Merge tag 'v5.3.6' into toradex_5.3.y

This is the 5.3.6 stable release

23 files changed, 185 insertions, 133 deletions

diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2.dts b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2.dts
index 4e916e1f71f7..1c2a9ca491c0 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2.dts
@@ -66,8 +66,8 @@
 		gpios = <&gpio_ao GPIOAO_9 GPIO_ACTIVE_HIGH>;
 		gpios-states = <0>;
 
-		states = <3300000 0
-			  1800000 1>;
+		states = <3300000 0>,
+			 <1800000 1>;
 	};
 
 	flash_1v8: regulator-flash_1v8 {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
index b636912a2715..afcf8a9f667b 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
@@ -75,8 +75,8 @@
 		gpios-states = <1>;
 
 		/* Based on P200 schematics, signal CARD_1.8V/3.3V_CTR */
-		states = <1800000 0
-			  3300000 1>;
+		states = <1800000 0>,
+			 <3300000 1>;
 	};
 
 	vddio_boot: regulator-vddio_boot {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
index 9972b1515da6..6039adda12ee 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
@@ -77,8 +77,8 @@
 		gpios = <&gpio_ao GPIOAO_3 GPIO_ACTIVE_HIGH>;
 		gpios-states = <0>;
 
-		states = <3300000 0
-			  1800000 1>;
+		states = <3300000 0>,
+			 <1800000 1>;
 	};
 
 	vcc1v8: regulator-vcc1v8 {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
index e8f925871edf..89f7b41b0e9e 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
@@ -46,8 +46,8 @@
 		gpios-states = <1>;
 
 		/* Based on P200 schematics, signal CARD_1.8V/3.3V_CTR */
-		states = <1800000 0
-			  3300000 1>;
+		states = <1800000 0>,
+			 <3300000 1>;
 
 		regulator-settling-time-up-us = <10000>;
 		regulator-settling-time-down-us = <150000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts
index 796baea7a0bf..c8d74e61dec1 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts
@@ -38,8 +38,8 @@
 		gpios-states = <1>;
 
 		/* Based on P200 schematics, signal CARD_1.8V/3.3V_CTR */
-		states = <1800000 0
-			  3300000 1>;
+		states = <1800000 0>,
+			 <3300000 1>;
 	};
 
 	vddio_boot: regulator-vddio_boot {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
index 26907ac82930..c433a031841f 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
@@ -38,8 +38,8 @@
 		gpios-states = <1>;
 
 		/* Based on P200 schematics, signal CARD_1.8V/3.3V_CTR */
-		states = <1800000 0
-			  3300000 1>;
+		states = <1800000 0>,
+			 <3300000 1>;
 	};
 
 	vddio_boot: regulator-vddio_boot {
diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
index 52aae341d0da..d1f4eb197af2 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
@@ -169,15 +169,14 @@
 		opp-1300000000 {
 			opp-hz = /bits/ 64 <1300000000>;
 			opp-microvolt = <1000000>;
-			opp-supported-hw = <0xc>, <0x7>;
+			opp-supported-hw = <0xc>, <0x4>;
 			clock-latency-ns = <150000>;
 		};
 
 		opp-1500000000 {
 			opp-hz = /bits/ 64 <1500000000>;
 			opp-microvolt = <1000000>;
-			/* Consumer only but rely on speed grading */
-			opp-supported-hw = <0x8>, <0x7>;
+			opp-supported-hw = <0x8>, <0x3>;
 			clock-latency-ns = <150000>;
 		};
 	};
diff --git a/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi b/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi
index 11c0a7137823..db6df76e97a1 100644
--- a/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi
+++ b/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi
@@ -61,7 +61,9 @@
 	protected-clocks = <GCC_BIMC_CDSP_CLK>,
 			   <GCC_CDSP_CFG_AHB_CLK>,
 			   <GCC_CDSP_BIMC_CLK_SRC>,
-			   <GCC_CDSP_TBU_CLK>;
+			   <GCC_CDSP_TBU_CLK>,
+			   <141>, /* GCC_WCSS_Q6_AHB_CLK */
+			   <142>; /* GCC_WCSS_Q6_AXIM_CLK */
 };
 
 &pms405_spmi_regulators {
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index e9fefd8a7e02..f0f2c555033b 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -801,6 +801,7 @@
 			 <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>;
 		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
+		max-frequency = <150000000>;
 		status = "disabled";
 	};
 
@@ -812,6 +813,7 @@
 			 <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>;
 		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
+		max-frequency = <150000000>;
 		status = "disabled";
 	};
 
@@ -823,6 +825,7 @@
 			 <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>;
 		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
+		max-frequency = <150000000>;
 		status = "disabled";
 	};
 
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index c8c850bc3dfb..6dd011e0b434 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -26,7 +26,7 @@
  * (the optimize attribute silently ignores these options).
  */
 
-#define ATOMIC_OP(op, asm_op)						\
+#define ATOMIC_OP(op, asm_op, constraint)				\
 __LL_SC_INLINE void							\
 __LL_SC_PREFIX(arch_atomic_##op(int i, atomic_t *v))			\
 {									\
@@ -40,11 +40,11 @@ __LL_SC_PREFIX(arch_atomic_##op(int i, atomic_t *v))			\
 "	stxr	%w1, %w0, %2\n"						\
 "	cbnz	%w1, 1b"						\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i));							\
+	: #constraint "r" (i));						\
 }									\
 __LL_SC_EXPORT(arch_atomic_##op);
 
-#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op)		\
+#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\
 __LL_SC_INLINE int							\
 __LL_SC_PREFIX(arch_atomic_##op##_return##name(int i, atomic_t *v))	\
 {									\
@@ -59,14 +59,14 @@ __LL_SC_PREFIX(arch_atomic_##op##_return##name(int i, atomic_t *v))	\
 "	cbnz	%w1, 1b\n"						\
 "	" #mb								\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i)							\
+	: #constraint "r" (i)						\
 	: cl);								\
 									\
 	return result;							\
 }									\
 __LL_SC_EXPORT(arch_atomic_##op##_return##name);
 
-#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op)		\
+#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)	\
 __LL_SC_INLINE int							\
 __LL_SC_PREFIX(arch_atomic_fetch_##op##name(int i, atomic_t *v))	\
 {									\
@@ -81,7 +81,7 @@ __LL_SC_PREFIX(arch_atomic_fetch_##op##name(int i, atomic_t *v))	\
 "	cbnz	%w2, 1b\n"						\
 "	" #mb								\
 	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
-	: "Ir" (i)							\
+	: #constraint "r" (i)						\
 	: cl);								\
 									\
 	return result;							\
@@ -99,8 +99,8 @@ __LL_SC_EXPORT(arch_atomic_fetch_##op##name);
 	ATOMIC_FETCH_OP (_acquire,        , a,  , "memory", __VA_ARGS__)\
 	ATOMIC_FETCH_OP (_release,        ,  , l, "memory", __VA_ARGS__)
 
-ATOMIC_OPS(add, add)
-ATOMIC_OPS(sub, sub)
+ATOMIC_OPS(add, add, I)
+ATOMIC_OPS(sub, sub, J)
 
 #undef ATOMIC_OPS
 #define ATOMIC_OPS(...)							\
@@ -110,17 +110,17 @@ ATOMIC_OPS(sub, sub)
 	ATOMIC_FETCH_OP (_acquire,        , a,  , "memory", __VA_ARGS__)\
 	ATOMIC_FETCH_OP (_release,        ,  , l, "memory", __VA_ARGS__)
 
-ATOMIC_OPS(and, and)
-ATOMIC_OPS(andnot, bic)
-ATOMIC_OPS(or, orr)
-ATOMIC_OPS(xor, eor)
+ATOMIC_OPS(and, and, )
+ATOMIC_OPS(andnot, bic, )
+ATOMIC_OPS(or, orr, )
+ATOMIC_OPS(xor, eor, )
 
 #undef ATOMIC_OPS
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define ATOMIC64_OP(op, asm_op)						\
+#define ATOMIC64_OP(op, asm_op, constraint)				\
 __LL_SC_INLINE void							\
 __LL_SC_PREFIX(arch_atomic64_##op(s64 i, atomic64_t *v))		\
 {									\
@@ -134,11 +134,11 @@ __LL_SC_PREFIX(arch_atomic64_##op(s64 i, atomic64_t *v))		\
 "	stxr	%w1, %0, %2\n"						\
 "	cbnz	%w1, 1b"						\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i));							\
+	: #constraint "r" (i));						\
 }									\
 __LL_SC_EXPORT(arch_atomic64_##op);
 
-#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op)		\
+#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\
 __LL_SC_INLINE s64							\
 __LL_SC_PREFIX(arch_atomic64_##op##_return##name(s64 i, atomic64_t *v))\
 {									\
@@ -153,14 +153,14 @@ __LL_SC_PREFIX(arch_atomic64_##op##_return##name(s64 i, atomic64_t *v))\
 "	cbnz	%w1, 1b\n"						\
 "	" #mb								\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i)							\
+	: #constraint "r" (i)						\
 	: cl);								\
 									\
 	return result;							\
 }									\
 __LL_SC_EXPORT(arch_atomic64_##op##_return##name);
 
-#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op)		\
+#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)\
 __LL_SC_INLINE s64							\
 __LL_SC_PREFIX(arch_atomic64_fetch_##op##name(s64 i, atomic64_t *v))	\
 {									\
@@ -175,7 +175,7 @@ __LL_SC_PREFIX(arch_atomic64_fetch_##op##name(s64 i, atomic64_t *v))	\
 "	cbnz	%w2, 1b\n"						\
 "	" #mb								\
 	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
-	: "Ir" (i)							\
+	: #constraint "r" (i)						\
 	: cl);								\
 									\
 	return result;							\
@@ -193,8 +193,8 @@ __LL_SC_EXPORT(arch_atomic64_fetch_##op##name);
 	ATOMIC64_FETCH_OP (_acquire,, a,  , "memory", __VA_ARGS__)	\
 	ATOMIC64_FETCH_OP (_release,,  , l, "memory", __VA_ARGS__)
 
-ATOMIC64_OPS(add, add)
-ATOMIC64_OPS(sub, sub)
+ATOMIC64_OPS(add, add, I)
+ATOMIC64_OPS(sub, sub, J)
 
 #undef ATOMIC64_OPS
 #define ATOMIC64_OPS(...)						\
@@ -204,10 +204,10 @@ ATOMIC64_OPS(sub, sub)
 	ATOMIC64_FETCH_OP (_acquire,, a,  , "memory", __VA_ARGS__)	\
 	ATOMIC64_FETCH_OP (_release,,  , l, "memory", __VA_ARGS__)
 
-ATOMIC64_OPS(and, and)
-ATOMIC64_OPS(andnot, bic)
-ATOMIC64_OPS(or, orr)
-ATOMIC64_OPS(xor, eor)
+ATOMIC64_OPS(and, and, L)
+ATOMIC64_OPS(andnot, bic, )
+ATOMIC64_OPS(or, orr, L)
+ATOMIC64_OPS(xor, eor, L)
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_FETCH_OP
@@ -237,7 +237,7 @@ __LL_SC_PREFIX(arch_atomic64_dec_if_positive(atomic64_t *v))
 }
 __LL_SC_EXPORT(arch_atomic64_dec_if_positive);
 
-#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl)		\
+#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl, constraint)	\
 __LL_SC_INLINE u##sz							\
 __LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr,		\
 					 unsigned long old,		\
@@ -265,29 +265,34 @@ __LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr,		\
 	"2:"								\
 	: [tmp] "=&r" (tmp), [oldval] "=&r" (oldval),			\
 	  [v] "+Q" (*(u##sz *)ptr)					\
-	: [old] "Kr" (old), [new] "r" (new)				\
+	: [old] #constraint "r" (old), [new] "r" (new)			\
 	: cl);								\
 									\
 	return oldval;							\
 }									\
 __LL_SC_EXPORT(__cmpxchg_case_##name##sz);
 
-__CMPXCHG_CASE(w, b,     ,  8,        ,  ,  ,         )
-__CMPXCHG_CASE(w, h,     , 16,        ,  ,  ,         )
-__CMPXCHG_CASE(w,  ,     , 32,        ,  ,  ,         )
-__CMPXCHG_CASE( ,  ,     , 64,        ,  ,  ,         )
-__CMPXCHG_CASE(w, b, acq_,  8,        , a,  , "memory")
-__CMPXCHG_CASE(w, h, acq_, 16,        , a,  , "memory")
-__CMPXCHG_CASE(w,  , acq_, 32,        , a,  , "memory")
-__CMPXCHG_CASE( ,  , acq_, 64,        , a,  , "memory")
-__CMPXCHG_CASE(w, b, rel_,  8,        ,  , l, "memory")
-__CMPXCHG_CASE(w, h, rel_, 16,        ,  , l, "memory")
-__CMPXCHG_CASE(w,  , rel_, 32,        ,  , l, "memory")
-__CMPXCHG_CASE( ,  , rel_, 64,        ,  , l, "memory")
-__CMPXCHG_CASE(w, b,  mb_,  8, dmb ish,  , l, "memory")
-__CMPXCHG_CASE(w, h,  mb_, 16, dmb ish,  , l, "memory")
-__CMPXCHG_CASE(w,  ,  mb_, 32, dmb ish,  , l, "memory")
-__CMPXCHG_CASE( ,  ,  mb_, 64, dmb ish,  , l, "memory")
+/*
+ * Earlier versions of GCC (no later than 8.1.0) appear to incorrectly
+ * handle the 'K' constraint for the value 4294967295 - thus we use no
+ * constraint for 32 bit operations.
+ */
+__CMPXCHG_CASE(w, b,     ,  8,        ,  ,  ,         , )
+__CMPXCHG_CASE(w, h,     , 16,        ,  ,  ,         , )
+__CMPXCHG_CASE(w,  ,     , 32,        ,  ,  ,         , )
+__CMPXCHG_CASE( ,  ,     , 64,        ,  ,  ,         , L)
+__CMPXCHG_CASE(w, b, acq_,  8,        , a,  , "memory", )
+__CMPXCHG_CASE(w, h, acq_, 16,        , a,  , "memory", )
+__CMPXCHG_CASE(w,  , acq_, 32,        , a,  , "memory", )
+__CMPXCHG_CASE( ,  , acq_, 64,        , a,  , "memory", L)
+__CMPXCHG_CASE(w, b, rel_,  8,        ,  , l, "memory", )
+__CMPXCHG_CASE(w, h, rel_, 16,        ,  , l, "memory", )
+__CMPXCHG_CASE(w,  , rel_, 32,        ,  , l, "memory", )
+__CMPXCHG_CASE( ,  , rel_, 64,        ,  , l, "memory", L)
+__CMPXCHG_CASE(w, b,  mb_,  8, dmb ish,  , l, "memory", )
+__CMPXCHG_CASE(w, h,  mb_, 16, dmb ish,  , l, "memory", )
+__CMPXCHG_CASE(w,  ,  mb_, 32, dmb ish,  , l, "memory", )
+__CMPXCHG_CASE( ,  ,  mb_, 64, dmb ish,  , l, "memory", L)
 
 #undef __CMPXCHG_CASE
 
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 7a299a20f6dc..7a8b8bc69e8d 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -63,7 +63,7 @@ __XCHG_CASE( ,  ,  mb_, 64, dmb ish, nop,  , a, l, "memory")
 #undef __XCHG_CASE
 
 #define __XCHG_GEN(sfx)							\
-static inline unsigned long __xchg##sfx(unsigned long x,		\
+static __always_inline  unsigned long __xchg##sfx(unsigned long x,	\
 					volatile void *ptr,		\
 					int size)			\
 {									\
@@ -105,7 +105,7 @@ __XCHG_GEN(_mb)
 #define arch_xchg(...)		__xchg_wrapper( _mb, __VA_ARGS__)
 
 #define __CMPXCHG_GEN(sfx)						\
-static inline unsigned long __cmpxchg##sfx(volatile void *ptr,		\
+static __always_inline unsigned long __cmpxchg##sfx(volatile void *ptr,	\
 					   unsigned long old,		\
 					   unsigned long new,		\
 					   int size)			\
@@ -212,7 +212,7 @@ __CMPWAIT_CASE( ,  , 64);
 #undef __CMPWAIT_CASE
 
 #define __CMPWAIT_GEN(sfx)						\
-static inline void __cmpwait##sfx(volatile void *ptr,			\
+static __always_inline void __cmpwait##sfx(volatile void *ptr,		\
 				  unsigned long val,			\
 				  int size)				\
 {									\
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index e7d46631cc42..b1454d117cd2 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -51,14 +51,6 @@
 #define MIDR_CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \
 			     MIDR_ARCHITECTURE_MASK)
 
-#define MIDR_IS_CPU_MODEL_RANGE(midr, model, rv_min, rv_max)		\
-({									\
-	u32 _model = (midr) & MIDR_CPU_MODEL_MASK;			\
-	u32 rv = (midr) & (MIDR_REVISION_MASK | MIDR_VARIANT_MASK);	\
-									\
-	_model == (model) && rv >= (rv_min) && rv <= (rv_max);		\
- })
-
 #define ARM_CPU_IMP_ARM			0x41
 #define ARM_CPU_IMP_APM			0x50
 #define ARM_CPU_IMP_CAVIUM		0x43
@@ -159,10 +151,19 @@ struct midr_range {
 #define MIDR_REV(m, v, r) MIDR_RANGE(m, v, r, v, r)
 #define MIDR_ALL_VERSIONS(m) MIDR_RANGE(m, 0, 0, 0xf, 0xf)
 
+static inline bool midr_is_cpu_model_range(u32 midr, u32 model, u32 rv_min,
+					   u32 rv_max)
+{
+	u32 _model = midr & MIDR_CPU_MODEL_MASK;
+	u32 rv = midr & (MIDR_REVISION_MASK | MIDR_VARIANT_MASK);
+
+	return _model == model && rv >= rv_min && rv <= rv_max;
+}
+
 static inline bool is_midr_in_range(u32 midr, struct midr_range const *range)
 {
-	return MIDR_IS_CPU_MODEL_RANGE(midr, range->model,
-				 range->rv_min, range->rv_max);
+	return midr_is_cpu_model_range(midr, range->model,
+				       range->rv_min, range->rv_max);
 }
 
 static inline bool
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index ed57b760f38c..a17393ff6677 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -30,4 +30,6 @@ static inline u32 disr_to_esr(u64 disr)
 	return esr;
 }
 
+asmlinkage void enter_from_user_mode(void);
+
 #endif	/* __ASM_EXCEPTION_H */
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 8af7a85f76bd..bc3949064725 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -251,6 +251,7 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
 	dsb(ishst);
 	__tlbi(vaae1is, addr);
 	dsb(ish);
+	isb();
 }
 #endif
 
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index b1fdc486aed8..9323bcc40a58 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -894,7 +894,7 @@ static bool has_no_hw_prefetch(const struct arm64_cpu_capabilities *entry, int _
 	u32 midr = read_cpuid_id();
 
 	/* Cavium ThunderX pass 1.x and 2.x */
-	return MIDR_IS_CPU_MODEL_RANGE(midr, MIDR_THUNDERX,
+	return midr_is_cpu_model_range(midr, MIDR_THUNDERX,
 		MIDR_CPU_VAR_REV(0, 0),
 		MIDR_CPU_VAR_REV(1, MIDR_REVISION_MASK));
 }
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 320a30dbe35e..84a822748c84 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -30,9 +30,9 @@
  * Context tracking subsystem.  Used to instrument transitions
  * between user and kernel mode.
  */
-	.macro ct_user_exit
+	.macro ct_user_exit_irqoff
 #ifdef CONFIG_CONTEXT_TRACKING
-	bl	context_tracking_user_exit
+	bl	enter_from_user_mode
 #endif
 	.endm
 
@@ -792,8 +792,8 @@ el0_cp15:
 	/*
 	 * Trapped CP15 (MRC, MCR, MRRC, MCRR) instructions
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_cp15instr
@@ -805,8 +805,8 @@ el0_da:
 	 * Data abort handling
 	 */
 	mrs	x26, far_el1
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	clear_address_tag x0, x26
 	mov	x1, x25
 	mov	x2, sp
@@ -818,11 +818,11 @@ el0_ia:
 	 */
 	mrs	x26, far_el1
 	gic_prio_kentry_setup tmp=x0
+	ct_user_exit_irqoff
 	enable_da_f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
-	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
@@ -832,8 +832,8 @@ el0_fpsimd_acc:
 	/*
 	 * Floating Point or Advanced SIMD access
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_fpsimd_acc
@@ -842,8 +842,8 @@ el0_sve_acc:
 	/*
 	 * Scalable Vector Extension access
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_sve_acc
@@ -852,8 +852,8 @@ el0_fpsimd_exc:
 	/*
 	 * Floating Point, Advanced SIMD or SVE exception
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_fpsimd_exc
@@ -868,11 +868,11 @@ el0_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	gic_prio_kentry_setup tmp=x0
+	ct_user_exit_irqoff
 	enable_da_f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
-	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
@@ -882,8 +882,8 @@ el0_undef:
 	/*
 	 * Undefined instruction
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, sp
 	bl	do_undefinstr
 	b	ret_to_user
@@ -891,8 +891,8 @@ el0_sys:
 	/*
 	 * System instructions, for trapped cache maintenance instructions
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_sysinstr
@@ -902,17 +902,18 @@ el0_dbg:
 	 * Debug exception handling
 	 */
 	tbnz	x24, #0, el0_inv		// EL0 only
+	mrs	x24, far_el1
 	gic_prio_kentry_setup tmp=x3
-	mrs	x0, far_el1
+	ct_user_exit_irqoff
+	mov	x0, x24
 	mov	x1, x25
 	mov	x2, sp
 	bl	do_debug_exception
 	enable_da_f
-	ct_user_exit
 	b	ret_to_user
 el0_inv:
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mov	x2, x25
@@ -925,13 +926,13 @@ el0_irq:
 	kernel_entry 0
 el0_irq_naked:
 	gic_prio_irq_setup pmr=x20, tmp=x0
+	ct_user_exit_irqoff
 	enable_da_f
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
 
-	ct_user_exit
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 	tbz	x22, #55, 1f
 	bl	do_el0_irq_bp_hardening
@@ -958,13 +959,14 @@ ENDPROC(el1_error)
 el0_error:
 	kernel_entry 0
 el0_error_naked:
-	mrs	x1, esr_el1
+	mrs	x25, esr_el1
 	gic_prio_kentry_setup tmp=x2
+	ct_user_exit_irqoff
 	enable_dbg
 	mov	x0, sp
+	mov	x1, x25
 	bl	do_serror
 	enable_da_f
-	ct_user_exit
 	b	ret_to_user
 ENDPROC(el0_error)
 
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
new file mode 100644
index 000000000000..25a2a9b479c2
--- /dev/null
+++ b/arch/arm64/kernel/image-vars.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Linker script variables to be set after section resolution, as
+ * ld.lld does not like variables assigned before SECTIONS is processed.
+ */
+#ifndef __ARM64_KERNEL_IMAGE_VARS_H
+#define __ARM64_KERNEL_IMAGE_VARS_H
+
+#ifndef LINKER_SCRIPT
+#error This file should only be included in vmlinux.lds.S
+#endif
+
+#ifdef CONFIG_EFI
+
+__efistub_stext_offset = stext - _text;
+
+/*
+ * The EFI stub has its own symbol namespace prefixed by __efistub_, to
+ * isolate it from the kernel proper. The following symbols are legally
+ * accessed by the stub, so provide some aliases to make them accessible.
+ * Only include data symbols here, or text symbols of functions that are
+ * guaranteed to be safe when executed at another offset than they were
+ * linked at. The routines below are all implemented in assembler in a
+ * position independent manner
+ */
+__efistub_memcmp		= __pi_memcmp;
+__efistub_memchr		= __pi_memchr;
+__efistub_memcpy		= __pi_memcpy;
+__efistub_memmove		= __pi_memmove;
+__efistub_memset		= __pi_memset;
+__efistub_strlen		= __pi_strlen;
+__efistub_strnlen		= __pi_strnlen;
+__efistub_strcmp		= __pi_strcmp;
+__efistub_strncmp		= __pi_strncmp;
+__efistub_strrchr		= __pi_strrchr;
+__efistub___flush_dcache_area	= __pi___flush_dcache_area;
+
+#ifdef CONFIG_KASAN
+__efistub___memcpy		= __pi_memcpy;
+__efistub___memmove		= __pi_memmove;
+__efistub___memset		= __pi_memset;
+#endif
+
+__efistub__text			= _text;
+__efistub__end			= _end;
+__efistub__edata		= _edata;
+__efistub_screen_info		= screen_info;
+
+#endif
+
+#endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h
index 2b85c0d6fa3d..c7d38c660372 100644
--- a/arch/arm64/kernel/image.h
+++ b/arch/arm64/kernel/image.h
@@ -65,46 +65,4 @@
 	DEFINE_IMAGE_LE64(_kernel_offset_le, TEXT_OFFSET);	\
 	DEFINE_IMAGE_LE64(_kernel_flags_le, __HEAD_FLAGS);
 
-#ifdef CONFIG_EFI
-
-/*
- * Use ABSOLUTE() to avoid ld.lld treating this as a relative symbol:
- * https://github.com/ClangBuiltLinux/linux/issues/561
- */
-__efistub_stext_offset = ABSOLUTE(stext - _text);
-
-/*
- * The EFI stub has its own symbol namespace prefixed by __efistub_, to
- * isolate it from the kernel proper. The following symbols are legally
- * accessed by the stub, so provide some aliases to make them accessible.
- * Only include data symbols here, or text symbols of functions that are
- * guaranteed to be safe when executed at another offset than they were
- * linked at. The routines below are all implemented in assembler in a
- * position independent manner
- */
-__efistub_memcmp		= __pi_memcmp;
-__efistub_memchr		= __pi_memchr;
-__efistub_memcpy		= __pi_memcpy;
-__efistub_memmove		= __pi_memmove;
-__efistub_memset		= __pi_memset;
-__efistub_strlen		= __pi_strlen;
-__efistub_strnlen		= __pi_strnlen;
-__efistub_strcmp		= __pi_strcmp;
-__efistub_strncmp		= __pi_strncmp;
-__efistub_strrchr		= __pi_strrchr;
-__efistub___flush_dcache_area	= __pi___flush_dcache_area;
-
-#ifdef CONFIG_KASAN
-__efistub___memcpy		= __pi_memcpy;
-__efistub___memmove		= __pi_memmove;
-__efistub___memset		= __pi_memset;
-#endif
-
-__efistub__text			= _text;
-__efistub__end			= _end;
-__efistub__edata		= _edata;
-__efistub_screen_info		= screen_info;
-
-#endif
-
 #endif /* __ARM64_KERNEL_IMAGE_H */
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 32893b3d9164..742a636861e7 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -7,9 +7,11 @@
  */
 
 #include <linux/bug.h>
+#include <linux/context_tracking.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
 #include <linux/kallsyms.h>
+#include <linux/kprobes.h>
 #include <linux/spinlock.h>
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
@@ -900,6 +902,13 @@ asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
 		nmi_exit();
 }
 
+asmlinkage void enter_from_user_mode(void)
+{
+	CT_WARN_ON(ct_state() != CONTEXT_USER);
+	user_exit_irqoff();
+}
+NOKPROBE_SYMBOL(enter_from_user_mode);
+
 void __pte_error(const char *file, int line, unsigned long val)
 {
 	pr_err("%s:%d: bad pte %016lx.\n", file, line, val);
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 7fa008374907..803b24d2464a 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -245,6 +245,8 @@ SECTIONS
 	HEAD_SYMBOLS
 }
 
+#include "image-vars.h"
+
 /*
  * The HYP init code and ID map text can't be longer than a page each,
  * and should not cross a page boundary.
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f3c795278def..b1ee6cb4b17f 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -570,8 +570,12 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
+	unsigned long aligned_start, aligned_end;
+
+	aligned_start = __virt_to_phys(start) & PAGE_MASK;
+	aligned_end = PAGE_ALIGN(__virt_to_phys(end));
+	memblock_free(aligned_start, aligned_end - aligned_start);
 	free_reserved_area((void *)start, (void *)end, 0, "initrd");
-	memblock_free(__virt_to_phys(start), end - start);
 }
 #endif
 
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index b050641b5139..8dac7110f0cb 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -54,7 +54,11 @@ unsigned long arch_mmap_rnd(void)
 static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
 {
 	unsigned long gap = rlim_stack->rlim_cur;
-	unsigned long pad = (STACK_RND_MASK << PAGE_SHIFT) + stack_guard_gap;
+	unsigned long pad = stack_guard_gap;
+
+	/* Account for stack randomization if necessary */
+	if (current->flags & PF_RANDOMIZE)
+		pad += (STACK_RND_MASK << PAGE_SHIFT);
 
 	/* Values close to RLIM_INFINITY can overflow. */
 	if (gap + pad > gap)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 7dbf2be470f6..28a8f7b87ff0 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -286,6 +286,15 @@ skip_pgd:
 	msr	sctlr_el1, x18
 	isb
 
+	/*
+	 * Invalidate the local I-cache so that any instructions fetched
+	 * speculatively from the PoC are discarded, since they may have
+	 * been dynamically patched at the PoU.
+	 */
+	ic	iallu
+	dsb	nsh
+	isb
+
 	/* Set the flag to zero to indicate that we're all done */
 	str	wzr, [flag_ptr]
 	ret