!blksize)
-		blksize = NBD_DEF_BLKSIZE;
+		blksize = 1u << NBD_DEF_BLKSIZE_BITS;
 	if (blksize < 512 || blksize > PAGE_SIZE || !is_power_of_2(blksize))
 		return -EINVAL;
 
 	nbd->config->bytesize = bytesize;
-	nbd->config->blksize = blksize;
+	nbd->config->blksize_bits = __ffs(blksize);
 
 	if (!nbd->task_recv)
 		return 0;
@@ -1337,7 +1342,7 @@ static int nbd_start_device(struct nbd_device *nbd)
 		args->index = i;
 		queue_work(nbd->recv_workq, &args->work);
 	}
-	return nbd_set_size(nbd, config->bytesize, config->blksize);
+	return nbd_set_size(nbd, config->bytesize, nbd_blksize(config));
 }
 
 static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev)
@@ -1406,11 +1411,11 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 	case NBD_SET_BLKSIZE:
 		return nbd_set_size(nbd, config->bytesize, arg);
 	case NBD_SET_SIZE:
-		return nbd_set_size(nbd, arg, config->blksize);
+		return nbd_set_size(nbd, arg, nbd_blksize(config));
 	case NBD_SET_SIZE_BLOCKS:
-		if (check_mul_overflow((loff_t)arg, config->blksize, &bytesize))
+		if (check_shl_overflow(arg, config->blksize_bits, &bytesize))
 			return -EINVAL;
-		return nbd_set_size(nbd, bytesize, config->blksize);
+		return nbd_set_size(nbd, bytesize, nbd_blksize(config));
 	case NBD_SET_TIMEOUT:
 		nbd_set_cmd_timeout(nbd, arg);
 		return 0;
@@ -1476,7 +1481,7 @@ static struct nbd_config *nbd_alloc_config(void)
 	atomic_set(&config->recv_threads, 0);
 	init_waitqueue_head(&config->recv_wq);
 	init_waitqueue_head(&config->conn_wait);
-	config->blksize = NBD_DEF_BLKSIZE;
+	config->blksize_bits = NBD_DEF_BLKSIZE_BITS;
 	atomic_set(&config->live_connections, 0);
 	try_module_get(THIS_MODULE);
 	return config;
@@ -1604,7 +1609,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd)
 	debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_fops);
 	debugfs_create_u64("size_bytes", 0444, dir, &config->bytesize);
 	debugfs_create_u32("timeout", 0444, dir, &nbd->tag_set.timeout);
-	debugfs_create_u64("blocksize", 0444, dir, &config->blksize);
+	debugfs_create_u32("blocksize_bits", 0444, dir, &config->blksize_bits);
 	debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_fops);
 
 	return 0;
@@ -1826,7 +1831,7 @@ nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = {
 static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd)
 {
 	struct nbd_config *config = nbd->config;
-	u64 bsize = config->blksize;
+	u64 bsize = nbd_blksize(config);
 	u64 bytes = config->bytesize;
 
 	if (info->attrs[NBD_ATTR_SIZE_BYTES])
@@ -1835,7 +1840,7 @@ static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd)
 	if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES])
 		bsize = nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]);
 
-	if (bytes != config->bytesize || bsize != config->blksize)
+	if (bytes != config->bytesize || bsize != nbd_blksize(config))
 		return nbd_set_size(nbd, bytes, bsize);
 	return 0;
 }

drivers/crypto/ccp/ccp-ops.c

@@ -778,7 +778,7 @@ ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 				    in_place ? DMA_BIDIRECTIONAL
 					     : DMA_TO_DEVICE);
 		if (ret)
-			goto e_ctx;
+			goto e_aad;
 
 		if (in_place) {
 			dst = src;
@@ -863,7 +863,7 @@ ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	op.u.aes.size = 0;
 	ret = cmd_q->ccp->vdata->perform->aes(&op);
 	if (ret)
-		goto e_dst;
+		goto e_final_wa;
 
 	if (aes->action == CCP_AES_ACTION_ENCRYPT) {
 		/* Put the ciphered tag after the ciphertext. */
@@ -873,17 +873,19 @@ ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		ret = ccp_init_dm_workarea(&tag, cmd_q, authsize,
 					   DMA_BIDIRECTIONAL);
 		if (ret)
-			goto e_tag;
+			goto e_final_wa;
 		ret = ccp_set_dm_area(&tag, 0, p_tag, 0, authsize);
-		if (ret)
+		if (ret) {
-			goto e_tag;
+			ccp_dm_free(&tag);
+			goto e_final_wa;
+		}
 
 		ret = crypto_memneq(tag.address, final_wa.address,
 				    authsize) ? -EBADMSG : 0;
 		ccp_dm_free(&tag);
 	}
 
-e_tag:
+e_final_wa:
 	ccp_dm_free(&final_wa);
 
 e_dst:

drivers/gpio/gpio-pca953x.c

@@ -468,15 +468,8 @@ static int pca953x_gpio_get_value(struct gpio_chip *gc, unsigned off)
 	mutex_lock(&chip->i2c_lock);
 	ret = regmap_read(chip->regmap, inreg, &reg_val);
 	mutex_unlock(&chip->i2c_lock);
-	if (ret < 0) {
+	if (ret < 0)
-		/*
+		return ret;
-		 * NOTE:
-		 * diagnostic already emitted; that's all we should
-		 * do unless gpio_*_value_cansleep() calls become different
-		 * from their nonsleeping siblings (and report faults).
-		 */
-		return 0;
-	}
 
 	return !!(reg_val & bit);
 }

drivers/gpio/gpio-rockchip.c

@@ -689,6 +689,7 @@ static int rockchip_gpio_probe(struct platform_device *pdev)
 	struct device_node *pctlnp = of_get_parent(np);
 	struct pinctrl_dev *pctldev = NULL;
 	struct rockchip_pin_bank *bank = NULL;
+	struct rockchip_pin_output_deferred *cfg;
 	static int gpio;
 	int id, ret;
 
@@ -716,12 +717,33 @@ static int rockchip_gpio_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	/*
+	 * Prevent clashes with a deferred output setting
+	 * being added right at this moment.
+	 */
+	mutex_lock(&bank->deferred_lock);
+
 	ret = rockchip_gpiolib_register(bank);
 	if (ret) {
 		clk_disable_unprepare(bank->clk);
+		mutex_unlock(&bank->deferred_lock);
 		return ret;
 	}
 
+	while (!list_empty(&bank->deferred_output)) {
+		cfg = list_first_entry(&bank->deferred_output,
+				       struct rockchip_pin_output_deferred, head);
+		list_del(&cfg->head);
+
+		ret = rockchip_gpio_direction_output(&bank->gpio_chip, cfg->pin, cfg->arg);
+		if (ret)
+			dev_warn(dev, "setting output pin %u to %u failed\n", cfg->pin, cfg->arg);
+
+		kfree(cfg);
+	}
+
+	mutex_unlock(&bank->deferred_lock);
+
 	platform_set_drvdata(pdev, bank);
 	dev_info(dev, "probed %pOF\n", np);
 

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

@@ -837,6 +837,28 @@ static int convert_tiling_flags_to_modifier(struct amdgpu_framebuffer *afb)
 	return 0;
 }
 
+/* Mirrors the is_displayable check in radeonsi's gfx6_compute_surface */
+static int check_tiling_flags_gfx6(struct amdgpu_framebuffer *afb)
+{
+	u64 micro_tile_mode;
+
+	/* Zero swizzle mode means linear */
+	if (AMDGPU_TILING_GET(afb->tiling_flags, SWIZZLE_MODE) == 0)
+		return 0;
+
+	micro_tile_mode = AMDGPU_TILING_GET(afb->tiling_flags, MICRO_TILE_MODE);
+	switch (micro_tile_mode) {
+	case 0: /* DISPLAY */
+	case 3: /* RENDER */
+		return 0;
+	default:
+		drm_dbg_kms(afb->base.dev,
+			    "Micro tile mode %llu not supported for scanout\n",
+			    micro_tile_mode);
+		return -EINVAL;
+	}
+}
+
 static void get_block_dimensions(unsigned int block_log2, unsigned int cpp,
 				 unsigned int *width, unsigned int *height)
 {
@@ -1103,6 +1125,7 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev,
 				    const struct drm_mode_fb_cmd2 *mode_cmd,
 				    struct drm_gem_object *obj)
 {
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int ret, i;
 
 	/*
@@ -1122,6 +1145,14 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev,
 	if (ret)
 		return ret;
 
+	if (!dev->mode_config.allow_fb_modifiers) {
+		drm_WARN_ONCE(dev, adev->family >= AMDGPU_FAMILY_AI,
+			      "GFX9+ requires FB check based on format modifier\n");
+		ret = check_tiling_flags_gfx6(rfb);
+		if (ret)
+			return ret;
+	}
+
 	if (dev->mode_config.allow_fb_modifiers &&
 	    !(rfb->base.flags & DRM_MODE_FB_MODIFIERS)) {
 		ret = convert_tiling_flags_to_modifier(rfb);

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -3599,7 +3599,7 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
 
 	/* set static priority for a queue/ring */
 	gfx_v9_0_mqd_set_priority(ring, mqd);
-	mqd->cp_hqd_quantum = RREG32(mmCP_HQD_QUANTUM);
+	mqd->cp_hqd_quantum = RREG32_SOC15(GC, 0, mmCP_HQD_QUANTUM);
 
 	/* map_queues packet doesn't need activate the queue,
 	 * so only kiq need set this field.

drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c

@@ -1098,6 +1098,8 @@ static int gmc_v10_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	gmc_v10_0_gart_disable(adev);
+
 	if (amdgpu_sriov_vf(adev)) {
 		/* full access mode, so don't touch any GMC register */
 		DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
@@ -1106,7 +1108,6 @@ static int gmc_v10_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
-	gmc_v10_0_gart_disable(adev);
 
 	return 0;
 }

drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c

@@ -1794,6 +1794,8 @@ static int gmc_v9_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	gmc_v9_0_gart_disable(adev);
+
 	if (amdgpu_sriov_vf(adev)) {
 		/* full access mode, so don't touch any GMC register */
 		DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
@@ -1802,7 +1804,6 @@ static int gmc_v9_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
-	gmc_v9_0_gart_disable(adev);
 
 	return 0;
 }

drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c

@@ -868,6 +868,12 @@ static int sdma_v5_2_start(struct amdgpu_device *adev)
 			msleep(1000);
 	}
 
+	/* TODO: check whether can submit a doorbell request to raise
+	 * a doorbell fence to exit gfxoff.
+	 */
+	if (adev->in_s0ix)
+		amdgpu_gfx_off_ctrl(adev, false);
+
 	sdma_v5_2_soft_reset(adev);
 	/* unhalt the MEs */
 	sdma_v5_2_enable(adev, true);
@@ -876,6 +882,8 @@ static int sdma_v5_2_start(struct amdgpu_device *adev)
 
 	/* start the gfx rings and rlc compute queues */
 	r = sdma_v5_2_gfx_resume(adev);
+	if (adev->in_s0ix)
+		amdgpu_gfx_off_ctrl(adev, true);
 	if (r)
 		return r;
 	r = sdma_v5_2_rlc_resume(adev);

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -1115,6 +1115,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	init_data.asic_id.pci_revision_id = adev->pdev->revision;
 	init_data.asic_id.hw_internal_rev = adev->external_rev_id;
+	init_data.asic_id.chip_id = adev->pdev->device;
 
 	init_data.asic_id.vram_width = adev->gmc.vram_width;
 	/* TODO: initialize init_data.asic_id.vram_type here!!!! */
@@ -1719,6 +1720,7 @@ static int dm_late_init(void *handle)
 		linear_lut[i] = 0xFFFF * i / 15;
 
 	params.set = 0;
+	params.backlight_ramping_override = false;
 	params.backlight_ramping_start = 0xCCCC;
 	params.backlight_ramping_reduction = 0xCCCCCCCC;
 	params.backlight_lut_array_size = 16;

drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c

@@ -1826,14 +1826,13 @@ bool perform_link_training_with_retries(
 		if (panel_mode == DP_PANEL_MODE_EDP) {
 			struct cp_psp *cp_psp = &stream->ctx->cp_psp;
 
-			if (cp_psp && cp_psp->funcs.enable_assr) {
+			if (cp_psp && cp_psp->funcs.enable_assr)
-				if (!cp_psp->funcs.enable_assr(cp_psp->handle, link)) {
+				/* ASSR is bound to fail with unsigned PSP
-					/* since eDP implies ASSR on, change panel
+				 * verstage used during devlopment phase.
-					 * mode to disable ASSR
+				 * Report and continue with eDP panel mode to
-					 */
+				 * perform eDP link training with right settings
-					panel_mode = DP_PANEL_MODE_DEFAULT;
+				 */
-				}
+				cp_psp->funcs.enable_assr(cp_psp->handle, link);
-			}
 		}
 #endif
 

drivers/gpu/drm/exynos/exynos5433_drm_decon.c

@@ -793,7 +793,6 @@ static int exynos5433_decon_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct decon_context *ctx;
-	struct resource *res;
 	int ret;
 	int i;
 
@@ -818,8 +817,7 @@ static int exynos5433_decon_probe(struct platform_device *pdev)
 		ctx->clks[i] = clk;
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ctx->addr = devm_platform_ioremap_resource(pdev, 0);
-	ctx->addr = devm_ioremap_resource(dev, res);
 	if (IS_ERR(ctx->addr))
 		return PTR_ERR(ctx->addr);
 

drivers/gpu/drm/exynos/exynos_drm_dsi.c

@@ -1738,7 +1738,6 @@ static const struct component_ops exynos_dsi_component_ops = {
 static int exynos_dsi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct resource *res;
 	struct exynos_dsi *dsi;
 	int ret, i;
 
@@ -1789,8 +1788,7 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 		}
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	dsi->reg_base = devm_platform_ioremap_resource(pdev, 0);
-	dsi->reg_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(dsi->reg_base))
 		return PTR_ERR(dsi->reg_base);
 

drivers/gpu/drm/exynos/exynos_drm_fimc.c

@@ -85,7 +85,6 @@ struct fimc_scaler {
 /*
  * A structure of fimc context.
  *
- * @regs_res: register resources.
  * @regs: memory mapped io registers.
  * @lock: locking of operations.
  * @clocks: fimc clocks.
@@ -103,7 +102,6 @@ struct fimc_context {
 	struct exynos_drm_ipp_formats	*formats;
 	unsigned int			num_formats;
 
-	struct resource	*regs_res;
 	void __iomem	*regs;
 	spinlock_t	lock;
 	struct clk	*clocks[FIMC_CLKS_MAX];
@@ -1327,8 +1325,7 @@ static int fimc_probe(struct platform_device *pdev)
 	ctx->num_formats = num_formats;
 
 	/* resource memory */
-	ctx->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ctx->regs = devm_platform_ioremap_resource(pdev, 0);
-	ctx->regs = devm_ioremap_resource(dev, ctx->regs_res);
 	if (IS_ERR(ctx->regs))
 		return PTR_ERR(ctx->regs);
 

drivers/gpu/drm/exynos/exynos_drm_fimd.c

@@ -1202,9 +1202,7 @@ static int fimd_probe(struct platform_device *pdev)
 		return PTR_ERR(ctx->lcd_clk);
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ctx->regs = devm_platform_ioremap_resource(pdev, 0);
-
-	ctx->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(ctx->regs))
 		return PTR_ERR(ctx->regs);
 

drivers/gpu/drm/exynos/exynos_drm_g2d.c

@@ -1449,7 +1449,6 @@ static const struct component_ops g2d_component_ops = {
 static int g2d_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct resource *res;
 	struct g2d_data *g2d;
 	int ret;
 
@@ -1491,9 +1490,7 @@ static int g2d_probe(struct platform_device *pdev)
 	clear_bit(G2D_BIT_SUSPEND_RUNQUEUE, &g2d->flags);
 	clear_bit(G2D_BIT_ENGINE_BUSY, &g2d->flags);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	g2d->regs = devm_platform_ioremap_resource(pdev, 0);
-
-	g2d->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(g2d->regs)) {
 		ret = PTR_ERR(g2d->regs);
 		goto err_put_clk;

drivers/gpu/drm/exynos/exynos_drm_gsc.c

@@ -86,7 +86,6 @@ struct gsc_scaler {
 /*
  * A structure of gsc context.
  *
- * @regs_res: register resources.
  * @regs: memory mapped io registers.
  * @gsc_clk: gsc gate clock.
  * @sc: scaler infomations.
@@ -103,7 +102,6 @@ struct gsc_context {
 	struct exynos_drm_ipp_formats	*formats;
 	unsigned int			num_formats;
 
-	struct resource	*regs_res;
 	void __iomem	*regs;
 	const char	**clk_names;
 	struct clk	*clocks[GSC_MAX_CLOCKS];
@@ -1272,9 +1270,7 @@ static int gsc_probe(struct platform_device *pdev)
 		}
 	}
 
-	/* resource memory */
+	ctx->regs = devm_platform_ioremap_resource(pdev, 0);
-	ctx->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ctx->regs = devm_ioremap_resource(dev, ctx->regs_res);
 	if (IS_ERR(ctx->regs))
 		return PTR_ERR(ctx->regs);
 

drivers/gpu/drm/exynos/exynos_drm_rotator.c

@@ -278,7 +278,6 @@ static const struct component_ops rotator_component_ops = {
 static int rotator_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct resource	*regs_res;
 	struct rot_context *rot;
 	const struct rot_variant *variant;
 	int irq;
@@ -292,8 +291,7 @@ static int rotator_probe(struct platform_device *pdev)
 	rot->formats = variant->formats;
 	rot->num_formats = variant->num_formats;
 	rot->dev = dev;
-	regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	rot->regs = devm_platform_ioremap_resource(pdev, 0);
-	rot->regs = devm_ioremap_resource(dev, regs_res);
 	if (IS_ERR(rot->regs))
 		return PTR_ERR(rot->regs);
 

drivers/gpu/drm/exynos/exynos_drm_scaler.c

@@ -485,7 +485,6 @@ static const struct component_ops scaler_component_ops = {
 static int scaler_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct resource	*regs_res;
 	struct scaler_context *scaler;
 	int irq;
 	int ret, i;
@@ -498,8 +497,7 @@ static int scaler_probe(struct platform_device *pdev)
 		(struct scaler_data *)of_device_get_match_data(dev);
 
 	scaler->dev = dev;
-	regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	scaler->regs = devm_platform_ioremap_resource(pdev, 0);
-	scaler->regs = devm_ioremap_resource(dev, regs_res);
 	if (IS_ERR(scaler->regs))
 		return PTR_ERR(scaler->regs);
 

drivers/gpu/drm/exynos/exynos_hdmi.c

@@ -1957,7 +1957,6 @@ static int hdmi_probe(struct platform_device *pdev)
 	struct hdmi_audio_infoframe *audio_infoframe;
 	struct device *dev = &pdev->dev;
 	struct hdmi_context *hdata;
-	struct resource *res;
 	int ret;
 
 	hdata = devm_kzalloc(dev, sizeof(struct hdmi_context), GFP_KERNEL);
@@ -1979,8 +1978,7 @@ static int hdmi_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	hdata->regs = devm_platform_ioremap_resource(pdev, 0);
-	hdata->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(hdata->regs)) {
 		ret = PTR_ERR(hdata->regs);
 		return ret;

drivers/gpu/drm/i915/gt/intel_context.c

@@ -362,8 +362,9 @@ static int __intel_context_active(struct i915_active *active)
 	return 0;
 }
 
-static int sw_fence_dummy_notify(struct i915_sw_fence *sf,
+static int __i915_sw_fence_call
-				 enum i915_sw_fence_notify state)
+sw_fence_dummy_notify(struct i915_sw_fence *sf,
+		      enum i915_sw_fence_notify state)
 {
 	return NOTIFY_DONE;
 }

drivers/gpu/drm/i915/gt/intel_rps.c

@@ -882,8 +882,6 @@ void intel_rps_park(struct intel_rps *rps)
 	if (!intel_rps_is_enabled(rps))
 		return;
 
-	GEM_BUG_ON(atomic_read(&rps->num_waiters));
-
 	if (!intel_rps_clear_active(rps))
 		return;
 

drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h

@@ -102,11 +102,11 @@ static_assert(sizeof(struct guc_ct_buffer_desc) == 64);
  *  |   +-------+--------------------------------------------------------------+
  *  |   |   7:0 | NUM_DWORDS = length (in dwords) of the embedded HXG message  |
  *  +---+-------+--------------------------------------------------------------+
- *  | 1 |  31:0 |  +--------------------------------------------------------+  |
+ *  | 1 |  31:0 |                                                              |
- *  +---+-------+  |                                                        |  |
+ *  +---+-------+                                                              |
- *  |...|       |  |  Embedded `HXG Message`_                               |  |
+ *  |...|       | [Embedded `HXG Message`_]                                    |
- *  +---+-------+  |                                                        |  |
+ *  +---+-------+                                                              |
- *  | n |  31:0 |  +--------------------------------------------------------+  |
+ *  | n |  31:0 |                                                              |
  *  +---+-------+--------------------------------------------------------------+
  */
 

drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h

@@ -38,11 +38,11 @@
  *  +---+-------+--------------------------------------------------------------+
  *  |   | Bits  | Description                                                  |
  *  +===+=======+==============================================================+
- *  | 0 |  31:0 |  +--------------------------------------------------------+  |
+ *  | 0 |  31:0 |                                                              |
- *  +---+-------+  |                                                        |  |
+ *  +---+-------+                                                              |
- *  |...|       |  |  Embedded `HXG Message`_                               |  |
+ *  |...|       | [Embedded `HXG Message`_]                                    |
- *  +---+-------+  |                                                        |  |
+ *  +---+-------+                                                              |
- *  | n |  31:0 |  +--------------------------------------------------------+  |
+ *  | n |  31:0 |                                                              |
  *  +---+-------+--------------------------------------------------------------+
  */
 

drivers/gpu/drm/i915/gvt/scheduler.c

@@ -576,7 +576,7 @@ retry:
 
 			/* No one is going to touch shadow bb from now on. */
 			i915_gem_object_flush_map(bb->obj);
-			i915_gem_object_unlock(bb->obj);
+			i915_gem_ww_ctx_fini(&ww);
 		}
 	}
 	return 0;
@@ -630,7 +630,7 @@ retry:
 		return ret;
 	}
 
-	i915_gem_object_unlock(wa_ctx->indirect_ctx.obj);
+	i915_gem_ww_ctx_fini(&ww);
 
 	/* FIXME: we are not tracking our pinned VMA leaving it
 	 * up to the core to fix up the stray pin_count upon

drivers/gpu/drm/i915/i915_request.c

@@ -829,8 +829,6 @@ static void __i915_request_ctor(void *arg)
 	i915_sw_fence_init(&rq->submit, submit_notify);
 	i915_sw_fence_init(&rq->semaphore, semaphore_notify);
 
-	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0);
-
 	rq->capture_list = NULL;
 
 	init_llist_head(&rq->execute_cb);
@@ -905,17 +903,12 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->ring = ce->ring;
 	rq->execution_mask = ce->engine->mask;
 
-	kref_init(&rq->fence.refcount);
-	rq->fence.flags = 0;
-	rq->fence.error = 0;
-	INIT_LIST_HEAD(&rq->fence.cb_list);
-
 	ret = intel_timeline_get_seqno(tl, rq, &seqno);
 	if (ret)
 		goto err_free;
 
-	rq->fence.context = tl->fence_context;
+	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock,
-	rq->fence.seqno = seqno;
+		       tl->fence_context, seqno);
 
 	RCU_INIT_POINTER(rq->timeline, tl);
 	rq->hwsp_seqno = tl->hwsp_seqno;

drivers/gpu/drm/tegra/dc.c

@@ -1845,7 +1845,6 @@ tegra_crtc_update_memory_bandwidth(struct drm_crtc *crtc,
 				   bool prepare_bandwidth_transition)
 {
 	const struct tegra_plane_state *old_tegra_state, *new_tegra_state;
-	const struct tegra_dc_state *old_dc_state, *new_dc_state;
 	u32 i, new_avg_bw, old_avg_bw, new_peak_bw, old_peak_bw;
 	const struct drm_plane_state *old_plane_state;
 	const struct drm_crtc_state *old_crtc_state;
@@ -1858,8 +1857,6 @@ tegra_crtc_update_memory_bandwidth(struct drm_crtc *crtc,
 		return;
 
 	old_crtc_state = drm_atomic_get_old_crtc_state(state, crtc);
-	old_dc_state = to_const_dc_state(old_crtc_state);
-	new_dc_state = to_const_dc_state(crtc->state);
 
 	if (!crtc->state->active) {
 		if (!old_crtc_state->active)

drivers/gpu/drm/tegra/dc.h

@@ -35,12 +35,6 @@ static inline struct tegra_dc_state *to_dc_state(struct drm_crtc_state *state)
 	return NULL;
 }
 
-static inline const struct tegra_dc_state *
-to_const_dc_state(const struct drm_crtc_state *state)
-{
-	return to_dc_state((struct drm_crtc_state *)state);
-}
-
 struct tegra_dc_stats {
 	unsigned long frames;
 	unsigned long vblank;

drivers/gpu/drm/tegra/uapi.c

@@ -222,7 +222,7 @@ int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_f
 		mapping->iova = sg_dma_address(mapping->sgt->sgl);
 	}
 
-	mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->size;
+	mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->gem.size;
 
 	err = xa_alloc(&context->mappings, &args->mapping, mapping, XA_LIMIT(1, U32_MAX),
 		       GFP_KERNEL);

drivers/gpu/host1x/fence.c

@@ -15,7 +15,7 @@
 #include "intr.h"
 #include "syncpt.h"
 
-DEFINE_SPINLOCK(lock);
+static DEFINE_SPINLOCK(lock);
 
 struct host1x_syncpt_fence {
 	struct dma_fence base;
@@ -152,8 +152,10 @@ struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold)
 		return ERR_PTR(-ENOMEM);
 
 	fence->waiter = kzalloc(sizeof(*fence->waiter), GFP_KERNEL);
-	if (!fence->waiter)
+	if (!fence->waiter) {
+		kfree(fence);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	fence->sp = sp;
 	fence->threshold = threshold;

drivers/hwmon/k10temp.c

@@ -362,12 +362,6 @@ static const struct hwmon_channel_info *k10temp_info[] = {
 			   HWMON_T_INPUT | HWMON_T_LABEL,
 			   HWMON_T_INPUT | HWMON_T_LABEL,
 			   HWMON_T_INPUT | HWMON_T_LABEL),
-	HWMON_CHANNEL_INFO(in,
-			   HWMON_I_INPUT | HWMON_I_LABEL,
-			   HWMON_I_INPUT | HWMON_I_LABEL),
-	HWMON_CHANNEL_INFO(curr,
-			   HWMON_C_INPUT | HWMON_C_LABEL,
-			   HWMON_C_INPUT | HWMON_C_LABEL),
 	NULL
 };
 

drivers/hwmon/ltc2947-core.c

@@ -989,8 +989,12 @@ static int ltc2947_setup(struct ltc2947_data *st)
 		return ret;
 
 	/* check external clock presence */
-	extclk = devm_clk_get(st->dev, NULL);
+	extclk = devm_clk_get_optional(st->dev, NULL);
-	if (!IS_ERR(extclk)) {
+	if (IS_ERR(extclk))
+		return dev_err_probe(st->dev, PTR_ERR(extclk),
+				     "Failed to get external clock\n");
+
+	if (extclk) {
 		unsigned long rate_hz;
 		u8 pre = 0, div, tbctl;
 		u64 aux;

drivers/hwmon/mlxreg-fan.c

@@ -315,8 +315,8 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev,
 {
 	struct mlxreg_fan *fan = cdev->devdata;
 	unsigned long cur_state;
+	int i, config = 0;
 	u32 regval;
-	int i;
 	int err;
 
 	/*
@@ -329,6 +329,12 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev,
 	 * overwritten.
 	 */
 	if (state >= MLXREG_FAN_SPEED_MIN && state <= MLXREG_FAN_SPEED_MAX) {
+		/*
+		 * This is configuration change, which is only supported through sysfs.
+		 * For configuration non-zero value is to be returned to avoid thermal
+		 * statistics update.
+		 */
+		config = 1;
 		state -= MLXREG_FAN_MAX_STATE;
 		for (i = 0; i < state; i++)
 			fan->cooling_levels[i] = state;
@@ -343,7 +349,7 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev,
 
 		cur_state = MLXREG_FAN_PWM_DUTY2STATE(regval);
 		if (state < cur_state)
-			return 0;
+			return config;
 
 		state = cur_state;
 	}
@@ -359,7 +365,7 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev,
 		dev_err(fan->dev, "Failed to write PWM duty\n");
 		return err;
 	}
-	return 0;
+	return config;
 }
 
 static const struct thermal_cooling_device_ops mlxreg_fan_cooling_ops = {

drivers/hwmon/occ/common.c

@@ -340,18 +340,11 @@ static ssize_t occ_show_temp_10(struct device *dev,
 		if (val == OCC_TEMP_SENSOR_FAULT)
 			return -EREMOTEIO;
 
-		/*
+		/* sensor not ready */
-		 * VRM doesn't return temperature, only alarm bit. This
+		if (val == 0)
-		 * attribute maps to tempX_alarm instead of tempX_input for
+			return -EAGAIN;
-		 * VRM
-		 */
-		if (temp->fru_type != OCC_FRU_TYPE_VRM) {
-			/* sensor not ready */
-			if (val == 0)
-				return -EAGAIN;
 
-			val *= 1000;
+		val *= 1000;
-		}
 		break;
 	case 2:
 		val = temp->fru_type;
@@ -886,7 +879,7 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 					     0, i);
 		attr++;
 
-		if (sensors->temp.version > 1 &&
+		if (sensors->temp.version == 2 &&
 		    temp->fru_type == OCC_FRU_TYPE_VRM) {
 			snprintf(attr->name, sizeof(attr->name),
 				 "temp%d_alarm", s);

drivers/hwmon/pmbus/ibm-cffps.c

@@ -171,8 +171,14 @@ static ssize_t ibm_cffps_debugfs_read(struct file *file, char __user *buf,
 		cmd = CFFPS_SN_CMD;
 		break;
 	case CFFPS_DEBUGFS_MAX_POWER_OUT:
-		rc = i2c_smbus_read_word_swapped(psu->client,
+		if (psu->version == cffps1) {
-						 CFFPS_MAX_POWER_OUT_CMD);
+			rc = i2c_smbus_read_word_swapped(psu->client,
+					CFFPS_MAX_POWER_OUT_CMD);
+		} else {
+			rc = i2c_smbus_read_word_data(psu->client,
+					CFFPS_MAX_POWER_OUT_CMD);
+		}
+
 		if (rc < 0)
 			return rc;
 

drivers/hwmon/pmbus/mp2975.c

@@ -54,7 +54,7 @@
 
 #define MP2975_RAIL2_FUNC	(PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT | \
 				 PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT | \
-				 PMBUS_PHASE_VIRTUAL)
+				 PMBUS_HAVE_POUT | PMBUS_PHASE_VIRTUAL)
 
 struct mp2975_data {
 	struct pmbus_driver_info info;