arm64 updates for 6.19:

Core features:
 
  - Basic Arm MPAM (Memory system resource Partitioning And Monitoring)
    driver under drivers/resctrl/ which makes use of the fs/rectrl/ API
 
 Perf and PMU:
 
  - Avoid cycle counter on multi-threaded CPUs
 
  - Extend CSPMU device probing and add additional filtering support for
    NVIDIA implementations
 
  - Add support for the PMUs on the NoC S3 interconnect
 
  - Add additional compatible strings for new Cortex and C1 CPUs
 
  - Add support for data source filtering to the SPE driver
 
  - Add support for i.MX8QM and "DB" PMU in the imx PMU driver
 
 Memory managemennt:
 
  - Avoid broadcast TLBI if page reused in write fault
 
  - Elide TLB invalidation if the old PTE was not valid
 
  - Drop redundant cpu_set_*_tcr_t0sz() macros
 
  - Propagate pgtable_alloc() errors outside of __create_pgd_mapping()
 
  - Propagate return value from __change_memory_common()
 
 ACPI and EFI:
 
  - Call EFI runtime services without disabling preemption
 
  - Remove unused ACPI function
 
 Miscellaneous:
 
  - ptrace support to disable streaming on SME-only systems
 
  - Improve sysreg generation to include a 'Prefix' descriptor
 
  - Replace __ASSEMBLY__ with __ASSEMBLER__
 
  - Align register dumps in the kselftest zt-test
 
  - Remove some no longer used macros/functions
 
  - Various spelling corrections
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE5RElWfyWxS+3PLO2a9axLQDIXvEFAmkvMjkACgkQa9axLQDI
 XvGaGg//dtT/ZAqrWa6Yniv1LOlh837C07YdxAYTTuJ+I87DnrxIqjwbW+ye+bF+
 61RTkioeCUm3PH+ncO9gPVNi4ASZ1db3/Rc8Fb6rr1TYOI1sMIeBsbbVdRJgsbX6
 zu9197jOBHscTAeDceB6jZBDyW8iSLINPZ7LN6lGxXsZM/Vn5zfE0heKEEio6Fsx
 +AzO2vos0XcwBR9vFGXtiCDx57T+/cXUtrWfA0Cjz4nvHSgD8+ghS+Jwv+kHMt1L
 zrarqbeQfj+Iixm9PVHiazv+8THo9QdNl1yGLxDmJ4LEVPewjW5jBs8+5e8e3/Gj
 p5JEvmSyWvKTTbFoM5vhxC72A7yuT1QwAk2iCyFIxMbQ25PndHboKVp/569DzOkT
 +6CjI88sVSP6D7bVlN6pFlzc/Fa07YagnDMnMCSfk4LBjUfE3jYb+usaFydyv/rl
 jwZbJrnSF/H+uQlyoJFgOEXSoQdDsll3dv6yEsUCwbd8RqXbAe3svbguOUHSdvIj
 sCViezGZQ7Rkn6D21AfF9j6e7ceaSDaf5DWMxPI3dAxFKG8TJbCBsToR59NnoSj+
 bNEozbZ1mCxmwH8i43wZ6P0RkClvJnoXcvRA+TJj02fSZACO39d3XDNswfXWL41r
 KiWGUJZyn2lPKtiAWVX6pSBtDJ+5rFhuoFgADLX6trkxDe9/EMQ=
 =4Sb6
 -----END PGP SIGNATURE-----

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

Pull arm64 updates from Catalin Marinas:
 "These are the arm64 updates for 6.19.

  The biggest part is the Arm MPAM driver under drivers/resctrl/.
  There's a patch touching mm/ to handle spurious faults for huge pmd
  (similar to the pte version). The corresponding arm64 part allows us
  to avoid the TLB maintenance if a (huge) page is reused after a write
  fault. There's EFI refactoring to allow runtime services with
  preemption enabled and the rest is the usual perf/PMU updates and
  several cleanups/typos.

  Summary:

  Core features:

   - Basic Arm MPAM (Memory system resource Partitioning And Monitoring)
     driver under drivers/resctrl/ which makes use of the fs/rectrl/ API

  Perf and PMU:

   - Avoid cycle counter on multi-threaded CPUs

   - Extend CSPMU device probing and add additional filtering support
     for NVIDIA implementations

   - Add support for the PMUs on the NoC S3 interconnect

   - Add additional compatible strings for new Cortex and C1 CPUs

   - Add support for data source filtering to the SPE driver

   - Add support for i.MX8QM and "DB" PMU in the imx PMU driver

  Memory managemennt:

   - Avoid broadcast TLBI if page reused in write fault

   - Elide TLB invalidation if the old PTE was not valid

   - Drop redundant cpu_set_*_tcr_t0sz() macros

   - Propagate pgtable_alloc() errors outside of __create_pgd_mapping()

   - Propagate return value from __change_memory_common()

  ACPI and EFI:

   - Call EFI runtime services without disabling preemption

   - Remove unused ACPI function

  Miscellaneous:

   - ptrace support to disable streaming on SME-only systems

   - Improve sysreg generation to include a 'Prefix' descriptor

   - Replace __ASSEMBLY__ with __ASSEMBLER__

   - Align register dumps in the kselftest zt-test

   - Remove some no longer used macros/functions

   - Various spelling corrections"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (94 commits)
  arm64/mm: Document why linear map split failure upon vm_reset_perms is not problematic
  arm64/pageattr: Propagate return value from __change_memory_common
  arm64/sysreg: Remove unused define ARM64_FEATURE_FIELD_BITS
  KVM: arm64: selftests: Consider all 7 possible levels of cache
  KVM: arm64: selftests: Remove ARM64_FEATURE_FIELD_BITS and its last user
  arm64: atomics: lse: Remove unused parameters from ATOMIC_FETCH_OP_AND macros
  Documentation/arm64: Fix the typo of register names
  ACPI: GTDT: Get rid of acpi_arch_timer_mem_init()
  perf: arm_spe: Add support for filtering on data source
  perf: Add perf_event_attr::config4
  perf/imx_ddr: Add support for PMU in DB (system interconnects)
  perf/imx_ddr: Get and enable optional clks
  perf/imx_ddr: Move ida_alloc() from ddr_perf_init() to ddr_perf_probe()
  dt-bindings: perf: fsl-imx-ddr: Add compatible string for i.MX8QM, i.MX8QXP and i.MX8DXL
  arm64: remove duplicate ARCH_HAS_MEM_ENCRYPT
  arm64: mm: use untagged address to calculate page index
  MAINTAINERS: new entry for MPAM Driver
  arm_mpam: Add kunit tests for props_mismatch()
  arm_mpam: Add kunit test for bitmap reset
  arm_mpam: Add helper to reset saved mbwu state
  ...

Documentation/arch/arm64/booting.rst

@@ -391,13 +391,13 @@ Before jumping into the kernel, the following conditions must be met:
     - SMCR_EL2.LEN must be initialised to the same value for all CPUs the
       kernel will execute on.
 
-    - HWFGRTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
+    - HFGRTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
 
-    - HWFGWTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
+    - HFGWTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
 
-    - HWFGRTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
+    - HFGRTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
 
-    - HWFGWTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
+    - HFGWTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
 
   For CPUs with the Scalable Matrix Extension FA64 feature (FEAT_SME_FA64):
 

Documentation/arch/arm64/sve.rst

@@ -402,6 +402,11 @@ The regset data starts with struct user_sve_header, containing:
   streaming mode and any SETREGSET of NT_ARM_SSVE will enter streaming mode
   if the target was not in streaming mode.
 
+* On systems that do not support SVE it is permitted to use SETREGSET to
+  write SVE_PT_REGS_FPSIMD formatted data via NT_ARM_SVE, in this case the
+  vector length should be specified as 0. This allows streaming mode to be
+  disabled on systems with SME but not SVE.
+
 * If any register data is provided along with SVE_PT_VL_ONEXEC then the
   registers data will be interpreted with the current vector length, not
   the vector length configured for use on exec.

Documentation/devicetree/bindings/perf/fsl-imx-ddr.yaml

@@ -14,6 +14,7 @@ properties:
     oneOf:
       - enum:
           - fsl,imx8-ddr-pmu
+          - fsl,imx8dxl-db-pmu
           - fsl,imx8m-ddr-pmu
           - fsl,imx8mq-ddr-pmu
           - fsl,imx8mm-ddr-pmu
@@ -28,7 +29,10 @@ properties:
               - fsl,imx8mp-ddr-pmu
           - const: fsl,imx8m-ddr-pmu
       - items:
-          - const: fsl,imx8dxl-ddr-pmu
+          - enum:
+              - fsl,imx8dxl-ddr-pmu
+              - fsl,imx8qm-ddr-pmu
+              - fsl,imx8qxp-ddr-pmu
           - const: fsl,imx8-ddr-pmu
       - items:
           - enum:
@@ -43,6 +47,14 @@ properties:
   interrupts:
     maxItems: 1
 
+  clocks:
+    maxItems: 2
+
+  clock-names:
+    items:
+      - const: ipg
+      - const: cnt
+
 required:
   - compatible
   - reg
@@ -50,6 +62,21 @@ required:
 
 additionalProperties: false
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: fsl,imx8dxl-db-pmu
+    then:
+      required:
+        - clocks
+        - clock-names
+    else:
+      properties:
+        clocks: false
+        clock-names: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>

MAINTAINERS

@@ -17470,6 +17470,16 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml
 F:	drivers/video/backlight/mp3309c.c
 
+MPAM DRIVER
+M:	James Morse <james.morse@arm.com>
+M:	Ben Horgan <ben.horgan@arm.com>
+R:	Reinette Chatre <reinette.chatre@intel.com>
+R:	Fenghua Yu <fenghuay@nvidia.com>
+S:	Maintained
+F:	drivers/resctrl/mpam_*
+F:	drivers/resctrl/test_mpam_*
+F:	include/linux/arm_mpam.h
+
 MPS MP2869 DRIVER
 M:	Wensheng Wang <wenswang@yeah.net>
 L:	linux-hwmon@vger.kernel.org

arch/arm64/Kconfig

@@ -47,7 +47,6 @@ config ARM64
 	select ARCH_HAS_SETUP_DMA_OPS
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_SET_MEMORY
-	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	select ARCH_STACKWALK
 	select ARCH_HAS_STRICT_KERNEL_RWX
@@ -2023,6 +2022,31 @@ config ARM64_TLB_RANGE
 	  ARMv8.4-TLBI provides TLBI invalidation instruction that apply to a
 	  range of input addresses.
 
+config ARM64_MPAM
+	bool "Enable support for MPAM"
+	select ARM64_MPAM_DRIVER if EXPERT	# does nothing yet
+	select ACPI_MPAM if ACPI
+	help
+	  Memory System Resource Partitioning and Monitoring (MPAM) is an
+	  optional extension to the Arm architecture that allows each
+	  transaction issued to the memory system to be labelled with a
+	  Partition identifier (PARTID) and Performance Monitoring Group
+	  identifier (PMG).
+
+	  Memory system components, such as the caches, can be configured with
+	  policies to control how much of various physical resources (such as
+	  memory bandwidth or cache memory) the transactions labelled with each
+	  PARTID can consume.  Depending on the capabilities of the hardware,
+	  the PARTID and PMG can also be used as filtering criteria to measure
+	  the memory system resource consumption of different parts of a
+	  workload.
+
+	  Use of this extension requires CPU support, support in the
+	  Memory System Components (MSC), and a description from firmware
+	  of where the MSCs are in the address space.
+
+	  MPAM is exposed to user-space via the resctrl pseudo filesystem.
+
 endmenu # "ARMv8.4 architectural features"
 
 menu "ARMv8.5 architectural features"

arch/arm64/include/asm/alternative-macros.h

@@ -19,7 +19,7 @@
 #error "cpucaps have overflown ARM64_CB_BIT"
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/stringify.h>
 
@@ -207,7 +207,7 @@ alternative_endif
 #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...)	\
 	alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
 
-#endif  /*  __ASSEMBLY__  */
+#endif  /*  __ASSEMBLER__  */
 
 /*
  * Usage: asm(ALTERNATIVE(oldinstr, newinstr, cpucap));
@@ -219,7 +219,7 @@ alternative_endif
 #define ALTERNATIVE(oldinstr, newinstr, ...)   \
 	_ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -263,6 +263,6 @@ alternative_has_cap_unlikely(const unsigned long cpucap)
 	return true;
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_ALTERNATIVE_MACROS_H */

arch/arm64/include/asm/alternative.h

@@ -4,7 +4,7 @@
 
 #include <asm/alternative-macros.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/init.h>
 #include <linux/types.h>
@@ -37,5 +37,5 @@ static inline int apply_alternatives_module(void *start, size_t length)
 void alt_cb_patch_nops(struct alt_instr *alt, __le32 *origptr,
 		       __le32 *updptr, int nr_inst);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_ALTERNATIVE_H */

arch/arm64/include/asm/arch_gicv3.h

@@ -9,7 +9,7 @@
 
 #include <asm/sysreg.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/irqchip/arm-gic-common.h>
 #include <linux/stringify.h>
@@ -188,5 +188,5 @@ static inline bool gic_has_relaxed_pmr_sync(void)
 	return cpus_have_cap(ARM64_HAS_GIC_PRIO_RELAXED_SYNC);
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_ARCH_GICV3_H */

arch/arm64/include/asm/asm-extable.h

@@ -27,7 +27,7 @@
 /* Data fields for EX_TYPE_UACCESS_CPY */
 #define EX_DATA_UACCESS_WRITE	BIT(0)
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #define __ASM_EXTABLE_RAW(insn, fixup, type, data)	\
 	.pushsection	__ex_table, "a";		\
@@ -77,7 +77,7 @@
 	__ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_UACCESS_CPY, \uaccess_is_write)
 	.endm
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #include <linux/stringify.h>
 
@@ -132,6 +132,6 @@
 			    EX_DATA_REG(ADDR, addr)				\
 			  ")")
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_ASM_EXTABLE_H */

arch/arm64/include/asm/assembler.h

@@ -5,7 +5,7 @@
  * Copyright (C) 1996-2000 Russell King
  * Copyright (C) 2012 ARM Ltd.
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #error "Only include this from assembly code"
 #endif
 
@@ -325,14 +325,14 @@ alternative_cb_end
  * tcr_set_t0sz - update TCR.T0SZ so that we can load the ID map
  */
 	.macro	tcr_set_t0sz, valreg, t0sz
-	bfi	\valreg, \t0sz, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
+	bfi	\valreg, \t0sz, #TCR_EL1_T0SZ_SHIFT, #TCR_EL1_T0SZ_WIDTH
 	.endm
 
 /*
  * tcr_set_t1sz - update TCR.T1SZ
  */
 	.macro	tcr_set_t1sz, valreg, t1sz
-	bfi	\valreg, \t1sz, #TCR_T1SZ_OFFSET, #TCR_TxSZ_WIDTH
+	bfi	\valreg, \t1sz, #TCR_EL1_T1SZ_SHIFT, #TCR_EL1_T1SZ_WIDTH
 	.endm
 
 /*
@@ -371,7 +371,7 @@ alternative_endif
  * [start, end) with dcache line size explicitly provided.
  *
  * 	op:		operation passed to dc instruction
- * 	domain:		domain used in dsb instruciton
+ * 	domain:		domain used in dsb instruction
  * 	start:          starting virtual address of the region
  * 	end:            end virtual address of the region
  *	linesz:		dcache line size
@@ -412,7 +412,7 @@ alternative_endif
  * [start, end)
  *
  * 	op:		operation passed to dc instruction
- * 	domain:		domain used in dsb instruciton
+ * 	domain:		domain used in dsb instruction
  * 	start:          starting virtual address of the region
  * 	end:            end virtual address of the region
  * 	fixup:		optional label to branch to on user fault
@@ -589,7 +589,7 @@ alternative_endif
 	.macro	offset_ttbr1, ttbr, tmp
 #if defined(CONFIG_ARM64_VA_BITS_52) && !defined(CONFIG_ARM64_LPA2)
 	mrs	\tmp, tcr_el1
-	and	\tmp, \tmp, #TCR_T1SZ_MASK
+	and	\tmp, \tmp, #TCR_EL1_T1SZ_MASK
 	cmp	\tmp, #TCR_T1SZ(VA_BITS_MIN)
 	orr	\tmp, \ttbr, #TTBR1_BADDR_4852_OFFSET
 	csel	\ttbr, \tmp, \ttbr, eq

arch/arm64/include/asm/atomic_lse.h

@@ -103,17 +103,17 @@ static __always_inline void __lse_atomic_and(int i, atomic_t *v)
 	return __lse_atomic_andnot(~i, v);
 }
 
-#define ATOMIC_FETCH_OP_AND(name, mb, cl...)				\
+#define ATOMIC_FETCH_OP_AND(name)					\
 static __always_inline int						\
 __lse_atomic_fetch_and##name(int i, atomic_t *v)			\
 {									\
 	return __lse_atomic_fetch_andnot##name(~i, v);			\
 }
 
-ATOMIC_FETCH_OP_AND(_relaxed,   )
+ATOMIC_FETCH_OP_AND(_relaxed)
-ATOMIC_FETCH_OP_AND(_acquire,  a, "memory")
+ATOMIC_FETCH_OP_AND(_acquire)
-ATOMIC_FETCH_OP_AND(_release,  l, "memory")
+ATOMIC_FETCH_OP_AND(_release)
-ATOMIC_FETCH_OP_AND(        , al, "memory")
+ATOMIC_FETCH_OP_AND(        )
 
 #undef ATOMIC_FETCH_OP_AND
 
@@ -210,17 +210,17 @@ static __always_inline void __lse_atomic64_and(s64 i, atomic64_t *v)
 	return __lse_atomic64_andnot(~i, v);
 }
 
-#define ATOMIC64_FETCH_OP_AND(name, mb, cl...)				\
+#define ATOMIC64_FETCH_OP_AND(name)					\
 static __always_inline long						\
 __lse_atomic64_fetch_and##name(s64 i, atomic64_t *v)			\
 {									\
 	return __lse_atomic64_fetch_andnot##name(~i, v);		\
 }
 
-ATOMIC64_FETCH_OP_AND(_relaxed,   )
+ATOMIC64_FETCH_OP_AND(_relaxed)
-ATOMIC64_FETCH_OP_AND(_acquire,  a, "memory")
+ATOMIC64_FETCH_OP_AND(_acquire)
-ATOMIC64_FETCH_OP_AND(_release,  l, "memory")
+ATOMIC64_FETCH_OP_AND(_release)
-ATOMIC64_FETCH_OP_AND(        , al, "memory")
+ATOMIC64_FETCH_OP_AND(        )
 
 #undef ATOMIC64_FETCH_OP_AND
 

arch/arm64/include/asm/barrier.h

@@ -7,7 +7,7 @@
 #ifndef __ASM_BARRIER_H
 #define __ASM_BARRIER_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/kasan-checks.h>
 
@@ -221,6 +221,6 @@ do {									\
 
 #include <asm-generic/barrier.h>
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif	/* __ASM_BARRIER_H */

arch/arm64/include/asm/cache.h

@@ -35,7 +35,7 @@
 #define ARCH_DMA_MINALIGN	(128)
 #define ARCH_KMALLOC_MINALIGN	(8)
 
-#if !defined(__ASSEMBLY__) && !defined(BUILD_VDSO)
+#if !defined(__ASSEMBLER__) && !defined(BUILD_VDSO)
 
 #include <linux/bitops.h>
 #include <linux/kasan-enabled.h>
@@ -135,6 +135,6 @@ static inline u32 __attribute_const__ read_cpuid_effective_cachetype(void)
 	return ctr;
 }
 
-#endif /* !defined(__ASSEMBLY__) && !defined(BUILD_VDSO) */
+#endif /* !defined(__ASSEMBLER__) && !defined(BUILD_VDSO) */
 
 #endif

arch/arm64/include/asm/cpucaps.h

@@ -5,7 +5,7 @@
 
 #include <asm/cpucap-defs.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 /*
  * Check whether a cpucap is possible at compiletime.
@@ -77,6 +77,6 @@ cpucap_is_possible(const unsigned int cap)
 
 	return true;
 }
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/cpufeature.h

@@ -19,7 +19,7 @@
 #define ARM64_SW_FEATURE_OVERRIDE_HVHE		4
 #define ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF	8
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/bug.h>
 #include <linux/jump_label.h>
@@ -199,7 +199,7 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
  *    registers (e.g, SCTLR, TCR etc.) or patching the kernel via
  *    alternatives. The kernel patching is batched and performed at later
  *    point. The actions are always initiated only after the capability
- *    is finalised. This is usally denoted by "enabling" the capability.
+ *    is finalised. This is usually denoted by "enabling" the capability.
  *    The actions are initiated as follows :
  *	a) Action is triggered on all online CPUs, after the capability is
  *	finalised, invoked within the stop_machine() context from
@@ -251,7 +251,7 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
 #define ARM64_CPUCAP_SCOPE_LOCAL_CPU		((u16)BIT(0))
 #define ARM64_CPUCAP_SCOPE_SYSTEM		((u16)BIT(1))
 /*
- * The capabilitiy is detected on the Boot CPU and is used by kernel
+ * The capability is detected on the Boot CPU and is used by kernel
  * during early boot. i.e, the capability should be "detected" and
  * "enabled" as early as possibly on all booting CPUs.
  */
@@ -1078,6 +1078,6 @@ static inline bool cpu_has_lpa2(void)
 #endif
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif

arch/arm64/include/asm/cputype.h

@@ -247,9 +247,9 @@
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
 #define MIDR_FUJITSU_ERRATUM_010001		MIDR_FUJITSU_A64FX
 #define MIDR_FUJITSU_ERRATUM_010001_MASK	(~MIDR_CPU_VAR_REV(1, 0))
-#define TCR_CLEAR_FUJITSU_ERRATUM_010001	(TCR_NFD1 | TCR_NFD0)
+#define TCR_CLEAR_FUJITSU_ERRATUM_010001	(TCR_EL1_NFD1 | TCR_EL1_NFD0)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/sysreg.h>
 
@@ -328,6 +328,6 @@ static inline u32 __attribute_const__ read_cpuid_cachetype(void)
 {
 	return read_cpuid(CTR_EL0);
 }
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif

arch/arm64/include/asm/current.h

@@ -4,7 +4,7 @@
 
 #include <linux/compiler.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct task_struct;
 
@@ -23,7 +23,7 @@ static __always_inline struct task_struct *get_current(void)
 
 #define current get_current()
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_CURRENT_H */
 

arch/arm64/include/asm/debug-monitors.h

@@ -48,7 +48,7 @@
 #define AARCH32_BREAK_THUMB2_LO	0xf7f0
 #define AARCH32_BREAK_THUMB2_HI	0xa000
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 struct task_struct;
 
 #define DBG_ARCH_ID_RESERVED	0	/* In case of ptrace ABI updates. */
@@ -88,5 +88,5 @@ static inline bool try_step_suspended_breakpoints(struct pt_regs *regs)
 
 bool try_handle_aarch32_break(struct pt_regs *regs);
 
-#endif	/* __ASSEMBLY */
+#endif	/* __ASSEMBLER__ */
 #endif	/* __ASM_DEBUG_MONITORS_H */

arch/arm64/include/asm/efi.h

@@ -126,21 +126,14 @@ static inline void efi_set_pgd(struct mm_struct *mm)
 		if (mm != current->active_mm) {
 			/*
 			 * Update the current thread's saved ttbr0 since it is
-			 * restored as part of a return from exception. Enable
+			 * restored as part of a return from exception.
-			 * access to the valid TTBR0_EL1 and invoke the errata
-			 * workaround directly since there is no return from
-			 * exception when invoking the EFI run-time services.
 			 */
 			update_saved_ttbr0(current, mm);
-			uaccess_ttbr0_enable();
-			post_ttbr_update_workaround();
 		} else {
 			/*
-			 * Defer the switch to the current thread's TTBR0_EL1
+			 * Restore the current thread's saved ttbr0
-			 * until uaccess_enable(). Restore the current
+			 * corresponding to its active_mm
-			 * thread's saved ttbr0 corresponding to its active_mm
 			 */
-			uaccess_ttbr0_disable();
 			update_saved_ttbr0(current, current->active_mm);
 		}
 	}

arch/arm64/include/asm/el2_setup.h

@@ -7,7 +7,7 @@
 #ifndef __ARM_KVM_INIT_H__
 #define __ARM_KVM_INIT_H__
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #error Assembly-only header
 #endif
 
@@ -24,7 +24,7 @@
 	 * ID_AA64MMFR4_EL1.E2H0 < 0. On such CPUs HCR_EL2.E2H is RES1, but it
 	 * can reset into an UNKNOWN state and might not read as 1 until it has
 	 * been initialized explicitly.
-	 * Initalize HCR_EL2.E2H so that later code can rely upon HCR_EL2.E2H
+	 * Initialize HCR_EL2.E2H so that later code can rely upon HCR_EL2.E2H
 	 * indicating whether the CPU is running in E2H mode.
 	 */
 	mrs_s	x1, SYS_ID_AA64MMFR4_EL1

arch/arm64/include/asm/elf.h

@@ -133,7 +133,7 @@
 #define ELF_ET_DYN_BASE		(2 * DEFAULT_MAP_WINDOW_64 / 3)
 #endif /* CONFIG_ARM64_FORCE_52BIT */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <uapi/linux/elf.h>
 #include <linux/bug.h>
@@ -293,6 +293,6 @@ static inline int arch_check_elf(void *ehdr, bool has_interp,
 	return 0;
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif

arch/arm64/include/asm/esr.h

@@ -431,7 +431,7 @@
 #define ESR_ELx_IT_GCSPOPCX		6
 #define ESR_ELx_IT_GCSPOPX		7
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/types.h>
 
 static inline unsigned long esr_brk_comment(unsigned long esr)
@@ -534,6 +534,6 @@ static inline bool esr_iss_is_eretab(unsigned long esr)
 }
 
 const char *esr_get_class_string(unsigned long esr);
-#endif /* __ASSEMBLY */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_ESR_H */

arch/arm64/include/asm/fixmap.h

@@ -15,7 +15,7 @@
 #ifndef _ASM_ARM64_FIXMAP_H
 #define _ASM_ARM64_FIXMAP_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/kernel.h>
 #include <linux/math.h>
 #include <linux/sizes.h>
@@ -117,5 +117,5 @@ extern void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t pr
 
 #include <asm-generic/fixmap.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_ARM64_FIXMAP_H */

arch/arm64/include/asm/fpsimd.h

@@ -12,7 +12,7 @@
 #include <asm/sigcontext.h>
 #include <asm/sysreg.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/bitmap.h>
 #include <linux/build_bug.h>

arch/arm64/include/asm/ftrace.h

@@ -37,7 +37,7 @@
  */
 #define ARCH_FTRACE_SHIFT_STACK_TRACER 1
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/compat.h>
 
 extern void _mcount(unsigned long);
@@ -217,9 +217,9 @@ static inline bool arch_syscall_match_sym_name(const char *sym,
 	 */
 	return !strcmp(sym + 8, name);
 }
-#endif /* ifndef __ASSEMBLY__ */
+#endif /* ifndef __ASSEMBLER__ */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,

arch/arm64/include/asm/gpr-num.h

@@ -2,7 +2,7 @@
 #ifndef __ASM_GPR_NUM_H
 #define __ASM_GPR_NUM_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
 	.equ	.L__gpr_num_x\num, \num
@@ -11,7 +11,7 @@
 	.equ	.L__gpr_num_xzr, 31
 	.equ	.L__gpr_num_wzr, 31
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #define __DEFINE_ASM_GPR_NUMS					\
 "	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" \
@@ -21,6 +21,6 @@
 "	.equ	.L__gpr_num_xzr, 31\n"				\
 "	.equ	.L__gpr_num_wzr, 31\n"
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_GPR_NUM_H */

arch/arm64/include/asm/hwcap.h

@@ -46,7 +46,7 @@
 #define COMPAT_HWCAP2_SB	(1 << 5)
 #define COMPAT_HWCAP2_SSBS	(1 << 6)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/log2.h>
 
 /*

arch/arm64/include/asm/image.h

@@ -20,7 +20,7 @@
 #define ARM64_IMAGE_FLAG_PAGE_SIZE_64K		3
 #define ARM64_IMAGE_FLAG_PHYS_BASE		1
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define arm64_image_flag_field(flags, field) \
 				(((flags) >> field##_SHIFT) & field##_MASK)
@@ -54,6 +54,6 @@ struct arm64_image_header {
 	__le32 res5;
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_IMAGE_H */

arch/arm64/include/asm/insn.h

@@ -12,7 +12,7 @@
 
 #include <asm/insn-def.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 enum aarch64_insn_hint_cr_op {
 	AARCH64_INSN_HINT_NOP	= 0x0 << 5,
@@ -730,6 +730,6 @@ u32 aarch32_insn_mcr_extract_crm(u32 insn);
 typedef bool (pstate_check_t)(unsigned long);
 extern pstate_check_t * const aarch32_opcode_cond_checks[16];
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif	/* __ASM_INSN_H */

arch/arm64/include/asm/jump_label.h

@@ -8,7 +8,7 @@
 #ifndef __ASM_JUMP_LABEL_H
 #define __ASM_JUMP_LABEL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <asm/insn.h>
@@ -58,5 +58,5 @@ static __always_inline bool arch_static_branch_jump(struct static_key * const ke
 	return true;
 }
 
-#endif  /* __ASSEMBLY__ */
+#endif  /* __ASSEMBLER__ */
 #endif	/* __ASM_JUMP_LABEL_H */

arch/arm64/include/asm/kasan.h

@@ -2,7 +2,7 @@
 #ifndef __ASM_KASAN_H
 #define __ASM_KASAN_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/linkage.h>
 #include <asm/memory.h>

arch/arm64/include/asm/kexec.h

@@ -25,7 +25,7 @@
 
 #define KEXEC_ARCH KEXEC_ARCH_AARCH64
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /**
  * crash_setup_regs() - save registers for the panic kernel
@@ -130,6 +130,6 @@ extern int load_other_segments(struct kimage *image,
 		char *cmdline);
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif

arch/arm64/include/asm/kgdb.h

@@ -14,7 +14,7 @@
 #include <linux/ptrace.h>
 #include <asm/debug-monitors.h>
 
-#ifndef	__ASSEMBLY__
+#ifndef	__ASSEMBLER__
 
 static inline void arch_kgdb_breakpoint(void)
 {
@@ -36,7 +36,7 @@ static inline int kgdb_single_step_handler(struct pt_regs *regs,
 }
 #endif
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /*
  * gdb remote procotol (well most versions of it) expects the following

arch/arm64/include/asm/kvm_asm.h

@@ -46,7 +46,7 @@
 
 #define __KVM_HOST_SMCCC_FUNC___kvm_hyp_init			0
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/mm.h>
 
@@ -303,7 +303,7 @@ void kvm_compute_final_ctr_el0(struct alt_instr *alt,
 void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, u64 elr_virt,
 	u64 elr_phys, u64 par, uintptr_t vcpu, u64 far, u64 hpfar);
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 .macro get_host_ctxt reg, tmp
 	adr_this_cpu \reg, kvm_host_data, \tmp

arch/arm64/include/asm/kvm_mmu.h

@@ -49,7 +49,7 @@
  * mappings, and none of this applies in that case.
  */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #include <asm/alternative.h>
 
@@ -396,5 +396,5 @@ void kvm_s2_ptdump_create_debugfs(struct kvm *kvm);
 static inline void kvm_s2_ptdump_create_debugfs(struct kvm *kvm) {}
 #endif /* CONFIG_PTDUMP_STAGE2_DEBUGFS */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ARM64_KVM_MMU_H__ */

arch/arm64/include/asm/kvm_mte.h

@@ -5,7 +5,7 @@
 #ifndef __ASM_KVM_MTE_H
 #define __ASM_KVM_MTE_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #include <asm/sysreg.h>
 
@@ -62,5 +62,5 @@ alternative_else_nop_endif
 .endm
 
 #endif /* CONFIG_ARM64_MTE */
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_KVM_MTE_H */

arch/arm64/include/asm/kvm_ptrauth.h

@@ -8,7 +8,7 @@
 #ifndef __ASM_KVM_PTRAUTH_H
 #define __ASM_KVM_PTRAUTH_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #include <asm/sysreg.h>
 
@@ -100,7 +100,7 @@ alternative_else_nop_endif
 .endm
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
-#else  /* !__ASSEMBLY */
+#else  /* !__ASSEMBLER__ */
 
 #define __ptrauth_save_key(ctxt, key)					\
 	do {								\
@@ -120,5 +120,5 @@ alternative_else_nop_endif
 		__ptrauth_save_key(ctxt, APGA);				\
 	} while(0)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_KVM_PTRAUTH_H */

arch/arm64/include/asm/linkage.h

@@ -1,7 +1,7 @@
 #ifndef __ASM_LINKAGE_H
 #define __ASM_LINKAGE_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #include <asm/assembler.h>
 #endif
 

arch/arm64/include/asm/memory.h

@@ -207,7 +207,7 @@
  */
 #define TRAMP_SWAPPER_OFFSET	(2 * PAGE_SIZE)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/bitops.h>
 #include <linux/compiler.h>
@@ -392,7 +392,6 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
  *  virt_to_page(x)	convert a _valid_ virtual address to struct page *
  *  virt_addr_valid(x)	indicates whether a virtual address is valid
  */
-#define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
 
 #if defined(CONFIG_DEBUG_VIRTUAL)
 #define page_to_virt(x)	({						\
@@ -422,7 +421,7 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
 })
 
 void dump_mem_limit(void);
-#endif /* !ASSEMBLY */
+#endif /* !__ASSEMBLER__ */
 
 /*
  * Given that the GIC architecture permits ITS implementations that can only be

arch/arm64/include/asm/mmu.h

@@ -12,7 +12,7 @@
 #define USER_ASID_FLAG	(UL(1) << USER_ASID_BIT)
 #define TTBR_ASID_MASK	(UL(0xffff) << 48)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/refcount.h>
 #include <asm/cpufeature.h>
@@ -112,5 +112,5 @@ void kpti_install_ng_mappings(void);
 static inline void kpti_install_ng_mappings(void) {}
 #endif
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 #endif

arch/arm64/include/asm/mmu_context.h

@@ -8,7 +8,7 @@
 #ifndef __ASM_MMU_CONTEXT_H
 #define __ASM_MMU_CONTEXT_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/compiler.h>
 #include <linux/sched.h>
@@ -61,11 +61,6 @@ static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
 	cpu_do_switch_mm(virt_to_phys(pgd),mm);
 }
 
-/*
- * TCR.T0SZ value to use when the ID map is active.
- */
-#define idmap_t0sz	TCR_T0SZ(IDMAP_VA_BITS)
-
 /*
  * Ensure TCR.T0SZ is set to the provided value.
  */
@@ -73,18 +68,15 @@ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz)
 {
 	unsigned long tcr = read_sysreg(tcr_el1);
 
-	if ((tcr & TCR_T0SZ_MASK) == t0sz)
+	if ((tcr & TCR_EL1_T0SZ_MASK) == t0sz)
 		return;
 
-	tcr &= ~TCR_T0SZ_MASK;
+	tcr &= ~TCR_EL1_T0SZ_MASK;
 	tcr |= t0sz;
 	write_sysreg(tcr, tcr_el1);
 	isb();
 }
 
-#define cpu_set_default_tcr_t0sz()	__cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual))
-#define cpu_set_idmap_tcr_t0sz()	__cpu_set_tcr_t0sz(idmap_t0sz)
-
 /*
  * Remove the idmap from TTBR0_EL1 and install the pgd of the active mm.
  *
@@ -103,7 +95,7 @@ static inline void cpu_uninstall_idmap(void)
 
 	cpu_set_reserved_ttbr0();
 	local_flush_tlb_all();
-	cpu_set_default_tcr_t0sz();
+	__cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual));
 
 	if (mm != &init_mm && !system_uses_ttbr0_pan())
 		cpu_switch_mm(mm->pgd, mm);
@@ -113,7 +105,7 @@ static inline void cpu_install_idmap(void)
 {
 	cpu_set_reserved_ttbr0();
 	local_flush_tlb_all();
-	cpu_set_idmap_tcr_t0sz();
+	__cpu_set_tcr_t0sz(TCR_T0SZ(IDMAP_VA_BITS));
 
 	cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm);
 }
@@ -330,6 +322,6 @@ static inline void deactivate_mm(struct task_struct *tsk,
 
 #include <asm-generic/mmu_context.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* !__ASM_MMU_CONTEXT_H */

arch/arm64/include/asm/mte-kasan.h

@@ -9,7 +9,7 @@
 #include <asm/cputype.h>
 #include <asm/mte-def.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -259,6 +259,6 @@ static inline int mte_enable_kernel_store_only(void)
 
 #endif /* CONFIG_ARM64_MTE */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_MTE_KASAN_H  */

arch/arm64/include/asm/mte.h

@@ -8,7 +8,7 @@
 #include <asm/compiler.h>
 #include <asm/mte-def.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/bitfield.h>
 #include <linux/kasan-enabled.h>
@@ -282,5 +282,5 @@ static inline void mte_check_tfsr_exit(void)
 }
 #endif /* CONFIG_KASAN_HW_TAGS */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_MTE_H  */

arch/arm64/include/asm/page.h

@@ -10,7 +10,7 @@
 
 #include <asm/page-def.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/personality.h> /* for READ_IMPLIES_EXEC */
 #include <linux/types.h> /* for gfp_t */
@@ -45,7 +45,7 @@ int pfn_is_map_memory(unsigned long pfn);
 
 #include <asm/memory.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #define VM_DATA_DEFAULT_FLAGS	(VM_DATA_FLAGS_TSK_EXEC | VM_MTE_ALLOWED)
 

arch/arm64/include/asm/pgtable-hwdef.h

@@ -228,102 +228,53 @@
 /*
  * TCR flags.
  */
-#define TCR_T0SZ_OFFSET		0
+#define TCR_T0SZ(x)		((UL(64) - (x)) << TCR_EL1_T0SZ_SHIFT)
-#define TCR_T1SZ_OFFSET		16
+#define TCR_T1SZ(x)		((UL(64) - (x)) << TCR_EL1_T1SZ_SHIFT)
-#define TCR_T0SZ(x)		((UL(64) - (x)) << TCR_T0SZ_OFFSET)
-#define TCR_T1SZ(x)		((UL(64) - (x)) << TCR_T1SZ_OFFSET)
-#define TCR_TxSZ(x)		(TCR_T0SZ(x) | TCR_T1SZ(x))
-#define TCR_TxSZ_WIDTH		6
-#define TCR_T0SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET)
-#define TCR_T1SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T1SZ_OFFSET)
 
-#define TCR_EPD0_SHIFT		7
+#define TCR_T0SZ_MASK		TCR_EL1_T0SZ_MASK
-#define TCR_EPD0_MASK		(UL(1) << TCR_EPD0_SHIFT)
+#define TCR_T1SZ_MASK		TCR_EL1_T1SZ_MASK
-#define TCR_IRGN0_SHIFT		8
-#define TCR_IRGN0_MASK		(UL(3) << TCR_IRGN0_SHIFT)
-#define TCR_IRGN0_NC		(UL(0) << TCR_IRGN0_SHIFT)
-#define TCR_IRGN0_WBWA		(UL(1) << TCR_IRGN0_SHIFT)
-#define TCR_IRGN0_WT		(UL(2) << TCR_IRGN0_SHIFT)
-#define TCR_IRGN0_WBnWA		(UL(3) << TCR_IRGN0_SHIFT)
 
-#define TCR_EPD1_SHIFT		23
+#define TCR_EPD0_MASK		TCR_EL1_EPD0_MASK
-#define TCR_EPD1_MASK		(UL(1) << TCR_EPD1_SHIFT)
+#define TCR_EPD1_MASK		TCR_EL1_EPD1_MASK
-#define TCR_IRGN1_SHIFT		24
-#define TCR_IRGN1_MASK		(UL(3) << TCR_IRGN1_SHIFT)
-#define TCR_IRGN1_NC		(UL(0) << TCR_IRGN1_SHIFT)
-#define TCR_IRGN1_WBWA		(UL(1) << TCR_IRGN1_SHIFT)
-#define TCR_IRGN1_WT		(UL(2) << TCR_IRGN1_SHIFT)
-#define TCR_IRGN1_WBnWA		(UL(3) << TCR_IRGN1_SHIFT)
 
-#define TCR_IRGN_NC		(TCR_IRGN0_NC | TCR_IRGN1_NC)
+#define TCR_IRGN0_MASK		TCR_EL1_IRGN0_MASK
-#define TCR_IRGN_WBWA		(TCR_IRGN0_WBWA | TCR_IRGN1_WBWA)
+#define TCR_IRGN0_WBWA		(TCR_EL1_IRGN0_WBWA << TCR_EL1_IRGN0_SHIFT)
-#define TCR_IRGN_WT		(TCR_IRGN0_WT | TCR_IRGN1_WT)
-#define TCR_IRGN_WBnWA		(TCR_IRGN0_WBnWA | TCR_IRGN1_WBnWA)
-#define TCR_IRGN_MASK		(TCR_IRGN0_MASK | TCR_IRGN1_MASK)
 
+#define TCR_ORGN0_MASK		TCR_EL1_ORGN0_MASK
+#define TCR_ORGN0_WBWA		(TCR_EL1_ORGN0_WBWA << TCR_EL1_ORGN0_SHIFT)
 
-#define TCR_ORGN0_SHIFT		10
+#define TCR_SH0_MASK		TCR_EL1_SH0_MASK
-#define TCR_ORGN0_MASK		(UL(3) << TCR_ORGN0_SHIFT)
+#define TCR_SH0_INNER		(TCR_EL1_SH0_INNER << TCR_EL1_SH0_SHIFT)
-#define TCR_ORGN0_NC		(UL(0) << TCR_ORGN0_SHIFT)
-#define TCR_ORGN0_WBWA		(UL(1) << TCR_ORGN0_SHIFT)
-#define TCR_ORGN0_WT		(UL(2) << TCR_ORGN0_SHIFT)
-#define TCR_ORGN0_WBnWA		(UL(3) << TCR_ORGN0_SHIFT)
 
-#define TCR_ORGN1_SHIFT		26
+#define TCR_SH1_MASK		TCR_EL1_SH1_MASK
-#define TCR_ORGN1_MASK		(UL(3) << TCR_ORGN1_SHIFT)
-#define TCR_ORGN1_NC		(UL(0) << TCR_ORGN1_SHIFT)
-#define TCR_ORGN1_WBWA		(UL(1) << TCR_ORGN1_SHIFT)
-#define TCR_ORGN1_WT		(UL(2) << TCR_ORGN1_SHIFT)
-#define TCR_ORGN1_WBnWA		(UL(3) << TCR_ORGN1_SHIFT)
 
-#define TCR_ORGN_NC		(TCR_ORGN0_NC | TCR_ORGN1_NC)
+#define TCR_TG0_SHIFT		TCR_EL1_TG0_SHIFT
-#define TCR_ORGN_WBWA		(TCR_ORGN0_WBWA | TCR_ORGN1_WBWA)
+#define TCR_TG0_MASK		TCR_EL1_TG0_MASK
-#define TCR_ORGN_WT		(TCR_ORGN0_WT | TCR_ORGN1_WT)
+#define TCR_TG0_4K		(TCR_EL1_TG0_4K << TCR_EL1_TG0_SHIFT)
-#define TCR_ORGN_WBnWA		(TCR_ORGN0_WBnWA | TCR_ORGN1_WBnWA)
+#define TCR_TG0_64K		(TCR_EL1_TG0_64K << TCR_EL1_TG0_SHIFT)
-#define TCR_ORGN_MASK		(TCR_ORGN0_MASK | TCR_ORGN1_MASK)
+#define TCR_TG0_16K		(TCR_EL1_TG0_16K << TCR_EL1_TG0_SHIFT)
 
-#define TCR_SH0_SHIFT		12
+#define TCR_TG1_SHIFT		TCR_EL1_TG1_SHIFT
-#define TCR_SH0_MASK		(UL(3) << TCR_SH0_SHIFT)
+#define TCR_TG1_MASK		TCR_EL1_TG1_MASK
-#define TCR_SH0_INNER		(UL(3) << TCR_SH0_SHIFT)
+#define TCR_TG1_16K		(TCR_EL1_TG1_16K << TCR_EL1_TG1_SHIFT)
+#define TCR_TG1_4K		(TCR_EL1_TG1_4K << TCR_EL1_TG1_SHIFT)
+#define TCR_TG1_64K		(TCR_EL1_TG1_64K << TCR_EL1_TG1_SHIFT)
 
-#define TCR_SH1_SHIFT		28
+#define TCR_IPS_SHIFT		TCR_EL1_IPS_SHIFT
-#define TCR_SH1_MASK		(UL(3) << TCR_SH1_SHIFT)
+#define TCR_IPS_MASK		TCR_EL1_IPS_MASK
-#define TCR_SH1_INNER		(UL(3) << TCR_SH1_SHIFT)
+#define TCR_A1			TCR_EL1_A1
-#define TCR_SHARED		(TCR_SH0_INNER | TCR_SH1_INNER)
+#define TCR_ASID16		TCR_EL1_AS
-
+#define TCR_TBI0		TCR_EL1_TBI0
-#define TCR_TG0_SHIFT		14
+#define TCR_TBI1		TCR_EL1_TBI1
-#define TCR_TG0_MASK		(UL(3) << TCR_TG0_SHIFT)
+#define TCR_HA			TCR_EL1_HA
-#define TCR_TG0_4K		(UL(0) << TCR_TG0_SHIFT)
+#define TCR_HD			TCR_EL1_HD
-#define TCR_TG0_64K		(UL(1) << TCR_TG0_SHIFT)
+#define TCR_HPD0		TCR_EL1_HPD0
-#define TCR_TG0_16K		(UL(2) << TCR_TG0_SHIFT)
+#define TCR_HPD1		TCR_EL1_HPD1
-
+#define TCR_TBID0		TCR_EL1_TBID0
-#define TCR_TG1_SHIFT		30
+#define TCR_TBID1		TCR_EL1_TBID1
-#define TCR_TG1_MASK		(UL(3) << TCR_TG1_SHIFT)
+#define TCR_E0PD0		TCR_EL1_E0PD0
-#define TCR_TG1_16K		(UL(1) << TCR_TG1_SHIFT)
+#define TCR_E0PD1		TCR_EL1_E0PD1
-#define TCR_TG1_4K		(UL(2) << TCR_TG1_SHIFT)
+#define TCR_DS			TCR_EL1_DS
-#define TCR_TG1_64K		(UL(3) << TCR_TG1_SHIFT)
-
-#define TCR_IPS_SHIFT		32
-#define TCR_IPS_MASK		(UL(7) << TCR_IPS_SHIFT)
-#define TCR_A1			(UL(1) << 22)
-#define TCR_ASID16		(UL(1) << 36)
-#define TCR_TBI0		(UL(1) << 37)
-#define TCR_TBI1		(UL(1) << 38)
-#define TCR_HA			(UL(1) << 39)
-#define TCR_HD			(UL(1) << 40)
-#define TCR_HPD0_SHIFT		41
-#define TCR_HPD0		(UL(1) << TCR_HPD0_SHIFT)
-#define TCR_HPD1_SHIFT		42
-#define TCR_HPD1		(UL(1) << TCR_HPD1_SHIFT)
-#define TCR_TBID0		(UL(1) << 51)
-#define TCR_TBID1		(UL(1) << 52)
-#define TCR_NFD0		(UL(1) << 53)
-#define TCR_NFD1		(UL(1) << 54)
-#define TCR_E0PD0		(UL(1) << 55)
-#define TCR_E0PD1		(UL(1) << 56)
-#define TCR_TCMA0		(UL(1) << 57)
-#define TCR_TCMA1		(UL(1) << 58)
-#define TCR_DS			(UL(1) << 59)
 
 /*
  * TTBR.

arch/arm64/include/asm/pgtable-prot.h

@@ -62,7 +62,7 @@
 #define _PAGE_READONLY_EXEC	(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN)
 #define _PAGE_EXECONLY		(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/cpufeature.h>
 #include <asm/pgtable-types.h>
@@ -84,7 +84,7 @@ extern unsigned long prot_ns_shared;
 #else
 static inline bool __pure lpa2_is_enabled(void)
 {
-	return read_tcr() & TCR_DS;
+	return read_tcr() & TCR_EL1_DS;
 }
 
 #define PTE_MAYBE_SHARED	(lpa2_is_enabled() ? 0 : PTE_SHARED)
@@ -127,7 +127,7 @@ static inline bool __pure lpa2_is_enabled(void)
 #define PAGE_READONLY_EXEC	__pgprot(_PAGE_READONLY_EXEC)
 #define PAGE_EXECONLY		__pgprot(_PAGE_EXECONLY)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #define pte_pi_index(pte) ( \
 	((pte & BIT(PTE_PI_IDX_3)) >> (PTE_PI_IDX_3 - 3)) | \

arch/arm64/include/asm/pgtable.h

@@ -30,7 +30,7 @@
 
 #define vmemmap			((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/cmpxchg.h>
 #include <asm/fixmap.h>
@@ -130,12 +130,16 @@ static inline void arch_leave_lazy_mmu_mode(void)
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /*
- * Outside of a few very special situations (e.g. hibernation), we always
+ * We use local TLB invalidation instruction when reusing page in
- * use broadcast TLB invalidation instructions, therefore a spurious page
+ * write protection fault handler to avoid TLBI broadcast in the hot
- * fault on one CPU which has been handled concurrently by another CPU
+ * path.  This will cause spurious page faults if stale read-only TLB
- * does not need to perform additional invalidation.
+ * entries exist.
  */
-#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0)
+#define flush_tlb_fix_spurious_fault(vma, address, ptep)	\
+	local_flush_tlb_page_nonotify(vma, address)
+
+#define flush_tlb_fix_spurious_fault_pmd(vma, address, pmdp)	\
+	local_flush_tlb_page_nonotify(vma, address)
 
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
@@ -433,7 +437,7 @@ bool pgattr_change_is_safe(pteval_t old, pteval_t new);
  *   1      0      |   1           0          1
  *   1      1      |   0           1          x
  *
- * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via
+ * When hardware DBM is not present, the software PTE_DIRTY bit is updated via
  * the page fault mechanism. Checking the dirty status of a pte becomes:
  *
  *   PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY)
@@ -599,7 +603,7 @@ static inline int pte_protnone(pte_t pte)
 	/*
 	 * pte_present_invalid() tells us that the pte is invalid from HW
 	 * perspective but present from SW perspective, so the fields are to be
-	 * interpretted as per the HW layout. The second 2 checks are the unique
+	 * interpreted as per the HW layout. The second 2 checks are the unique
 	 * encoding that we use for PROT_NONE. It is insufficient to only use
 	 * the first check because we share the same encoding scheme with pmds
 	 * which support pmd_mkinvalid(), so can be present-invalid without
@@ -1949,6 +1953,6 @@ static inline void clear_young_dirty_ptes(struct vm_area_struct *vma,
 
 #endif /* CONFIG_ARM64_CONTPTE */
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_PGTABLE_H */

arch/arm64/include/asm/proc-fns.h

@@ -9,7 +9,7 @@
 #ifndef __ASM_PROCFNS_H
 #define __ASM_PROCFNS_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/page.h>
 
@@ -21,5 +21,5 @@ extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
 #include <asm/memory.h>
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_PROCFNS_H */

arch/arm64/include/asm/processor.h

@@ -25,7 +25,7 @@
 
 #define MTE_CTRL_STORE_ONLY		(1UL << 19)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/build_bug.h>
 #include <linux/cache.h>
@@ -437,5 +437,5 @@ int set_tsc_mode(unsigned int val);
 #define GET_TSC_CTL(adr)        get_tsc_mode((adr))
 #define SET_TSC_CTL(val)        set_tsc_mode((val))
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_PROCESSOR_H */

arch/arm64/include/asm/ptrace.h

@@ -94,7 +94,7 @@
  */
 #define NO_SYSCALL (-1)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/bug.h>
 #include <linux/types.h>
 
@@ -361,5 +361,5 @@ static inline void procedure_link_pointer_set(struct pt_regs *regs,
 
 extern unsigned long profile_pc(struct pt_regs *regs);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif

arch/arm64/include/asm/rsi_smc.h

@@ -122,7 +122,7 @@
  */
 #define SMC_RSI_ATTESTATION_TOKEN_CONTINUE	SMC_RSI_FID(0x195)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct realm_config {
 	union {
@@ -142,7 +142,7 @@ struct realm_config {
 	 */
 } __aligned(0x1000);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * Read configuration for the current Realm.

arch/arm64/include/asm/rwonce.h

@@ -5,7 +5,7 @@
 #ifndef __ASM_RWONCE_H
 #define __ASM_RWONCE_H
 
-#if defined(CONFIG_LTO) && !defined(__ASSEMBLY__)
+#if defined(CONFIG_LTO) && !defined(__ASSEMBLER__)
 
 #include <linux/compiler_types.h>
 #include <asm/alternative-macros.h>
@@ -62,7 +62,7 @@
 })
 
 #endif	/* !BUILD_VDSO */
-#endif	/* CONFIG_LTO && !__ASSEMBLY__ */
+#endif	/* CONFIG_LTO && !__ASSEMBLER__ */
 
 #include <asm-generic/rwonce.h>
 

arch/arm64/include/asm/scs.h

@@ -2,7 +2,7 @@
 #ifndef _ASM_SCS_H
 #define _ASM_SCS_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #include <asm/asm-offsets.h>
 #include <asm/sysreg.h>
@@ -55,6 +55,6 @@ enum {
 
 int __pi_scs_patch(const u8 eh_frame[], int size, bool skip_dry_run);
 
-#endif /* __ASSEMBLY __ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_SCS_H */

arch/arm64/include/asm/sdei.h

@@ -9,7 +9,7 @@
 
 #define SDEI_STACK_SIZE		IRQ_STACK_SIZE
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/linkage.h>
 #include <linux/preempt.h>
@@ -49,5 +49,5 @@ unsigned long do_sdei_event(struct pt_regs *regs,
 unsigned long sdei_arch_get_entry_point(int conduit);
 #define sdei_arch_get_entry_point(x)	sdei_arch_get_entry_point(x)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif	/* __ASM_SDEI_H */

arch/arm64/include/asm/simd.h

@@ -29,7 +29,7 @@ static __must_check inline bool may_use_simd(void)
 	 */
 	return !WARN_ON(!system_capabilities_finalized()) &&
 	       system_supports_fpsimd() &&
-	       !in_hardirq() && !irqs_disabled() && !in_nmi();
+	       !in_hardirq() && !in_nmi();
 }
 
 #else /* ! CONFIG_KERNEL_MODE_NEON */

arch/arm64/include/asm/smp.h

@@ -23,7 +23,7 @@
 #define CPU_STUCK_REASON_52_BIT_VA	(UL(1) << CPU_STUCK_REASON_SHIFT)
 #define CPU_STUCK_REASON_NO_GRAN	(UL(2) << CPU_STUCK_REASON_SHIFT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/threads.h>
 #include <linux/cpumask.h>
@@ -155,6 +155,6 @@ bool cpus_are_stuck_in_kernel(void);
 extern void crash_smp_send_stop(void);
 extern bool smp_crash_stop_failed(void);
 
-#endif /* ifndef __ASSEMBLY__ */
+#endif /* ifndef __ASSEMBLER__ */
 
 #endif /* ifndef __ASM_SMP_H */

arch/arm64/include/asm/spectre.h

@@ -12,7 +12,7 @@
 #define BP_HARDEN_EL2_SLOTS 4
 #define __BP_HARDEN_HYP_VECS_SZ	((BP_HARDEN_EL2_SLOTS - 1) * SZ_2K)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/smp.h>
 #include <asm/percpu.h>
 
@@ -119,5 +119,5 @@ void spectre_bhb_patch_clearbhb(struct alt_instr *alt,
 				__le32 *origptr, __le32 *updptr, int nr_inst);
 void spectre_print_disabled_mitigations(void);
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 #endif	/* __ASM_SPECTRE_H */

arch/arm64/include/asm/stacktrace/frame.h

@@ -25,7 +25,7 @@
 #define FRAME_META_TYPE_FINAL		1
 #define FRAME_META_TYPE_PT_REGS		2
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /* 
  * A standard AAPCS64 frame record.
  */
@@ -43,6 +43,6 @@ struct frame_record_meta {
 	struct frame_record record;
 	u64 type;
 };
-#endif /* __ASSEMBLY */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_STACKTRACE_FRAME_H */

arch/arm64/include/asm/suspend.h

@@ -23,7 +23,7 @@ struct cpu_suspend_ctx {
  * __cpu_suspend_enter()'s caller, and populated by __cpu_suspend_enter().
  * This data must survive until cpu_resume() is called.
  *
- * This struct desribes the size and the layout of the saved cpu state.
+ * This struct describes the size and the layout of the saved cpu state.
  * The layout of the callee_saved_regs is defined by the implementation
  * of __cpu_suspend_enter(), and cpu_resume(). This struct must be passed
  * in by the caller as __cpu_suspend_enter()'s stack-frame is gone once it

arch/arm64/include/asm/sysreg.h

@@ -52,7 +52,7 @@
 
 #ifndef CONFIG_BROKEN_GAS_INST
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 // The space separator is omitted so that __emit_inst(x) can be parsed as
 // either an assembler directive or an assembler macro argument.
 #define __emit_inst(x)			.inst(x)
@@ -71,11 +71,11 @@
 					 (((x) >> 24) & 0x000000ff))
 #endif	/* CONFIG_CPU_BIG_ENDIAN */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define __emit_inst(x)			.long __INSTR_BSWAP(x)
-#else  /* __ASSEMBLY__ */
+#else  /* __ASSEMBLER__ */
 #define __emit_inst(x)			".long " __stringify(__INSTR_BSWAP(x)) "\n\t"
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif	/* CONFIG_BROKEN_GAS_INST */
 
@@ -1129,9 +1129,7 @@
 #define gicr_insn(insn)			read_sysreg_s(GICV5_OP_GICR_##insn)
 #define gic_insn(v, insn)		write_sysreg_s(v, GICV5_OP_GIC_##insn)
 
-#define ARM64_FEATURE_FIELD_BITS	4
+#ifdef __ASSEMBLER__
-
-#ifdef __ASSEMBLY__
 
 	.macro	mrs_s, rt, sreg
 	 __emit_inst(0xd5200000|(\sreg)|(.L__gpr_num_\rt))

arch/arm64/include/asm/system_misc.h

@@ -7,7 +7,7 @@
 #ifndef __ASM_SYSTEM_MISC_H
 #define __ASM_SYSTEM_MISC_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/compiler.h>
 #include <linux/linkage.h>
@@ -28,6 +28,6 @@ void arm64_notify_die(const char *str, struct pt_regs *regs,
 struct mm_struct;
 extern void __show_regs(struct pt_regs *);
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif	/* __ASM_SYSTEM_MISC_H */

arch/arm64/include/asm/thread_info.h

@@ -10,7 +10,7 @@
 
 #include <linux/compiler.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct task_struct;
 

arch/arm64/include/asm/tlbflush.h

@@ -8,7 +8,7 @@
 #ifndef __ASM_TLBFLUSH_H
 #define __ASM_TLBFLUSH_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/bitfield.h>
 #include <linux/mm_types.h>
@@ -249,6 +249,19 @@ static inline unsigned long get_trans_granule(void)
  *		cannot be easily determined, the value TLBI_TTL_UNKNOWN will
  *		perform a non-hinted invalidation.
  *
+ *	local_flush_tlb_page(vma, addr)
+ *		Local variant of flush_tlb_page().  Stale TLB entries may
+ *		remain in remote CPUs.
+ *
+ *	local_flush_tlb_page_nonotify(vma, addr)
+ *		Same as local_flush_tlb_page() except MMU notifier will not be
+ *		called.
+ *
+ *	local_flush_tlb_contpte(vma, addr)
+ *		Invalidate the virtual-address range
+ *		'[addr, addr+CONT_PTE_SIZE)' mapped with contpte on local CPU
+ *		for the user address space corresponding to 'vma->mm'.  Stale
+ *		TLB entries may remain in remote CPUs.
  *
  *	Finally, take a look at asm/tlb.h to see how tlb_flush() is implemented
  *	on top of these routines, since that is our interface to the mmu_gather
@@ -282,6 +295,33 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 
+static inline void __local_flush_tlb_page_nonotify_nosync(struct mm_struct *mm,
+							  unsigned long uaddr)
+{
+	unsigned long addr;
+
+	dsb(nshst);
+	addr = __TLBI_VADDR(uaddr, ASID(mm));
+	__tlbi(vale1, addr);
+	__tlbi_user(vale1, addr);
+}
+
+static inline void local_flush_tlb_page_nonotify(struct vm_area_struct *vma,
+						 unsigned long uaddr)
+{
+	__local_flush_tlb_page_nonotify_nosync(vma->vm_mm, uaddr);
+	dsb(nsh);
+}
+
+static inline void local_flush_tlb_page(struct vm_area_struct *vma,
+					unsigned long uaddr)
+{
+	__local_flush_tlb_page_nonotify_nosync(vma->vm_mm, uaddr);
+	mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, uaddr & PAGE_MASK,
+						(uaddr & PAGE_MASK) + PAGE_SIZE);
+	dsb(nsh);
+}
+
 static inline void __flush_tlb_page_nosync(struct mm_struct *mm,
 					   unsigned long uaddr)
 {
@@ -472,6 +512,22 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 	dsb(ish);
 }
 
+static inline void local_flush_tlb_contpte(struct vm_area_struct *vma,
+					   unsigned long addr)
+{
+	unsigned long asid;
+
+	addr = round_down(addr, CONT_PTE_SIZE);
+
+	dsb(nshst);
+	asid = ASID(vma->vm_mm);
+	__flush_tlb_range_op(vale1, addr, CONT_PTES, PAGE_SIZE, asid,
+			     3, true, lpa2_is_enabled());
+	mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, addr,
+						    addr + CONT_PTE_SIZE);
+	dsb(nsh);
+}
+
 static inline void flush_tlb_range(struct vm_area_struct *vma,
 				   unsigned long start, unsigned long end)
 {
@@ -524,6 +580,33 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b
 {
 	__flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
 }
+
+static inline bool __pte_flags_need_flush(ptdesc_t oldval, ptdesc_t newval)
+{
+	ptdesc_t diff = oldval ^ newval;
+
+	/* invalid to valid transition requires no flush */
+	if (!(oldval & PTE_VALID))
+		return false;
+
+	/* Transition in the SW bits requires no flush */
+	diff &= ~PTE_SWBITS_MASK;
+
+	return diff;
+}
+
+static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
+{
+	return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte));
+}
+#define pte_needs_flush pte_needs_flush
+
+static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
+{
+	return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd));
+}
+#define huge_pmd_needs_flush huge_pmd_needs_flush
+
 #endif
 
 #endif

arch/arm64/include/asm/vdso.h

@@ -7,7 +7,7 @@
 
 #define __VDSO_PAGES    4
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <generated/vdso-offsets.h>
 
@@ -19,6 +19,6 @@
 extern char vdso_start[], vdso_end[];
 extern char vdso32_start[], vdso32_end[];
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_H */

arch/arm64/include/asm/vdso/compat_barrier.h

@@ -5,7 +5,7 @@
 #ifndef __COMPAT_BARRIER_H
 #define __COMPAT_BARRIER_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * Warning: This code is meant to be used from the compat vDSO only.
  */
@@ -31,6 +31,6 @@
 #define smp_rmb()	aarch32_smp_rmb()
 #define smp_wmb()	aarch32_smp_wmb()
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __COMPAT_BARRIER_H */

arch/arm64/include/asm/vdso/compat_gettimeofday.h

@@ -5,7 +5,7 @@
 #ifndef __ASM_VDSO_COMPAT_GETTIMEOFDAY_H
 #define __ASM_VDSO_COMPAT_GETTIMEOFDAY_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/barrier.h>
 #include <asm/unistd_compat_32.h>
@@ -161,6 +161,6 @@ static inline bool vdso_clocksource_ok(const struct vdso_clock *vc)
 }
 #define vdso_clocksource_ok	vdso_clocksource_ok
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_COMPAT_GETTIMEOFDAY_H */

arch/arm64/include/asm/vdso/getrandom.h

@@ -3,7 +3,7 @@
 #ifndef __ASM_VDSO_GETRANDOM_H
 #define __ASM_VDSO_GETRANDOM_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/unistd.h>
 #include <asm/vdso/vsyscall.h>
@@ -33,6 +33,6 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns
 	return ret;
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */

arch/arm64/include/asm/vdso/gettimeofday.h

@@ -7,7 +7,7 @@
 
 #ifdef __aarch64__
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/alternative.h>
 #include <asm/arch_timer.h>
@@ -96,7 +96,7 @@ static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(
 #define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data
 #endif /* IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB) */
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #else /* !__aarch64__ */
 

arch/arm64/include/asm/vdso/processor.h

@@ -5,13 +5,13 @@
 #ifndef __ASM_VDSO_PROCESSOR_H
 #define __ASM_VDSO_PROCESSOR_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 static inline void cpu_relax(void)
 {
 	asm volatile("yield" ::: "memory");
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_PROCESSOR_H */

arch/arm64/include/asm/vdso/vsyscall.h

@@ -2,7 +2,7 @@
 #ifndef __ASM_VDSO_VSYSCALL_H
 #define __ASM_VDSO_VSYSCALL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <vdso/datapage.h>
 
@@ -22,6 +22,6 @@ void __arch_update_vdso_clock(struct vdso_clock *vc)
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_VSYSCALL_H */

arch/arm64/include/asm/virt.h

@@ -56,7 +56,7 @@
  */
 #define BOOT_CPU_FLAG_E2H	BIT_ULL(32)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/ptrace.h>
 #include <asm/sections.h>
@@ -161,6 +161,6 @@ static inline bool is_hyp_nvhe(void)
 	return is_hyp_mode_available() && !is_kernel_in_hyp_mode();
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* ! __ASM__VIRT_H */

arch/arm64/include/asm/vmap_stack.h

@@ -3,9 +3,7 @@
 #ifndef __ASM_VMAP_STACK_H
 #define __ASM_VMAP_STACK_H
 
-#include <linux/bug.h>
 #include <linux/gfp.h>
-#include <linux/kconfig.h>
 #include <linux/vmalloc.h>
 #include <linux/pgtable.h>
 #include <asm/memory.h>
@@ -19,8 +17,6 @@ static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node)
 {
 	void *p;
 
-	BUILD_BUG_ON(!IS_ENABLED(CONFIG_VMAP_STACK));
-
 	p = __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node,
 			__builtin_return_address(0));
 	return kasan_reset_tag(p);

arch/arm64/include/uapi/asm/kvm.h

@@ -31,7 +31,7 @@
 #define KVM_SPSR_FIQ	4
 #define KVM_NR_SPSR	5
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/psci.h>
 #include <linux/types.h>
 #include <asm/ptrace.h>

arch/arm64/include/uapi/asm/ptrace.h

@@ -80,7 +80,7 @@
 #define PTRACE_PEEKMTETAGS	  33
 #define PTRACE_POKEMTETAGS	  34
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * User structures for general purpose, floating point and debug registers.
@@ -332,6 +332,6 @@ struct user_gcs {
 	__u64 gcspr_el0;
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _UAPI__ASM_PTRACE_H */

arch/arm64/include/uapi/asm/sigcontext.h

@@ -17,7 +17,7 @@
 #ifndef _UAPI__ASM_SIGCONTEXT_H
 #define _UAPI__ASM_SIGCONTEXT_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -192,7 +192,7 @@ struct gcs_context {
 	__u64 reserved;
 };
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #include <asm/sve_context.h>
 

arch/arm64/kernel/acpi.c

@@ -133,7 +133,7 @@ static int __init acpi_fadt_sanity_check(void)
 
 	/*
 	 * FADT is required on arm64; retrieve it to check its presence
-	 * and carry out revision and ACPI HW reduced compliancy tests
+	 * and carry out revision and ACPI HW reduced compliance tests
 	 */
 	status = acpi_get_table(ACPI_SIG_FADT, 0, &table);
 	if (ACPI_FAILURE(status)) {
@@ -423,7 +423,7 @@ int apei_claim_sea(struct pt_regs *regs)
 			irq_work_run();
 			__irq_exit();
 		} else {
-			pr_warn_ratelimited("APEI work queued but not completed");
+			pr_warn_ratelimited("APEI work queued but not completed\n");
 			err = -EINPROGRESS;
 		}
 	}

arch/arm64/kernel/cpufeature.c

@@ -1003,7 +1003,7 @@ static void __init sort_ftr_regs(void)
 
 /*
  * Initialise the CPU feature register from Boot CPU values.
- * Also initiliases the strict_mask for the register.
+ * Also initialises the strict_mask for the register.
  * Any bits that are not covered by an arm64_ftr_bits entry are considered
  * RES0 for the system-wide value, and must strictly match.
  */
@@ -1970,7 +1970,7 @@ static struct cpumask dbm_cpus __read_mostly;
 
 static inline void __cpu_enable_hw_dbm(void)
 {
-	u64 tcr = read_sysreg(tcr_el1) | TCR_HD;
+	u64 tcr = read_sysreg(tcr_el1) | TCR_EL1_HD;
 
 	write_sysreg(tcr, tcr_el1);
 	isb();
@@ -2256,7 +2256,7 @@ static bool has_generic_auth(const struct arm64_cpu_capabilities *entry,
 static void cpu_enable_e0pd(struct arm64_cpu_capabilities const *cap)
 {
 	if (this_cpu_has_cap(ARM64_HAS_E0PD))
-		sysreg_clear_set(tcr_el1, 0, TCR_E0PD1);
+		sysreg_clear_set(tcr_el1, 0, TCR_EL1_E0PD1);
 }
 #endif /* CONFIG_ARM64_E0PD */
 

arch/arm64/kernel/efi.c

@@ -10,6 +10,7 @@
 #include <linux/efi.h>
 #include <linux/init.h>
 #include <linux/kmemleak.h>
+#include <linux/kthread.h>
 #include <linux/screen_info.h>
 #include <linux/vmalloc.h>
 
@@ -165,20 +166,53 @@ asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f)
 	return s;
 }
 
-static DEFINE_RAW_SPINLOCK(efi_rt_lock);
-
 void arch_efi_call_virt_setup(void)
 {
-	efi_virtmap_load();
+	efi_runtime_assert_lock_held();
-	raw_spin_lock(&efi_rt_lock);
+
+	if (preemptible() && (current->flags & PF_KTHREAD)) {
+		/*
+		 * Disable migration to ensure that a preempted EFI runtime
+		 * service call will be resumed on the same CPU. This avoids
+		 * potential issues with EFI runtime calls that are preempted
+		 * while polling for an asynchronous completion of a secure
+		 * firmware call, which may not permit the CPU to change.
+		 */
+		migrate_disable();
+		kthread_use_mm(&efi_mm);
+	} else {
+		efi_virtmap_load();
+	}
+
+	/*
+	 * Enable access to the valid TTBR0_EL1 and invoke the errata
+	 * workaround directly since there is no return from exception when
+	 * invoking the EFI run-time services.
+	 */
+	uaccess_ttbr0_enable();
+	post_ttbr_update_workaround();
+
 	__efi_fpsimd_begin();
 }
 
 void arch_efi_call_virt_teardown(void)
 {
 	__efi_fpsimd_end();
-	raw_spin_unlock(&efi_rt_lock);
+
-	efi_virtmap_unload();
+	/*
+	 * Defer the switch to the current thread's TTBR0_EL1 until
+	 * uaccess_enable(). Do so before efi_virtmap_unload() updates the
+	 * saved TTBR0 value, so the userland page tables are not activated
+	 * inadvertently over the back of an exception.
+	 */
+	uaccess_ttbr0_disable();
+
+	if (preemptible() && (current->flags & PF_KTHREAD)) {
+		kthread_unuse_mm(&efi_mm);
+		migrate_enable();
+	} else {
+		efi_virtmap_unload();
+	}
 }
 
 asmlinkage u64 *efi_rt_stack_top __ro_after_init;

arch/arm64/kernel/entry-common.c

@@ -34,20 +34,12 @@
  * Handle IRQ/context state management when entering from kernel mode.
  * Before this function is called it is not safe to call regular kernel code,
  * instrumentable code, or any code which may trigger an exception.
- *
- * This is intended to match the logic in irqentry_enter(), handling the kernel
- * mode transitions only.
  */
-static __always_inline irqentry_state_t __enter_from_kernel_mode(struct pt_regs *regs)
-{
-	return irqentry_enter(regs);
-}
-
 static noinstr irqentry_state_t enter_from_kernel_mode(struct pt_regs *regs)
 {
 	irqentry_state_t state;
 
-	state = __enter_from_kernel_mode(regs);
+	state = irqentry_enter(regs);
 	mte_check_tfsr_entry();
 	mte_disable_tco_entry(current);
 
@@ -58,21 +50,12 @@ static noinstr irqentry_state_t enter_from_kernel_mode(struct pt_regs *regs)
  * Handle IRQ/context state management when exiting to kernel mode.
  * After this function returns it is not safe to call regular kernel code,
  * instrumentable code, or any code which may trigger an exception.
- *
- * This is intended to match the logic in irqentry_exit(), handling the kernel
- * mode transitions only, and with preemption handled elsewhere.
  */
-static __always_inline void __exit_to_kernel_mode(struct pt_regs *regs,
-						  irqentry_state_t state)
-{
-	irqentry_exit(regs, state);
-}
-
 static void noinstr exit_to_kernel_mode(struct pt_regs *regs,
 					irqentry_state_t state)
 {
 	mte_check_tfsr_exit();
-	__exit_to_kernel_mode(regs, state);
+	irqentry_exit(regs, state);
 }
 
 /*
@@ -80,17 +63,12 @@ static void noinstr exit_to_kernel_mode(struct pt_regs *regs,
  * Before this function is called it is not safe to call regular kernel code,
  * instrumentable code, or any code which may trigger an exception.
  */
-static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
+static __always_inline void arm64_enter_from_user_mode(struct pt_regs *regs)
 {
 	enter_from_user_mode(regs);
 	mte_disable_tco_entry(current);
 }
 
-static __always_inline void arm64_enter_from_user_mode(struct pt_regs *regs)
-{
-	__enter_from_user_mode(regs);
-}
-
 /*
  * Handle IRQ/context state management when exiting to user mode.
  * After this function returns it is not safe to call regular kernel code,

arch/arm64/kernel/entry-ftrace.S

@@ -94,7 +94,7 @@ SYM_CODE_START(ftrace_caller)
 	stp	x29, x30, [sp, #FREGS_SIZE]
 	add	x29, sp, #FREGS_SIZE
 
-	/* Prepare arguments for the the tracer func */
+	/* Prepare arguments for the tracer func */
 	sub	x0, x30, #AARCH64_INSN_SIZE		// ip (callsite's BL insn)
 	mov	x1, x9					// parent_ip (callsite's LR)
 	mov	x3, sp					// regs

arch/arm64/kernel/fpsimd.c

@@ -225,10 +225,21 @@ static void fpsimd_bind_task_to_cpu(void);
  */
 static void get_cpu_fpsimd_context(void)
 {
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
-		local_bh_disable();
+		/*
-	else
+		 * The softirq subsystem lacks a true unmask/mask API, and
+		 * re-enabling softirq processing using local_bh_enable() will
+		 * not only unmask softirqs, it will also result in immediate
+		 * delivery of any pending softirqs.
+		 * This is undesirable when running with IRQs disabled, but in
+		 * that case, there is no need to mask softirqs in the first
+		 * place, so only bother doing so when IRQs are enabled.
+		 */
+		if (!irqs_disabled())
+			local_bh_disable();
+	} else {
 		preempt_disable();
+	}
 }
 
 /*
@@ -240,10 +251,12 @@ static void get_cpu_fpsimd_context(void)
  */
 static void put_cpu_fpsimd_context(void)
 {
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
-		local_bh_enable();
+		if (!irqs_disabled())
-	else
+			local_bh_enable();
+	} else {
 		preempt_enable();
+	}
 }
 
 unsigned int task_get_vl(const struct task_struct *task, enum vec_type type)
@@ -1934,11 +1947,11 @@ void __efi_fpsimd_begin(void)
 	if (!system_supports_fpsimd())
 		return;
 
-	WARN_ON(preemptible());
-
 	if (may_use_simd()) {
 		kernel_neon_begin();
 	} else {
+		WARN_ON(preemptible());
+
 		/*
 		 * If !efi_sve_state, SVE can't be in use yet and doesn't need
 		 * preserving:

arch/arm64/kernel/ftrace.c

@@ -492,7 +492,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 		return ret;
 
 	/*
-	 * When using mcount, callsites in modules may have been initalized to
+	 * When using mcount, callsites in modules may have been initialized to
 	 * call an arbitrary module PLT (which redirects to the _mcount stub)
 	 * rather than the ftrace PLT we'll use at runtime (which redirects to
 	 * the ftrace trampoline). We can ignore the old PLT when initializing

arch/arm64/kernel/irq.c

@@ -62,7 +62,7 @@ static void __init init_irq_stacks(void)
 	}
 }
 
-#ifndef CONFIG_PREEMPT_RT
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
 static void ____do_softirq(struct pt_regs *regs)
 {
 	__do_softirq();

arch/arm64/kernel/machine_kexec.c

@@ -251,7 +251,7 @@ void crash_post_resume(void)
  * marked as Reserved as memory was allocated via memblock_reserve().
  *
  * In hibernation, the pages which are Reserved and yet "nosave" are excluded
- * from the hibernation iamge. crash_is_nosave() does thich check for crash
+ * from the hibernation image. crash_is_nosave() does thich check for crash
  * dump kernel and will reduce the total size of hibernation image.
  */
 

arch/arm64/kernel/pi/map_kernel.c

@@ -141,13 +141,13 @@ static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level)
 static void noinline __section(".idmap.text") set_ttbr0_for_lpa2(phys_addr_t ttbr)
 {
 	u64 sctlr = read_sysreg(sctlr_el1);
-	u64 tcr = read_sysreg(tcr_el1) | TCR_DS;
+	u64 tcr = read_sysreg(tcr_el1) | TCR_EL1_DS;
 	u64 mmfr0 = read_sysreg(id_aa64mmfr0_el1);
 	u64 parange = cpuid_feature_extract_unsigned_field(mmfr0,
 							   ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 
-	tcr &= ~TCR_IPS_MASK;
+	tcr &= ~TCR_EL1_IPS_MASK;
-	tcr |= parange << TCR_IPS_SHIFT;
+	tcr |= parange << TCR_EL1_IPS_SHIFT;
 
 	asm("	msr	sctlr_el1, %0		;"
 	    "	isb				;"
@@ -263,7 +263,7 @@ asmlinkage void __init early_map_kernel(u64 boot_status, phys_addr_t fdt)
 	}
 
 	if (va_bits > VA_BITS_MIN)
-		sysreg_clear_set(tcr_el1, TCR_T1SZ_MASK, TCR_T1SZ(va_bits));
+		sysreg_clear_set(tcr_el1, TCR_EL1_T1SZ_MASK, TCR_T1SZ(va_bits));
 
 	/*
 	 * The virtual KASLR displacement modulo 2MiB is decided by the

arch/arm64/kernel/probes/uprobes.c

@@ -131,7 +131,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	struct uprobe_task *utask = current->utask;
 
 	/*
-	 * Task has received a fatal signal, so reset back to probbed
+	 * Task has received a fatal signal, so reset back to probed
 	 * address.
 	 */
 	instruction_pointer_set(regs, utask->vaddr);

arch/arm64/kernel/ptrace.c

@@ -912,13 +912,39 @@ static int sve_set_common(struct task_struct *target,
 		return -EINVAL;
 
 	/*
-	 * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by
+	 * On systems without SVE we accept FPSIMD format writes with
-	 * vec_set_vector_length(), which will also validate them for us:
+	 * a VL of 0 to allow exiting streaming mode, otherwise a VL
+	 * is required.
 	 */
-	ret = vec_set_vector_length(target, type, header.vl,
+	if (header.vl) {
-		((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16);
+		/*
-	if (ret)
+		 * If the system does not support SVE we can't
-		return ret;
+		 * configure a SVE VL.
+		 */
+		if (!system_supports_sve() && type == ARM64_VEC_SVE)
+			return -EINVAL;
+
+		/*
+		 * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are
+		 * consumed by vec_set_vector_length(), which will
+		 * also validate them for us:
+		 */
+		ret = vec_set_vector_length(target, type, header.vl,
+					    ((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16);
+		if (ret)
+			return ret;
+	} else {
+		/* If the system supports SVE we require a VL. */
+		if (system_supports_sve())
+			return -EINVAL;
+
+		/*
+		 * Only FPSIMD formatted data with no flags set is
+		 * supported.
+		 */
+		if (header.flags != SVE_PT_REGS_FPSIMD)
+			return -EINVAL;
+	}
 
 	/* Allocate SME storage if necessary, preserving any existing ZA/ZT state */
 	if (type == ARM64_VEC_SME) {
@@ -1016,7 +1042,7 @@ static int sve_set(struct task_struct *target,
 		   unsigned int pos, unsigned int count,
 		   const void *kbuf, const void __user *ubuf)
 {
-	if (!system_supports_sve())
+	if (!system_supports_sve() && !system_supports_sme())
 		return -EINVAL;
 
 	return sve_set_common(target, regset, pos, count, kbuf, ubuf,

arch/arm64/kernel/sdei.c

@@ -63,8 +63,6 @@ static void free_sdei_stacks(void)
 {
 	int cpu;
 
-	BUILD_BUG_ON(!IS_ENABLED(CONFIG_VMAP_STACK));
-
 	for_each_possible_cpu(cpu) {
 		_free_sdei_stack(&sdei_stack_normal_ptr, cpu);
 		_free_sdei_stack(&sdei_stack_critical_ptr, cpu);
@@ -88,8 +86,6 @@ static int init_sdei_stacks(void)
 	int cpu;
 	int err = 0;
 
-	BUILD_BUG_ON(!IS_ENABLED(CONFIG_VMAP_STACK));
-
 	for_each_possible_cpu(cpu) {
 		err = _init_sdei_stack(&sdei_stack_normal_ptr, cpu);
 		if (err)
@@ -202,7 +198,7 @@ unsigned long sdei_arch_get_entry_point(int conduit)
 /*
  * do_sdei_event() returns one of:
  *  SDEI_EV_HANDLED -  success, return to the interrupted context.
- *  SDEI_EV_FAILED  -  failure, return this error code to firmare.
+ *  SDEI_EV_FAILED  -  failure, return this error code to firmware.
  *  virtual-address -  success, return to this address.
  */
 unsigned long __kprobes do_sdei_event(struct pt_regs *regs,

arch/arm64/kernel/smp.c

@@ -350,7 +350,7 @@ void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
 
 	/*
 	 * Now that the dying CPU is beyond the point of no return w.r.t.
-	 * in-kernel synchronisation, try to get the firwmare to help us to
+	 * in-kernel synchronisation, try to get the firmware to help us to
 	 * verify that it has really left the kernel before we consider
 	 * clobbering anything it might still be using.
 	 */
@@ -523,7 +523,7 @@ int arch_register_cpu(int cpu)
 
 	/*
 	 * Availability of the acpi handle is sufficient to establish
-	 * that _STA has aleady been checked. No need to recheck here.
+	 * that _STA has already been checked. No need to recheck here.
 	 */
 	c->hotpluggable = arch_cpu_is_hotpluggable(cpu);
 

arch/arm64/kernel/syscall.c

@@ -96,7 +96,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	 * (Similarly for HVC and SMC elsewhere.)
 	 */
 
-	if (flags & _TIF_MTE_ASYNC_FAULT) {
+	if (unlikely(flags & _TIF_MTE_ASYNC_FAULT)) {
 		/*
 		 * Process the asynchronous tag check fault before the actual
 		 * syscall. do_notify_resume() will send a signal to userspace

arch/arm64/kernel/traps.c

@@ -922,7 +922,7 @@ void __noreturn panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigne
 	__show_regs(regs);
 
 	/*
-	 * We use nmi_panic to limit the potential for recusive overflows, and
+	 * We use nmi_panic to limit the potential for recursive overflows, and
 	 * to get a better stack trace.
 	 */
 	nmi_panic(NULL, "kernel stack overflow");

arch/arm64/kernel/vmcore_info.c

@@ -14,7 +14,7 @@ static inline u64 get_tcr_el1_t1sz(void);
 
 static inline u64 get_tcr_el1_t1sz(void)
 {
-	return (read_sysreg(tcr_el1) & TCR_T1SZ_MASK) >> TCR_T1SZ_OFFSET;
+	return (read_sysreg(tcr_el1) & TCR_EL1_T1SZ_MASK) >> TCR_EL1_T1SZ_SHIFT;
 }
 
 void arch_crash_save_vmcoreinfo(void)

arch/arm64/kvm/arch_timer.c

@@ -806,7 +806,7 @@ static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map)
 		tpt = tpc = true;
 
 	/*
-	 * For the poor sods that could not correctly substract one value
+	 * For the poor sods that could not correctly subtract one value
 	 * from another, trap the full virtual timer and counter.
 	 */
 	if (has_broken_cntvoff() && timer_get_offset(map->direct_vtimer))

arch/arm64/kvm/arm.c

@@ -2448,7 +2448,7 @@ static void kvm_hyp_init_symbols(void)
 	kvm_nvhe_sym(__icache_flags) = __icache_flags;
 	kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits;
 
-	/* Propagate the FGT state to the the nVHE side */
+	/* Propagate the FGT state to the nVHE side */
 	kvm_nvhe_sym(hfgrtr_masks)  = hfgrtr_masks;
 	kvm_nvhe_sym(hfgwtr_masks)  = hfgwtr_masks;
 	kvm_nvhe_sym(hfgitr_masks)  = hfgitr_masks;

arch/arm64/kvm/hyp/nvhe/ffa.c

@@ -115,7 +115,7 @@ static void ffa_set_retval(struct kvm_cpu_context *ctxt,
 	 *
 	 * FFA-1.3 introduces 64-bit variants of the CPU cycle management
 	 * interfaces. Moreover, FF-A 1.3 clarifies that SMC32 direct requests
-	 * complete with SMC32 direct reponses which *should* allow us use the
+	 * complete with SMC32 direct responses which *should* allow us use the
 	 * function ID sent by the caller to determine whether to return x8-x17.
 	 *
 	 * Note that we also cannot rely on function IDs in the response.

arch/arm64/kvm/mmu.c

@@ -1755,7 +1755,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 	/*
 	 * Check if this is non-struct page memory PFN, and cannot support
-	 * CMOs. It could potentially be unsafe to access as cachable.
+	 * CMOs. It could potentially be unsafe to access as cacheable.
 	 */
 	if (vm_flags & (VM_PFNMAP | VM_MIXEDMAP) && !pfn_is_map_memory(pfn)) {
 		if (is_vma_cacheable) {

arch/arm64/kvm/nested.c

@@ -85,7 +85,7 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
 	/*
 	 * Let's treat memory allocation failures as benign: If we fail to
 	 * allocate anything, return an error and keep the allocated array
-	 * alive. Userspace may try to recover by intializing the vcpu
+	 * alive. Userspace may try to recover by initializing the vcpu
 	 * again, and there is no reason to affect the whole VM for this.
 	 */
 	num_mmus = atomic_read(&kvm->online_vcpus) * S2_MMU_PER_VCPU;

arch/arm64/mm/contpte.c

@@ -622,8 +622,7 @@ int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
 			__ptep_set_access_flags(vma, addr, ptep, entry, 0);
 
 		if (dirty)
-			__flush_tlb_range(vma, start_addr, addr,
+			local_flush_tlb_contpte(vma, start_addr);
-							PAGE_SIZE, true, 3);
 	} else {
 		__contpte_try_unfold(vma->vm_mm, addr, ptep, orig_pte);
 		__ptep_set_access_flags(vma, addr, ptep, entry, dirty);

arch/arm64/mm/fault.c

@@ -233,9 +233,13 @@ int __ptep_set_access_flags(struct vm_area_struct *vma,
 		pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
 	} while (pteval != old_pteval);
 
-	/* Invalidate a stale read-only entry */
+	/*
+	 * Invalidate the local stale read-only entry.  Remote stale entries
+	 * may still cause page faults and be invalidated via
+	 * flush_tlb_fix_spurious_fault().
+	 */
 	if (dirty)
-		flush_tlb_page(vma, address);
+		local_flush_tlb_page(vma, address);
 	return 1;
 }
 

arch/arm64/mm/mmu.c

@@ -49,6 +49,8 @@
 #define NO_CONT_MAPPINGS	BIT(1)
 #define NO_EXEC_MAPPINGS	BIT(2)	/* assumes FEAT_HPDS is not used */
 
+#define INVALID_PHYS_ADDR	(-1ULL)
+
 DEFINE_STATIC_KEY_FALSE(arm64_ptdump_lock_key);
 
 u64 kimage_voffset __ro_after_init;
@@ -194,11 +196,11 @@ static void init_pte(pte_t *ptep, unsigned long addr, unsigned long end,
 	} while (ptep++, addr += PAGE_SIZE, addr != end);
 }
 
-static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
+static int alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
-				unsigned long end, phys_addr_t phys,
+			       unsigned long end, phys_addr_t phys,
-				pgprot_t prot,
+			       pgprot_t prot,
-				phys_addr_t (*pgtable_alloc)(enum pgtable_type),
+			       phys_addr_t (*pgtable_alloc)(enum pgtable_type),
-				int flags)
+			       int flags)
 {
 	unsigned long next;
 	pmd_t pmd = READ_ONCE(*pmdp);
@@ -213,6 +215,8 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 			pmdval |= PMD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		pte_phys = pgtable_alloc(TABLE_PTE);
+		if (pte_phys == INVALID_PHYS_ADDR)
+			return -ENOMEM;
 		ptep = pte_set_fixmap(pte_phys);
 		init_clear_pgtable(ptep);
 		ptep += pte_index(addr);
@@ -244,11 +248,13 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 	 * walker.
 	 */
 	pte_clear_fixmap();
+
+	return 0;
 }
 
-static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end,
+static int init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end,
-		     phys_addr_t phys, pgprot_t prot,
+		    phys_addr_t phys, pgprot_t prot,
-		     phys_addr_t (*pgtable_alloc)(enum pgtable_type), int flags)
+		    phys_addr_t (*pgtable_alloc)(enum pgtable_type), int flags)
 {
 	unsigned long next;
 
@@ -269,22 +275,29 @@ static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end,
 			BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd),
 						      READ_ONCE(pmd_val(*pmdp))));
 		} else {
-			alloc_init_cont_pte(pmdp, addr, next, phys, prot,
+			int ret;
-					    pgtable_alloc, flags);
+
+			ret = alloc_init_cont_pte(pmdp, addr, next, phys, prot,
+						  pgtable_alloc, flags);
+			if (ret)
+				return ret;
 
 			BUG_ON(pmd_val(old_pmd) != 0 &&
 			       pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp)));
 		}
 		phys += next - addr;
 	} while (pmdp++, addr = next, addr != end);
+
+	return 0;
 }
 
-static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
+static int alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
-				unsigned long end, phys_addr_t phys,
+			       unsigned long end, phys_addr_t phys,
-				pgprot_t prot,
+			       pgprot_t prot,
-				phys_addr_t (*pgtable_alloc)(enum pgtable_type),
+			       phys_addr_t (*pgtable_alloc)(enum pgtable_type),
-				int flags)
+			       int flags)
 {
+	int ret;
 	unsigned long next;
 	pud_t pud = READ_ONCE(*pudp);
 	pmd_t *pmdp;
@@ -301,6 +314,8 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 			pudval |= PUD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		pmd_phys = pgtable_alloc(TABLE_PMD);
+		if (pmd_phys == INVALID_PHYS_ADDR)
+			return -ENOMEM;
 		pmdp = pmd_set_fixmap(pmd_phys);
 		init_clear_pgtable(pmdp);
 		pmdp += pmd_index(addr);
@@ -320,20 +335,26 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags);
+		ret = init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags);
+		if (ret)
+			goto out;
 
 		pmdp += pmd_index(next) - pmd_index(addr);
 		phys += next - addr;
 	} while (addr = next, addr != end);
 
+out:
 	pmd_clear_fixmap();
+
+	return ret;
 }
 
-static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
+static int alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
-			   phys_addr_t phys, pgprot_t prot,
+			  phys_addr_t phys, pgprot_t prot,
-			   phys_addr_t (*pgtable_alloc)(enum pgtable_type),
+			  phys_addr_t (*pgtable_alloc)(enum pgtable_type),
-			   int flags)
+			  int flags)
 {
+	int ret = 0;
 	unsigned long next;
 	p4d_t p4d = READ_ONCE(*p4dp);
 	pud_t *pudp;
@@ -346,6 +367,8 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
 			p4dval |= P4D_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		pud_phys = pgtable_alloc(TABLE_PUD);
+		if (pud_phys == INVALID_PHYS_ADDR)
+			return -ENOMEM;
 		pudp = pud_set_fixmap(pud_phys);
 		init_clear_pgtable(pudp);
 		pudp += pud_index(addr);
@@ -375,8 +398,10 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
 			BUG_ON(!pgattr_change_is_safe(pud_val(old_pud),
 						      READ_ONCE(pud_val(*pudp))));
 		} else {
-			alloc_init_cont_pmd(pudp, addr, next, phys, prot,
+			ret = alloc_init_cont_pmd(pudp, addr, next, phys, prot,
-					    pgtable_alloc, flags);
+						  pgtable_alloc, flags);
+			if (ret)
+				goto out;
 
 			BUG_ON(pud_val(old_pud) != 0 &&
 			       pud_val(old_pud) != READ_ONCE(pud_val(*pudp)));
@@ -384,14 +409,18 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
 		phys += next - addr;
 	} while (pudp++, addr = next, addr != end);
 
+out:
 	pud_clear_fixmap();
+
+	return ret;
 }
 
-static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
+static int alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
-			   phys_addr_t phys, pgprot_t prot,
+			  phys_addr_t phys, pgprot_t prot,
-			   phys_addr_t (*pgtable_alloc)(enum pgtable_type),
+			  phys_addr_t (*pgtable_alloc)(enum pgtable_type),
-			   int flags)
+			  int flags)
 {
+	int ret;
 	unsigned long next;
 	pgd_t pgd = READ_ONCE(*pgdp);
 	p4d_t *p4dp;
@@ -404,6 +433,8 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
 			pgdval |= PGD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		p4d_phys = pgtable_alloc(TABLE_P4D);
+		if (p4d_phys == INVALID_PHYS_ADDR)
+			return -ENOMEM;
 		p4dp = p4d_set_fixmap(p4d_phys);
 		init_clear_pgtable(p4dp);
 		p4dp += p4d_index(addr);
@@ -418,8 +449,10 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
 
 		next = p4d_addr_end(addr, end);
 
-		alloc_init_pud(p4dp, addr, next, phys, prot,
+		ret = alloc_init_pud(p4dp, addr, next, phys, prot,
-			       pgtable_alloc, flags);
+				     pgtable_alloc, flags);
+		if (ret)
+			goto out;
 
 		BUG_ON(p4d_val(old_p4d) != 0 &&
 		       p4d_val(old_p4d) != READ_ONCE(p4d_val(*p4dp)));
@@ -427,15 +460,19 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
 		phys += next - addr;
 	} while (p4dp++, addr = next, addr != end);
 
+out:
 	p4d_clear_fixmap();
+
+	return ret;
 }
 
-static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys,
+static int __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys,
-					unsigned long virt, phys_addr_t size,
+				       unsigned long virt, phys_addr_t size,
-					pgprot_t prot,
+				       pgprot_t prot,
-					phys_addr_t (*pgtable_alloc)(enum pgtable_type),
+				       phys_addr_t (*pgtable_alloc)(enum pgtable_type),
-					int flags)
+				       int flags)
 {
+	int ret;
 	unsigned long addr, end, next;
 	pgd_t *pgdp = pgd_offset_pgd(pgdir, virt);
 
@@ -444,7 +481,7 @@ static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys,
 	 * within a page, we cannot map the region as the caller expects.
 	 */
 	if (WARN_ON((phys ^ virt) & ~PAGE_MASK))
-		return;
+		return -EINVAL;
 
 	phys &= PAGE_MASK;
 	addr = virt & PAGE_MASK;
@@ -452,25 +489,45 @@ static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys,
 
 	do {
 		next = pgd_addr_end(addr, end);
-		alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc,
+		ret = alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc,
-			       flags);
+				     flags);
+		if (ret)
+			return ret;
 		phys += next - addr;
 	} while (pgdp++, addr = next, addr != end);
+
+	return 0;
 }
 
-static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
+static int __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
-				 unsigned long virt, phys_addr_t size,
+				unsigned long virt, phys_addr_t size,
-				 pgprot_t prot,
+				pgprot_t prot,
-				 phys_addr_t (*pgtable_alloc)(enum pgtable_type),
+				phys_addr_t (*pgtable_alloc)(enum pgtable_type),
-				 int flags)
+				int flags)
 {
+	int ret;
+
 	mutex_lock(&fixmap_lock);
-	__create_pgd_mapping_locked(pgdir, phys, virt, size, prot,
+	ret = __create_pgd_mapping_locked(pgdir, phys, virt, size, prot,
-				    pgtable_alloc, flags);
+					  pgtable_alloc, flags);
 	mutex_unlock(&fixmap_lock);
+
+	return ret;
 }
 
-#define INVALID_PHYS_ADDR	(-1ULL)
+static void early_create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
+				     unsigned long virt, phys_addr_t size,
+				     pgprot_t prot,
+				     phys_addr_t (*pgtable_alloc)(enum pgtable_type),
+				     int flags)
+{
+	int ret;
+
+	ret = __create_pgd_mapping(pgdir, phys, virt, size, prot, pgtable_alloc,
+				   flags);
+	if (ret)
+		panic("Failed to create page tables\n");
+}
 
 static phys_addr_t __pgd_pgtable_alloc(struct mm_struct *mm, gfp_t gfp,
 				       enum pgtable_type pgtable_type)
@@ -503,7 +560,7 @@ static phys_addr_t __pgd_pgtable_alloc(struct mm_struct *mm, gfp_t gfp,
 }
 
 static phys_addr_t
-try_pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type, gfp_t gfp)
+pgd_pgtable_alloc_init_mm_gfp(enum pgtable_type pgtable_type, gfp_t gfp)
 {
 	return __pgd_pgtable_alloc(&init_mm, gfp, pgtable_type);
 }
@@ -511,21 +568,13 @@ try_pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type, gfp_t gfp)
 static phys_addr_t __maybe_unused
 pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type)
 {
-	phys_addr_t pa;
+	return pgd_pgtable_alloc_init_mm_gfp(pgtable_type, GFP_PGTABLE_KERNEL);
-
-	pa = __pgd_pgtable_alloc(&init_mm, GFP_PGTABLE_KERNEL, pgtable_type);
-	BUG_ON(pa == INVALID_PHYS_ADDR);
-	return pa;
 }
 
 static phys_addr_t
 pgd_pgtable_alloc_special_mm(enum pgtable_type pgtable_type)
 {
-	phys_addr_t pa;
+	return  __pgd_pgtable_alloc(NULL, GFP_PGTABLE_KERNEL, pgtable_type);
-
-	pa = __pgd_pgtable_alloc(NULL, GFP_PGTABLE_KERNEL, pgtable_type);
-	BUG_ON(pa == INVALID_PHYS_ADDR);
-	return pa;
 }
 
 static void split_contpte(pte_t *ptep)
@@ -546,7 +595,7 @@ static int split_pmd(pmd_t *pmdp, pmd_t pmd, gfp_t gfp, bool to_cont)
 	pte_t *ptep;
 	int i;
 
-	pte_phys = try_pgd_pgtable_alloc_init_mm(TABLE_PTE, gfp);
+	pte_phys = pgd_pgtable_alloc_init_mm_gfp(TABLE_PTE, gfp);
 	if (pte_phys == INVALID_PHYS_ADDR)
 		return -ENOMEM;
 	ptep = (pte_t *)phys_to_virt(pte_phys);
@@ -591,7 +640,7 @@ static int split_pud(pud_t *pudp, pud_t pud, gfp_t gfp, bool to_cont)
 	pmd_t *pmdp;
 	int i;
 
-	pmd_phys = try_pgd_pgtable_alloc_init_mm(TABLE_PMD, gfp);
+	pmd_phys = pgd_pgtable_alloc_init_mm_gfp(TABLE_PMD, gfp);
 	if (pmd_phys == INVALID_PHYS_ADDR)
 		return -ENOMEM;
 	pmdp = (pmd_t *)phys_to_virt(pmd_phys);
@@ -935,8 +984,8 @@ void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
 			&phys, virt);
 		return;
 	}
-	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL,
+	early_create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL,
-			     NO_CONT_MAPPINGS);
+				 NO_CONT_MAPPINGS);
 }
 
 void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
@@ -950,8 +999,8 @@ void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 	if (page_mappings_only)
 		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
-	__create_pgd_mapping(mm->pgd, phys, virt, size, prot,
+	early_create_pgd_mapping(mm->pgd, phys, virt, size, prot,
-			     pgd_pgtable_alloc_special_mm, flags);
+				 pgd_pgtable_alloc_special_mm, flags);
 }
 
 static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
@@ -963,8 +1012,8 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
 		return;
 	}
 
-	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL,
+	early_create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL,
-			     NO_CONT_MAPPINGS);
+				 NO_CONT_MAPPINGS);
 
 	/* flush the TLBs after updating live kernel mappings */
 	flush_tlb_kernel_range(virt, virt + size);
@@ -973,8 +1022,8 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
 static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start,
 				  phys_addr_t end, pgprot_t prot, int flags)
 {
-	__create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start,
+	early_create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start,
-			     prot, early_pgtable_alloc, flags);
+				 prot, early_pgtable_alloc, flags);
 }
 
 void __init mark_linear_text_alias_ro(void)
@@ -1207,6 +1256,8 @@ static int __init __kpti_install_ng_mappings(void *__unused)
 	remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings);
 
 	if (!cpu) {
+		int ret;
+
 		alloc = __get_free_pages(GFP_ATOMIC | __GFP_ZERO, order);
 		kpti_ng_temp_pgd = (pgd_t *)(alloc + (levels - 1) * PAGE_SIZE);
 		kpti_ng_temp_alloc = kpti_ng_temp_pgd_pa = __pa(kpti_ng_temp_pgd);
@@ -1227,9 +1278,11 @@ static int __init __kpti_install_ng_mappings(void *__unused)
 		// covers the PTE[] page itself, the remaining entries are free
 		// to be used as a ad-hoc fixmap.
 		//
-		__create_pgd_mapping_locked(kpti_ng_temp_pgd, __pa(alloc),
+		ret = __create_pgd_mapping_locked(kpti_ng_temp_pgd, __pa(alloc),
-					    KPTI_NG_TEMP_VA, PAGE_SIZE, PAGE_KERNEL,
+						  KPTI_NG_TEMP_VA, PAGE_SIZE, PAGE_KERNEL,
-					    kpti_ng_pgd_alloc, 0);
+						  kpti_ng_pgd_alloc, 0);
+		if (ret)
+			panic("Failed to create page tables\n");
 	}
 
 	cpu_install_idmap();
@@ -1282,9 +1335,9 @@ static int __init map_entry_trampoline(void)
 
 	/* Map only the text into the trampoline page table */
 	memset(tramp_pg_dir, 0, PGD_SIZE);
-	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS,
+	early_create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS,
-			     entry_tramp_text_size(), prot,
+				 entry_tramp_text_size(), prot,
-			     pgd_pgtable_alloc_init_mm, NO_BLOCK_MAPPINGS);
+				 pgd_pgtable_alloc_init_mm, NO_BLOCK_MAPPINGS);
 
 	/* Map both the text and data into the kernel page table */
 	for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++)
@@ -1926,23 +1979,28 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	if (force_pte_mapping())
 		flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
-	__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
+	ret = __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
-			     size, params->pgprot, pgd_pgtable_alloc_init_mm,
+				   size, params->pgprot, pgd_pgtable_alloc_init_mm,
-			     flags);
+				   flags);
+	if (ret)
+		goto err;
 
 	memblock_clear_nomap(start, size);
 
 	ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
 			   params);
 	if (ret)
-		__remove_pgd_mapping(swapper_pg_dir,
+		goto err;
-				     __phys_to_virt(start), size);
-	else {
-		/* Address of hotplugged memory can be smaller */
-		max_pfn = max(max_pfn, PFN_UP(start + size));
-		max_low_pfn = max_pfn;
-	}
 
+	/* Address of hotplugged memory can be smaller */
+	max_pfn = max(max_pfn, PFN_UP(start + size));
+	max_low_pfn = max_pfn;
+
+	return 0;
+
+err:
+	__remove_pgd_mapping(swapper_pg_dir,
+			     __phys_to_virt(start), size);
 	return ret;
 }