Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 and cross-arch updates from Catalin Marinas:
 "Here's a slightly wider-spread set of updates for 5.9.

  Going outside the usual arch/arm64/ area is the removal of
  read_barrier_depends() series from Will and the MSI/IOMMU ID
  translation series from Lorenzo.

  The notable arm64 updates include ARMv8.4 TLBI range operations and
  translation level hint, time namespace support, and perf.

  Summary:

   - Removal of the tremendously unpopular read_barrier_depends()
     barrier, which is a NOP on all architectures apart from Alpha, in
     favour of allowing architectures to override READ_ONCE() and do
     whatever dance they need to do to ensure address dependencies
     provide LOAD -> LOAD/STORE ordering.

     This work also offers a potential solution if compilers are shown
     to convert LOAD -> LOAD address dependencies into control
     dependencies (e.g. under LTO), as weakly ordered architectures will
     effectively be able to upgrade READ_ONCE() to smp_load_acquire().
     The latter case is not used yet, but will be discussed further at
     LPC.

   - Make the MSI/IOMMU input/output ID translation PCI agnostic,
     augment the MSI/IOMMU ACPI/OF ID mapping APIs to accept an input ID
     bus-specific parameter and apply the resulting changes to the
     device ID space provided by the Freescale FSL bus.

   - arm64 support for TLBI range operations and translation table level
     hints (part of the ARMv8.4 architecture version).

   - Time namespace support for arm64.

   - Export the virtual and physical address sizes in vmcoreinfo for
     makedumpfile and crash utilities.

   - CPU feature handling cleanups and checks for programmer errors
     (overlapping bit-fields).

   - ACPI updates for arm64: disallow AML accesses to EFI code regions
     and kernel memory.

   - perf updates for arm64.

   - Miscellaneous fixes and cleanups, most notably PLT counting
     optimisation for module loading, recordmcount fix to ignore
     relocations other than R_AARCH64_CALL26, CMA areas reserved for
     gigantic pages on 16K and 64K configurations.

   - Trivial typos, duplicate words"

Link: http://lkml.kernel.org/r/20200710165203.31284-1-will@kernel.org
Link: http://lkml.kernel.org/r/20200619082013.13661-1-lorenzo.pieralisi@arm.com

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (82 commits)
  arm64: use IRQ_STACK_SIZE instead of THREAD_SIZE for irq stack
  arm64/mm: save memory access in check_and_switch_context() fast switch path
  arm64: sigcontext.h: delete duplicated word
  arm64: ptrace.h: delete duplicated word
  arm64: pgtable-hwdef.h: delete duplicated words
  bus: fsl-mc: Add ACPI support for fsl-mc
  bus/fsl-mc: Refactor the MSI domain creation in the DPRC driver
  of/irq: Make of_msi_map_rid() PCI bus agnostic
  of/irq: make of_msi_map_get_device_domain() bus agnostic
  dt-bindings: arm: fsl: Add msi-map device-tree binding for fsl-mc bus
  of/device: Add input id to of_dma_configure()
  of/iommu: Make of_map_rid() PCI agnostic
  ACPI/IORT: Add an input ID to acpi_dma_configure()
  ACPI/IORT: Remove useless PCI bus walk
  ACPI/IORT: Make iort_msi_map_rid() PCI agnostic
  ACPI/IORT: Make iort_get_device_domain IRQ domain agnostic
  ACPI/IORT: Make iort_match_node_callback walk the ACPI namespace for NC
  arm64: enable time namespace support
  arm64/vdso: Restrict splitting VVAR VMA
  arm64/vdso: Handle faults on timens page
  ...

50 files changed, 1016 insertions, 324 deletions

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 2144530d1428..2f8f7e54792f 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -16,10 +16,10 @@
 
 /*
  * To ensure dependency ordering is preserved for the _relaxed and
- * _release atomics, an smp_read_barrier_depends() is unconditionally
- * inserted into the _relaxed variants, which are used to build the
- * barriered versions. Avoid redundant back-to-back fences in the
- * _acquire and _fence versions.
+ * _release atomics, an smp_mb() is unconditionally inserted into the
+ * _relaxed variants, which are used to build the barriered versions.
+ * Avoid redundant back-to-back fences in the _acquire and _fence
+ * versions.
  */
 #define __atomic_acquire_fence()
 #define __atomic_post_full_fence()
@@ -70,7 +70,7 @@ static inline int atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
@@ -88,7 +88,7 @@ static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
@@ -123,7 +123,7 @@ static __inline__ s64 atomic64_##op##_return_relaxed(s64 i, atomic64_t * v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
@@ -141,7 +141,7 @@ static __inline__ s64 atomic64_fetch_##op##_relaxed(s64 i, atomic64_t * v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
diff --git a/arch/alpha/include/asm/barrier.h b/arch/alpha/include/asm/barrier.h
index 92ec486a4f9e..c56bfffc9918 100644
--- a/arch/alpha/include/asm/barrier.h
+++ b/arch/alpha/include/asm/barrier.h
@@ -2,64 +2,15 @@
 #ifndef __BARRIER_H
 #define __BARRIER_H
 
-#include <asm/compiler.h>
-
 #define mb()	__asm__ __volatile__("mb": : :"memory")
 #define rmb()	__asm__ __volatile__("mb": : :"memory")
 #define wmb()	__asm__ __volatile__("wmb": : :"memory")
 
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- */
-#define read_barrier_depends() __asm__ __volatile__("mb": : :"memory")
+#define __smp_load_acquire(p)						\
+({									\
+	compiletime_assert_atomic_type(*p);				\
+	__READ_ONCE(*p);						\
+})
 
 #ifdef CONFIG_SMP
 #define __ASM_SMP_MB	"\tmb\n"
diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h
index 162c17b2631f..660b14ce1317 100644
--- a/arch/alpha/include/asm/pgtable.h
+++ b/arch/alpha/include/asm/pgtable.h
@@ -277,9 +277,9 @@ extern inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= __DIRTY_BITS; retur
 extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; return pte; }
 
 /*
- * The smp_read_barrier_depends() in the following functions are required to
- * order the load of *dir (the pointer in the top level page table) with any
- * subsequent load of the returned pmd_t *ret (ret is data dependent on *dir).
+ * The smp_rmb() in the following functions are required to order the load of
+ * *dir (the pointer in the top level page table) with any subsequent load of
+ * the returned pmd_t *ret (ret is data dependent on *dir).
  *
  * If this ordering is not enforced, the CPU might load an older value of
  * *ret, which may be uninitialized data. See mm/memory.c:__pte_alloc for
@@ -293,7 +293,7 @@ extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; retu
 extern inline pmd_t * pmd_offset(pud_t * dir, unsigned long address)
 {
 	pmd_t *ret = (pmd_t *) pud_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1));
-	smp_read_barrier_depends(); /* see above */
+	smp_rmb(); /* see above */
 	return ret;
 }
 #define pmd_offset pmd_offset
@@ -303,7 +303,7 @@ extern inline pte_t * pte_offset_kernel(pmd_t * dir, unsigned long address)
 {
 	pte_t *ret = (pte_t *) pmd_page_vaddr(*dir)
 		+ ((address >> PAGE_SHIFT) & (PTRS_PER_PAGE - 1));
-	smp_read_barrier_depends(); /* see above */
+	smp_rmb(); /* see above */
 	return ret;
 }
 #define pte_offset_kernel pte_offset_kernel
diff --git a/arch/alpha/include/asm/rwonce.h b/arch/alpha/include/asm/rwonce.h
new file mode 100644
index 000000000000..35542bcf92b3
--- /dev/null
+++ b/arch/alpha/include/asm/rwonce.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Google LLC.
+ */
+#ifndef __ASM_RWONCE_H
+#define __ASM_RWONCE_H
+
+#ifdef CONFIG_SMP
+
+#include <asm/barrier.h>
+
+/*
+ * Alpha is apparently daft enough to reorder address-dependent loads
+ * on some CPU implementations. Knock some common sense into it with
+ * a memory barrier in READ_ONCE().
+ *
+ * For the curious, more information about this unusual reordering is
+ * available in chapter 15 of the "perfbook":
+ *
+ *  https://kernel.org/pub/linux/kernel/people/paulmck/perfbook/perfbook.html
+ *
+ */
+#define __READ_ONCE(x)							\
+({									\
+	__unqual_scalar_typeof(x) __x =					\
+		(*(volatile typeof(__x) *)(&(x)));			\
+	mb();								\
+	(typeof(x))__x;							\
+})
+
+#endif /* CONFIG_SMP */
+
+#include <asm-generic/rwonce.h>
+
+#endif /* __ASM_RWONCE_H */
diff --git a/arch/arm/include/asm/vdso/gettimeofday.h b/arch/arm/include/asm/vdso/gettimeofday.h
index 36dc18553ed8..1b207cf07697 100644
--- a/arch/arm/include/asm/vdso/gettimeofday.h
+++ b/arch/arm/include/asm/vdso/gettimeofday.h
@@ -7,6 +7,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/errno.h>
 #include <asm/unistd.h>
 #include <asm/vdso/cp15.h>
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 66dc41fd49f2..73aee7290cdf 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -118,6 +118,7 @@ config ARM64
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_VDSO_TIME_NS
 	select HANDLE_DOMAIN_IRQ
 	select HARDIRQS_SW_RESEND
 	select HAVE_PCI
@@ -1327,6 +1328,8 @@ config SWP_EMULATION
 	  ARMv8 obsoletes the use of A32 SWP/SWPB instructions such that
 	  they are always undefined. Say Y here to enable software
 	  emulation of these instructions for userspace using LDXR/STXR.
+	  This feature can be controlled at runtime with the abi.swp
+	  sysctl which is disabled by default.
 
 	  In some older versions of glibc [<=2.8] SWP is used during futex
 	  trylock() operations with the assumption that the code will not
@@ -1353,7 +1356,8 @@ config CP15_BARRIER_EMULATION
 	  Say Y here to enable software emulation of these
 	  instructions for AArch32 userspace code. When this option is
 	  enabled, CP15 barrier usage is traced which can help
-	  identify software that needs updating.
+	  identify software that needs updating. This feature can be
+	  controlled at runtime with the abi.cp15_barrier sysctl.
 
 	  If unsure, say Y
 
@@ -1364,7 +1368,8 @@ config SETEND_EMULATION
 	  AArch32 EL0, and is deprecated in ARMv8.
 
 	  Say Y here to enable software emulation of the instruction
-	  for AArch32 userspace code.
+	  for AArch32 userspace code. This feature can be controlled
+	  at runtime with the abi.setend sysctl.
 
 	  Note: All the cpus on the system must have mixed endian support at EL0
 	  for this feature to be enabled. If a new CPU - which doesn't support mixed
@@ -1596,6 +1601,20 @@ config ARM64_AMU_EXTN
 	  correctly reflect reality. Most commonly, the value read will be 0,
 	  indicating that the counter is not enabled.
 
+config AS_HAS_ARMV8_4
+	def_bool $(cc-option,-Wa$(comma)-march=armv8.4-a)
+
+config ARM64_TLB_RANGE
+	bool "Enable support for tlbi range feature"
+	default y
+	depends on AS_HAS_ARMV8_4
+	help
+	  ARMv8.4-TLBI provides TLBI invalidation instruction that apply to a
+	  range of input addresses.
+
+	  The feature introduces new assembly instructions, and they were
+	  support when binutils >= 2.30.
+
 endmenu
 
 menu "ARMv8.5 architectural features"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 70f5905954dd..55bc8546d9c7 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -82,11 +82,18 @@ endif
 # compiler to generate them and consequently to break the single image contract
 # we pass it only to the assembler. This option is utilized only in case of non
 # integrated assemblers.
+ifneq ($(CONFIG_AS_HAS_ARMV8_4), y)
 branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a
 endif
+endif
 
 KBUILD_CFLAGS += $(branch-prot-flags-y)
 
+ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
+# make sure to pass the newest target architecture to -march.
+KBUILD_CFLAGS	+= -Wa,-march=armv8.4-a
+endif
+
 ifeq ($(CONFIG_SHADOW_CALL_STACK), y)
 KBUILD_CFLAGS	+= -ffixed-x18
 endif
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 2ca7ba69c318..39273b5c14be 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -66,6 +66,7 @@ CONFIG_SCHED_SMT=y
 CONFIG_NUMA=y
 CONFIG_SECCOMP=y
 CONFIG_KEXEC=y
+CONFIG_KEXEC_FILE=y
 CONFIG_CRASH_DUMP=y
 CONFIG_XEN=y
 CONFIG_COMPAT=y
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index a45366c3909b..bd68e1b7f29f 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -47,20 +47,7 @@
 pgprot_t __acpi_get_mem_attribute(phys_addr_t addr);
 
 /* ACPI table mapping after acpi_permanent_mmap is set */
-static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
-					    acpi_size size)
-{
-	/* For normal memory we already have a cacheable mapping. */
-	if (memblock_is_map_memory(phys))
-		return (void __iomem *)__phys_to_virt(phys);
-
-	/*
-	 * We should still honor the memory's attribute here because
-	 * crash dump kernel possibly excludes some ACPI (reclaim)
-	 * regions from memblock list.
-	 */
-	return __ioremap(phys, size, __acpi_get_mem_attribute(phys));
-}
+void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size);
 #define acpi_os_ioremap acpi_os_ioremap
 
 typedef u64 phys_cpuid_t;
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index d7b3bb0cb180..07b643a70710 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -62,7 +62,9 @@
 #define ARM64_HAS_GENERIC_AUTH			52
 #define ARM64_HAS_32BIT_EL1			53
 #define ARM64_BTI				54
+#define ARM64_HAS_ARMv8_4_TTL			55
+#define ARM64_HAS_TLB_RANGE			56
 
-#define ARM64_NCAPS				55
+#define ARM64_NCAPS				57
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index f7c3d1ff091d..89b4f0142c28 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -692,6 +692,12 @@ static inline bool system_supports_bti(void)
 	return IS_ENABLED(CONFIG_ARM64_BTI) && cpus_have_const_cap(ARM64_BTI);
 }
 
+static inline bool system_supports_tlb_range(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_TLB_RANGE) &&
+		cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
+}
+
 #define ARM64_BP_HARDEN_UNKNOWN		-1
 #define ARM64_BP_HARDEN_WA_NEEDED	0
 #define ARM64_BP_HARDEN_NOT_REQUIRED	1
@@ -774,6 +780,7 @@ static inline unsigned int get_vmid_bits(u64 mmfr1)
 }
 
 u32 get_kvm_ipa_limit(void);
+void dump_cpu_features(void);
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 94ba0c5bced2..5abf91e3494c 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -49,6 +49,8 @@ extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 				 pte_t *ptep, pte_t pte, unsigned long sz);
 #define set_huge_swap_pte_at set_huge_swap_pte_at
 
+void __init arm64_hugetlb_cma_reserve(void);
+
 #include <asm-generic/hugetlb.h>
 
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index d683bcbf1e7c..22f73fe09030 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -95,6 +95,7 @@
 #define KERNEL_HWCAP_DGH		__khwcap2_feature(DGH)
 #define KERNEL_HWCAP_RNG		__khwcap2_feature(RNG)
 #define KERNEL_HWCAP_BTI		__khwcap2_feature(BTI)
+/* reserved for KERNEL_HWCAP_MTE	__khwcap2_feature(MTE) */
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 3bf626f6fe0c..329fb15f6bac 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -8,7 +8,7 @@
 #ifndef __ASM_KERNEL_PGTABLE_H
 #define __ASM_KERNEL_PGTABLE_H
 
-#include <linux/pgtable.h>
+#include <asm/pgtable-hwdef.h>
 #include <asm/sparsemem.h>
 
 /*
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index a1871bb32bb1..afa722504bfd 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -10,11 +10,8 @@
 #ifndef __ASM_MEMORY_H
 #define __ASM_MEMORY_H
 
-#include <linux/compiler.h>
 #include <linux/const.h>
 #include <linux/sizes.h>
-#include <linux/types.h>
-#include <asm/bug.h>
 #include <asm/page-def.h>
 
 /*
@@ -157,11 +154,15 @@
 #endif
 
 #ifndef __ASSEMBLY__
-extern u64			vabits_actual;
-#define PAGE_END		(_PAGE_END(vabits_actual))
 
 #include <linux/bitops.h>
+#include <linux/compiler.h>
 #include <linux/mmdebug.h>
+#include <linux/types.h>
+#include <asm/bug.h>
+
+extern u64			vabits_actual;
+#define PAGE_END		(_PAGE_END(vabits_actual))
 
 extern s64			physvirt_offset;
 extern s64			memstart_addr;
@@ -322,6 +323,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 	__is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr));	\
 })
 
+void dump_mem_limit(void);
 #endif /* !ASSEMBLY */
 
 /*
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index b0bd9b55594c..f2d7537d6f83 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -175,7 +175,7 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp)
  * take CPU migration into account.
  */
 #define destroy_context(mm)		do { } while(0)
-void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
+void check_and_switch_context(struct mm_struct *mm);
 
 #define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
@@ -214,8 +214,6 @@ enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 
 static inline void __switch_mm(struct mm_struct *next)
 {
-	unsigned int cpu = smp_processor_id();
-
 	/*
 	 * init_mm.pgd does not contain any user mappings and it is always
 	 * active for kernel addresses in TTBR1. Just set the reserved TTBR0.
@@ -225,7 +223,7 @@ static inline void __switch_mm(struct mm_struct *next)
 		return;
 	}
 
-	check_and_switch_context(next, cpu);
+	check_and_switch_context(next);
 }