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

Pull arm64 updates from Will Deacon:
 "The changes are a real mixed bag this time around.

  The only scary looking one from the diffstat is the uapi change to
  asm-generic/mman-common.h, but this has been acked by Arnd and is
  actually just adding a pair of comments in an attempt to prevent
  allocation of some PROT values which tend to get used for
  arch-specific purposes. We'll be using them for Branch Target
  Identification (a CFI-like hardening feature), which is currently
  under review on the mailing list.

  New architecture features:

   - Support for Armv8.5 E0PD, which benefits KASLR in the same way as
     KPTI but without the overhead. This allows KPTI to be disabled on
     CPUs that are not affected by Meltdown, even is KASLR is enabled.

   - Initial support for the Armv8.5 RNG instructions, which claim to
     provide access to a high bandwidth, cryptographically secure
     hardware random number generator. As well as exposing these to
     userspace, we also use them as part of the KASLR seed and to seed
     the crng once all CPUs have come online.

   - Advertise a bunch of new instructions to userspace, including
     support for Data Gathering Hint, Matrix Multiply and 16-bit
     floating point.

  Kexec:

   - Cleanups in preparation for relocating with the MMU enabled

   - Support for loading crash dump kernels with kexec_file_load()

  Perf and PMU drivers:

   - Cleanups and non-critical fixes for a couple of system PMU drivers

  FPU-less (aka broken) CPU support:

   - Considerable fixes to support CPUs without the FP/SIMD extensions,
     including their presence in heterogeneous systems. Good luck
     finding a 64-bit userspace that handles this.

  Modern assembly function annotations:

   - Start migrating our use of ENTRY() and ENDPROC() over to the
     new-fangled SYM_{CODE,FUNC}_{START,END} macros, which are intended
     to aid debuggers

  Kbuild:

   - Cleanup detection of LSE support in the assembler by introducing
     'as-instr'

   - Remove compressed Image files when building clean targets

  IP checksumming:

   - Implement optimised IPv4 checksumming routine when hardware offload
     is not in use. An IPv6 version is in the works, pending testing.

  Hardware errata:

   - Work around Cortex-A55 erratum #1530923

  Shadow call stack:

   - Work around some issues with Clang's integrated assembler not
     liking our perfectly reasonable assembly code

   - Avoid allocating the X18 register, so that it can be used to hold
     the shadow call stack pointer in future

  ACPI:

   - Fix ID count checking in IORT code. This may regress broken
     firmware that happened to work with the old implementation, in
     which case we'll have to revert it and try something else

   - Fix DAIF corruption on return from GHES handler with pseudo-NMIs

  Miscellaneous:

   - Whitelist some CPUs that are unaffected by Spectre-v2

   - Reduce frequency of ASID rollover when KPTI is compiled in but
     inactive

   - Reserve a couple of arch-specific PROT flags that are already used
     by Sparc and PowerPC and are planned for later use with BTI on
     arm64

   - Preparatory cleanup of our entry assembly code in preparation for
     moving more of it into C later on

   - Refactoring and cleanup"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (73 commits)
  arm64: acpi: fix DAIF manipulation with pNMI
  arm64: kconfig: Fix alignment of E0PD help text
  arm64: Use v8.5-RNG entropy for KASLR seed
  arm64: Implement archrandom.h for ARMv8.5-RNG
  arm64: kbuild: remove compressed images on 'make ARCH=arm64 (dist)clean'
  arm64: entry: Avoid empty alternatives entries
  arm64: Kconfig: select HAVE_FUTEX_CMPXCHG
  arm64: csum: Fix pathological zero-length calls
  arm64: entry: cleanup sp_el0 manipulation
  arm64: entry: cleanup el0 svc handler naming
  arm64: entry: mark all entry code as notrace
  arm64: assembler: remove smp_dmb macro
  arm64: assembler: remove inherit_daif macro
  ACPI/IORT: Fix 'Number of IDs' handling in iort_id_map()
  mm: Reserve asm-generic prot flags 0x10 and 0x20 for arch use
  arm64: Use macros instead of hard-coded constants for MAIR_EL1
  arm64: Add KRYO{3,4}XX CPU cores to spectre-v2 safe list
  arm64: kernel: avoid x18 in __cpu_soft_restart
  arm64: kvm: stop treating register x18 as caller save
  arm64/lib: copy_page: avoid x18 register in assembler code
  ...

Documentation/arm64/cpu-feature-registers.rst

@@ -117,6 +117,8 @@ infrastructure:
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
      +------------------------------+---------+---------+
+     | RNDR                         | [63-60] |    y    |
+     +------------------------------+---------+---------+
      | TS                           | [55-52] |    y    |
      +------------------------------+---------+---------+
      | FHM                          | [51-48] |    y    |
@@ -200,6 +202,12 @@ infrastructure:
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
      +------------------------------+---------+---------+
+     | I8MM                         | [55-52] |    y    |
+     +------------------------------+---------+---------+
+     | DGH                          | [51-48] |    y    |
+     +------------------------------+---------+---------+
+     | BF16                         | [47-44] |    y    |
+     +------------------------------+---------+---------+
      | SB                           | [39-36] |    y    |
      +------------------------------+---------+---------+
      | FRINTTS                      | [35-32] |    y    |
@@ -234,10 +242,18 @@ infrastructure:
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
      +------------------------------+---------+---------+
+     | F64MM                        | [59-56] |    y    |
+     +------------------------------+---------+---------+
+     | F32MM                        | [55-52] |    y    |
+     +------------------------------+---------+---------+
+     | I8MM                         | [47-44] |    y    |
+     +------------------------------+---------+---------+
      | SM4                          | [43-40] |    y    |
      +------------------------------+---------+---------+
      | SHA3                         | [35-32] |    y    |
      +------------------------------+---------+---------+
+     | BF16                         | [23-20] |    y    |
+     +------------------------------+---------+---------+
      | BitPerm                      | [19-16] |    y    |
      +------------------------------+---------+---------+
      | AES                          | [7-4]   |    y    |

Documentation/arm64/elf_hwcaps.rst

@@ -204,6 +204,37 @@ HWCAP2_FRINT
 
     Functionality implied by ID_AA64ISAR1_EL1.FRINTTS == 0b0001.
 
+HWCAP2_SVEI8MM
+
+    Functionality implied by ID_AA64ZFR0_EL1.I8MM == 0b0001.
+
+HWCAP2_SVEF32MM
+
+    Functionality implied by ID_AA64ZFR0_EL1.F32MM == 0b0001.
+
+HWCAP2_SVEF64MM
+
+    Functionality implied by ID_AA64ZFR0_EL1.F64MM == 0b0001.
+
+HWCAP2_SVEBF16
+
+    Functionality implied by ID_AA64ZFR0_EL1.BF16 == 0b0001.
+
+HWCAP2_I8MM
+
+    Functionality implied by ID_AA64ISAR1_EL1.I8MM == 0b0001.
+
+HWCAP2_BF16
+
+    Functionality implied by ID_AA64ISAR1_EL1.BF16 == 0b0001.
+
+HWCAP2_DGH
+
+    Functionality implied by ID_AA64ISAR1_EL1.DGH == 0b0001.
+
+HWCAP2_RNG
+
+    Functionality implied by ID_AA64ISAR0_EL1.RNDR == 0b0001.
 
 4. Unused AT_HWCAP bits
 -----------------------

Documentation/arm64/silicon-errata.rst

@@ -88,6 +88,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A76      | #1463225        | ARM64_ERRATUM_1463225       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A55      | #1530923        | ARM64_ERRATUM_1530923       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1188873,1418040| ARM64_ERRATUM_1418040       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |

arch/arm64/Kconfig

@@ -162,6 +162,7 @@ config ARM64
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_FUNCTION_ARG_ACCESS_API
+	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_RCU_TABLE_FREE
 	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
@@ -302,6 +303,9 @@ config ARCH_SUPPORTS_UPROBES
 config ARCH_PROC_KCORE_TEXT
 	def_bool y
 
+config BROKEN_GAS_INST
+	def_bool !$(as-instr,1:\n.inst 0\n.rept . - 1b\n\nnop\n.endr\n)
+
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN
@@ -515,9 +519,13 @@ config ARM64_ERRATUM_1418040
 
 	  If unsure, say Y.
 
+config ARM64_WORKAROUND_SPECULATIVE_AT_VHE
+	bool
+
 config ARM64_ERRATUM_1165522
 	bool "Cortex-A76: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
 	default y
+	select ARM64_WORKAROUND_SPECULATIVE_AT_VHE
 	help
 	  This option adds a workaround for ARM Cortex-A76 erratum 1165522.
 
@@ -527,6 +535,19 @@ config ARM64_ERRATUM_1165522
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_1530923
+	bool "Cortex-A55: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
+	default y
+	select ARM64_WORKAROUND_SPECULATIVE_AT_VHE
+	help
+	  This option adds a workaround for ARM Cortex-A55 erratum 1530923.
+
+	  Affected Cortex-A55 cores (r0p0, r0p1, r1p0, r2p0) could end-up with
+	  corrupted TLBs by speculating an AT instruction during a guest
+	  context switch.
+
+	  If unsure, say Y.
+
 config ARM64_ERRATUM_1286807
 	bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation"
 	default y
@@ -543,9 +564,13 @@ config ARM64_ERRATUM_1286807
 	  invalidated has been observed by other observers. The
 	  workaround repeats the TLBI+DSB operation.
 
+config ARM64_WORKAROUND_SPECULATIVE_AT_NVHE
+	bool
+
 config ARM64_ERRATUM_1319367
 	bool "Cortex-A57/A72: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
 	default y
+	select ARM64_WORKAROUND_SPECULATIVE_AT_NVHE
 	help
 	  This option adds work arounds for ARM Cortex-A57 erratum 1319537
 	  and A72 erratum 1319367
@@ -1364,6 +1389,11 @@ config ARM64_PAN
 	 instruction if the cpu does not implement the feature.
 
 config ARM64_LSE_ATOMICS
+	bool
+	default ARM64_USE_LSE_ATOMICS
+	depends on $(as-instr,.arch_extension lse)
+
+config ARM64_USE_LSE_ATOMICS
 	bool "Atomic instructions"
 	depends on JUMP_LABEL
 	default y
@@ -1485,6 +1515,30 @@ config ARM64_PTR_AUTH
 
 endmenu
 
+menu "ARMv8.5 architectural features"
+
+config ARM64_E0PD
+	bool "Enable support for E0PD"
+	default y
+	help
+	  E0PD (part of the ARMv8.5 extensions) allows us to ensure
+	  that EL0 accesses made via TTBR1 always fault in constant time,
+	  providing similar benefits to KASLR as those provided by KPTI, but
+	  with lower overhead and without disrupting legitimate access to
+	  kernel memory such as SPE.
+
+	  This option enables E0PD for TTBR1 where available.
+
+config ARCH_RANDOM
+	bool "Enable support for random number generation"
+	default y
+	help
+	  Random number generation (part of the ARMv8.5 Extensions)
+	  provides a high bandwidth, cryptographically secure
+	  hardware random number generator.
+
+endmenu
+
 config ARM64_SVE
 	bool "ARM Scalable Vector Extension support"
 	default y
@@ -1545,7 +1599,7 @@ config ARM64_MODULE_PLTS
 
 config ARM64_PSEUDO_NMI
 	bool "Support for NMI-like interrupts"
-	select CONFIG_ARM_GIC_V3
+	select ARM_GIC_V3
 	help
 	  Adds support for mimicking Non-Maskable Interrupts through the use of
 	  GIC interrupt priority. This support requires version 3 or later of

arch/arm64/Makefile

@@ -30,11 +30,8 @@ LDFLAGS_vmlinux	+= --fix-cortex-a53-843419
   endif
 endif
 
-# Check for binutils support for specific extensions
-lseinstr := $(call as-instr,.arch_extension lse,-DCONFIG_AS_LSE=1)
-
-ifeq ($(CONFIG_ARM64_LSE_ATOMICS), y)
-  ifeq ($(lseinstr),)
+ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS), y)
+  ifneq ($(CONFIG_ARM64_LSE_ATOMICS), y)
 $(warning LSE atomics not supported by binutils)
   endif
 endif
@@ -45,19 +42,15 @@ cc_has_k_constraint := $(call try-run,echo				\
 		return 0;						\
 	}' | $(CC) -S -x c -o "$$TMP" -,,-DCONFIG_CC_HAS_K_CONSTRAINT=1)
 
-ifeq ($(CONFIG_ARM64), y)
-brokengasinst := $(call as-instr,1:\n.inst 0\n.rept . - 1b\n\nnop\n.endr\n,,-DCONFIG_BROKEN_GAS_INST=1)
-
-  ifneq ($(brokengasinst),)
+ifeq ($(CONFIG_BROKEN_GAS_INST),y)
 $(warning Detected assembler with broken .inst; disassembly will be unreliable)
-  endif
 endif
 
-KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr) $(brokengasinst)	\
+KBUILD_CFLAGS	+= -mgeneral-regs-only	\
 		   $(compat_vdso) $(cc_has_k_constraint)
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS	+= $(call cc-disable-warning, psabi)
-KBUILD_AFLAGS	+= $(lseinstr) $(brokengasinst) $(compat_vdso)
+KBUILD_AFLAGS	+= $(compat_vdso)
 
 KBUILD_CFLAGS	+= $(call cc-option,-mabi=lp64)
 KBUILD_AFLAGS	+= $(call cc-option,-mabi=lp64)

arch/arm64/boot/Makefile

@@ -16,7 +16,7 @@
 
 OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
 
-targets := Image Image.gz
+targets := Image Image.bz2 Image.gz Image.lz4 Image.lzma Image.lzo
 
 $(obj)/Image: vmlinux FORCE
 	$(call if_changed,objcopy)

arch/arm64/include/asm/alternative.h

@@ -35,13 +35,16 @@ void apply_alternatives_module(void *start, size_t length);
 static inline void apply_alternatives_module(void *start, size_t length) { }
 #endif
 
-#define ALTINSTR_ENTRY(feature,cb)					      \
+#define ALTINSTR_ENTRY(feature)					              \
 	" .word 661b - .\n"				/* label           */ \
-	" .if " __stringify(cb) " == 0\n"				      \
 	" .word 663f - .\n"				/* new instruction */ \
-	" .else\n"							      \
+	" .hword " __stringify(feature) "\n"		/* feature bit     */ \
+	" .byte 662b-661b\n"				/* source len      */ \
+	" .byte 664f-663f\n"				/* replacement len */
+
+#define ALTINSTR_ENTRY_CB(feature, cb)					      \
+	" .word 661b - .\n"				/* label           */ \
 	" .word " __stringify(cb) "- .\n"		/* callback */	      \
-	" .endif\n"							      \
 	" .hword " __stringify(feature) "\n"		/* feature bit     */ \
 	" .byte 662b-661b\n"				/* source len      */ \
 	" .byte 664f-663f\n"				/* replacement len */
@@ -62,15 +65,14 @@ static inline void apply_alternatives_module(void *start, size_t length) { }
  *
  * Alternatives with callbacks do not generate replacement instructions.
  */
-#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled, cb)	\
+#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled)	\
 	".if "__stringify(cfg_enabled)" == 1\n"				\
 	"661:\n\t"							\
 	oldinstr "\n"							\
 	"662:\n"							\
 	".pushsection .altinstructions,\"a\"\n"				\
-	ALTINSTR_ENTRY(feature,cb)					\
+	ALTINSTR_ENTRY(feature)						\
 	".popsection\n"							\
-	" .if " __stringify(cb) " == 0\n"				\
 	".pushsection .altinstr_replacement, \"a\"\n"			\
 	"663:\n\t"							\
 	newinstr "\n"							\
@@ -78,17 +80,25 @@ static inline void apply_alternatives_module(void *start, size_t length) { }
 	".popsection\n\t"						\
 	".org	. - (664b-663b) + (662b-661b)\n\t"			\
 	".org	. - (662b-661b) + (664b-663b)\n"			\
-	".else\n\t"							\
+	".endif\n"
+
+#define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb)	\
+	".if "__stringify(cfg_enabled)" == 1\n"				\
+	"661:\n\t"							\
+	oldinstr "\n"							\
+	"662:\n"							\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY_CB(feature, cb)					\
+	".popsection\n"							\
 	"663:\n\t"							\
 	"664:\n\t"							\
-	".endif\n"							\
 	".endif\n"
 
 #define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...)	\
-	__ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg), 0)
+	__ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg))
 
 #define ALTERNATIVE_CB(oldinstr, cb) \
-	__ALTERNATIVE_CFG(oldinstr, "NOT_AN_INSTRUCTION", ARM64_CB_PATCH, 1, cb)
+	__ALTERNATIVE_CFG_CB(oldinstr, ARM64_CB_PATCH, 1, cb)
 #else
 
 #include <asm/assembler.h>

arch/arm64/include/asm/archrandom.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARCHRANDOM_H
+#define _ASM_ARCHRANDOM_H
+
+#ifdef CONFIG_ARCH_RANDOM
+
+#include <linux/random.h>
+#include <asm/cpufeature.h>
+
+static inline bool __arm64_rndr(unsigned long *v)
+{
+	bool ok;
+
+	/*
+	 * Reads of RNDR set PSTATE.NZCV to 0b0000 on success,
+	 * and set PSTATE.NZCV to 0b0100 otherwise.
+	 */
+	asm volatile(
+		__mrs_s("%0", SYS_RNDR_EL0) "\n"
+	"	cset %w1, ne\n"
+	: "=r" (*v), "=r" (ok)
+	:
+	: "cc");
+
+	return ok;
+}
+
+static inline bool __must_check arch_get_random_long(unsigned long *v)
+{
+	return false;
+}
+
+static inline bool __must_check arch_get_random_int(unsigned int *v)
+{
+	return false;
+}
+
+static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
+{
+	/*
+	 * Only support the generic interface after we have detected
+	 * the system wide capability, avoiding complexity with the
+	 * cpufeature code and with potential scheduling between CPUs
+	 * with and without the feature.
+	 */
+	if (!cpus_have_const_cap(ARM64_HAS_RNG))
+		return false;
+
+	return __arm64_rndr(v);
+}
+
+
+static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
+{
+	unsigned long val;
+	bool ok = arch_get_random_seed_long(&val);
+
+	*v = val;
+	return ok;
+}
+
+static inline bool __init __early_cpu_has_rndr(void)
+{
+	/* Open code as we run prior to the first call to cpufeature. */
+	unsigned long ftr = read_sysreg_s(SYS_ID_AA64ISAR0_EL1);
+	return (ftr >> ID_AA64ISAR0_RNDR_SHIFT) & 0xf;
+}
+
+#else
+
+static inline bool __arm64_rndr(unsigned long *v) { return false; }
+static inline bool __init __early_cpu_has_rndr(void) { return false; }
+
+#endif /* CONFIG_ARCH_RANDOM */
+#endif /* _ASM_ARCHRANDOM_H */

arch/arm64/include/asm/assembler.h

@@ -40,12 +40,6 @@
 	msr	daif, \flags
 	.endm
 
-	/* Only on aarch64 pstate, PSR_D_BIT is different for aarch32 */
-	.macro	inherit_daif, pstate:req, tmp:req
-	and	\tmp, \pstate, #(PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
-	msr	daif, \tmp
-	.endm
-
 	/* IRQ is the lowest priority flag, unconditionally unmask the rest. */
 	.macro enable_da_f
 	msr	daifclr, #(8 | 4 | 1)
@@ -85,13 +79,6 @@
 9990:
 	.endm
 
-/*
- * SMP data memory barrier
- */
-	.macro	smp_dmb, opt
-	dmb	\opt
-	.endm
-
 /*
  * RAS Error Synchronization barrier
  */
@@ -461,17 +448,6 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 	b.ne	9998b
 	.endm
 
-/*
- * Annotate a function as position independent, i.e., safe to be called before
- * the kernel virtual mapping is activated.
- */
-#define ENDPIPROC(x)			\
-	.globl	__pi_##x;		\
-	.type 	__pi_##x, %function;	\
-	.set	__pi_##x, x;		\
-	.size	__pi_##x, . - x;	\
-	ENDPROC(x)
-
 /*
  * Annotate a function as being unsuitable for kprobes.
  */

arch/arm64/include/asm/atomic_ll_sc.h

@@ -12,7 +12,7 @@
 
 #include <linux/stringify.h>
 
-#if IS_ENABLED(CONFIG_ARM64_LSE_ATOMICS) && IS_ENABLED(CONFIG_AS_LSE)
+#ifdef CONFIG_ARM64_LSE_ATOMICS
 #define __LL_SC_FALLBACK(asm_ops)					\
 "	b	3f\n"							\
 "	.subsection	1\n"						\

arch/arm64/include/asm/atomic_lse.h

@@ -14,6 +14,7 @@
 static inline void __lse_atomic_##op(int i, atomic_t *v)			\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 "	" #asm_op "	%w[i], %[v]\n"					\
 	: [i] "+r" (i), [v] "+Q" (v->counter)				\
 	: "r" (v));							\
@@ -30,6 +31,7 @@ ATOMIC_OP(add, stadd)
 static inline int __lse_atomic_fetch_##op##name(int i, atomic_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 "	" #asm_op #mb "	%w[i], %w[i], %[v]"				\
 	: [i] "+r" (i), [v] "+Q" (v->counter)				\
 	: "r" (v)							\
@@ -58,6 +60,7 @@ static inline int __lse_atomic_add_return##name(int i, atomic_t *v)	\
 	u32 tmp;							\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	ldadd" #mb "	%w[i], %w[tmp], %[v]\n"			\
 	"	add	%w[i], %w[i], %w[tmp]"				\
 	: [i] "+r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp)	\
@@ -77,6 +80,7 @@ ATOMIC_OP_ADD_RETURN(        , al, "memory")
 static inline void __lse_atomic_and(int i, atomic_t *v)
 {
 	asm volatile(
+	__LSE_PREAMBLE
 	"	mvn	%w[i], %w[i]\n"
 	"	stclr	%w[i], %[v]"
 	: [i] "+&r" (i), [v] "+Q" (v->counter)
@@ -87,6 +91,7 @@ static inline void __lse_atomic_and(int i, atomic_t *v)
 static inline int __lse_atomic_fetch_and##name(int i, atomic_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	mvn	%w[i], %w[i]\n"					\
 	"	ldclr" #mb "	%w[i], %w[i], %[v]"			\
 	: [i] "+&r" (i), [v] "+Q" (v->counter)				\
@@ -106,6 +111,7 @@ ATOMIC_FETCH_OP_AND(        , al, "memory")
 static inline void __lse_atomic_sub(int i, atomic_t *v)
 {
 	asm volatile(
+	__LSE_PREAMBLE
 	"	neg	%w[i], %w[i]\n"
 	"	stadd	%w[i], %[v]"
 	: [i] "+&r" (i), [v] "+Q" (v->counter)
@@ -118,6 +124,7 @@ static inline int __lse_atomic_sub_return##name(int i, atomic_t *v)	\
 	u32 tmp;							\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	neg	%w[i], %w[i]\n"					\
 	"	ldadd" #mb "	%w[i], %w[tmp], %[v]\n"			\
 	"	add	%w[i], %w[i], %w[tmp]"				\
@@ -139,6 +146,7 @@ ATOMIC_OP_SUB_RETURN(        , al, "memory")
 static inline int __lse_atomic_fetch_sub##name(int i, atomic_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	neg	%w[i], %w[i]\n"					\
 	"	ldadd" #mb "	%w[i], %w[i], %[v]"			\
 	: [i] "+&r" (i), [v] "+Q" (v->counter)				\
@@ -159,6 +167,7 @@ ATOMIC_FETCH_OP_SUB(        , al, "memory")
 static inline void __lse_atomic64_##op(s64 i, atomic64_t *v)		\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 "	" #asm_op "	%[i], %[v]\n"					\
 	: [i] "+r" (i), [v] "+Q" (v->counter)				\
 	: "r" (v));							\
@@ -175,6 +184,7 @@ ATOMIC64_OP(add, stadd)
 static inline long __lse_atomic64_fetch_##op##name(s64 i, atomic64_t *v)\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 "	" #asm_op #mb "	%[i], %[i], %[v]"				\
 	: [i] "+r" (i), [v] "+Q" (v->counter)				\
 	: "r" (v)							\
@@ -203,6 +213,7 @@ static inline long __lse_atomic64_add_return##name(s64 i, atomic64_t *v)\
 	unsigned long tmp;						\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	ldadd" #mb "	%[i], %x[tmp], %[v]\n"			\
 	"	add	%[i], %[i], %x[tmp]"				\
 	: [i] "+r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp)	\
@@ -222,6 +233,7 @@ ATOMIC64_OP_ADD_RETURN(        , al, "memory")
 static inline void __lse_atomic64_and(s64 i, atomic64_t *v)
 {
 	asm volatile(
+	__LSE_PREAMBLE
 	"	mvn	%[i], %[i]\n"
 	"	stclr	%[i], %[v]"
 	: [i] "+&r" (i), [v] "+Q" (v->counter)
@@ -232,6 +244,7 @@ static inline void __lse_atomic64_and(s64 i, atomic64_t *v)
 static inline long __lse_atomic64_fetch_and##name(s64 i, atomic64_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	mvn	%[i], %[i]\n"					\
 	"	ldclr" #mb "	%[i], %[i], %[v]"			\
 	: [i] "+&r" (i), [v] "+Q" (v->counter)				\
@@ -251,6 +264,7 @@ ATOMIC64_FETCH_OP_AND(        , al, "memory")
 static inline void __lse_atomic64_sub(s64 i, atomic64_t *v)
 {
 	asm volatile(
+	__LSE_PREAMBLE
 	"	neg	%[i], %[i]\n"
 	"	stadd	%[i], %[v]"
 	: [i] "+&r" (i), [v] "+Q" (v->counter)
@@ -263,6 +277,7 @@ static inline long __lse_atomic64_sub_return##name(s64 i, atomic64_t *v)	\
 	unsigned long tmp;						\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	neg	%[i], %[i]\n"					\
 	"	ldadd" #mb "	%[i], %x[tmp], %[v]\n"			\
 	"	add	%[i], %[i], %x[tmp]"				\
@@ -284,6 +299,7 @@ ATOMIC64_OP_SUB_RETURN(        , al, "memory")
 static inline long __lse_atomic64_fetch_sub##name(s64 i, atomic64_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	neg	%[i], %[i]\n"					\
 	"	ldadd" #mb "	%[i], %[i], %[v]"			\
 	: [i] "+&r" (i), [v] "+Q" (v->counter)				\
@@ -305,6 +321,7 @@ static inline s64 __lse_atomic64_dec_if_positive(atomic64_t *v)
 	unsigned long tmp;
 
 	asm volatile(
+	__LSE_PREAMBLE
 	"1:	ldr	%x[tmp], %[v]\n"
 	"	subs	%[ret], %x[tmp], #1\n"
 	"	b.lt	2f\n"
@@ -332,6 +349,7 @@ __lse__cmpxchg_case_##name##sz(volatile void *ptr,			\
 	unsigned long tmp;						\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	mov	%" #w "[tmp], %" #w "[old]\n"			\
 	"	cas" #mb #sfx "\t%" #w "[tmp], %" #w "[new], %[v]\n"	\
 	"	mov	%" #w "[ret], %" #w "[tmp]"			\
@@ -379,6 +397,7 @@ __lse__cmpxchg_double##name(unsigned long old1,				\
 	register unsigned long x4 asm ("x4") = (unsigned long)ptr;	\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\
 	"	eor	%[old1], %[old1], %[oldval1]\n"			\
 	"	eor	%[old2], %[old2], %[oldval2]\n"			\

arch/arm64/include/asm/checksum.h

@@ -35,6 +35,9 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 }
 #define ip_fast_csum ip_fast_csum
 
+extern unsigned int do_csum(const unsigned char *buff, int len);
+#define do_csum do_csum
+
 #include <asm-generic/checksum.h>
 
 #endif	/* __ASM_CHECKSUM_H */

arch/arm64/include/asm/cpu.h

@@ -39,6 +39,7 @@ struct cpuinfo_arm64 {
 	u32		reg_id_isar3;
 	u32		reg_id_isar4;
 	u32		reg_id_isar5;
+	u32		reg_id_isar6;
 	u32		reg_id_mmfr0;
 	u32		reg_id_mmfr1;
 	u32		reg_id_mmfr2;

arch/arm64/include/asm/cpucaps.h

@@ -44,7 +44,7 @@
 #define ARM64_SSBS				34
 #define ARM64_WORKAROUND_1418040		35
 #define ARM64_HAS_SB				36
-#define ARM64_WORKAROUND_1165522		37
+#define ARM64_WORKAROUND_SPECULATIVE_AT_VHE	37
 #define ARM64_HAS_ADDRESS_AUTH_ARCH		38
 #define ARM64_HAS_ADDRESS_AUTH_IMP_DEF		39
 #define ARM64_HAS_GENERIC_AUTH_ARCH		40
@@ -55,8 +55,10 @@
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM	45
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM	46
 #define ARM64_WORKAROUND_1542419		47
-#define ARM64_WORKAROUND_1319367		48
+#define ARM64_WORKAROUND_SPECULATIVE_AT_NVHE	48
+#define ARM64_HAS_E0PD				49
+#define ARM64_HAS_RNG				50
 
-#define ARM64_NCAPS				49
+#define ARM64_NCAPS				51
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/cpufeature.h

@@ -613,6 +613,11 @@ static inline bool system_has_prio_mask_debugging(void)
 	       system_uses_irq_prio_masking();
 }
 
+static inline bool system_capabilities_finalized(void)
+{
+	return static_branch_likely(&arm64_const_caps_ready);
+}
+
 #define ARM64_BP_HARDEN_UNKNOWN		-1
 #define ARM64_BP_HARDEN_WA_NEEDED	0
 #define ARM64_BP_HARDEN_NOT_REQUIRED	1

arch/arm64/include/asm/cputype.h

@@ -85,6 +85,8 @@
 #define QCOM_CPU_PART_FALKOR_V1		0x800
 #define QCOM_CPU_PART_FALKOR		0xC00
 #define QCOM_CPU_PART_KRYO		0x200
+#define QCOM_CPU_PART_KRYO_3XX_SILVER	0x803
+#define QCOM_CPU_PART_KRYO_4XX_SILVER	0x805
 
 #define NVIDIA_CPU_PART_DENVER		0x003
 #define NVIDIA_CPU_PART_CARMEL		0x004
@@ -111,6 +113,8 @@
 #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
 #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
 #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
+#define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER)
+#define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
 #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
 #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
 #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)

arch/arm64/include/asm/daifflags.h

@@ -38,7 +38,7 @@ static inline void local_daif_mask(void)
 	trace_hardirqs_off();
 }
 
-static inline unsigned long local_daif_save(void)
+static inline unsigned long local_daif_save_flags(void)
 {
 	unsigned long flags;
 
@@ -50,6 +50,15 @@ static inline unsigned long local_daif_save(void)
 			flags |= PSR_I_BIT;
 	}
 
+	return flags;
+}
+
+static inline unsigned long local_daif_save(void)
+{
+	unsigned long flags;
+
+	flags = local_daif_save_flags();
+
 	local_daif_mask();
 
 	return flags;

arch/arm64/include/asm/exception.h

@@ -45,8 +45,8 @@ void do_sysinstr(unsigned int esr, struct pt_regs *regs);
 void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
 void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr);
 void do_cp15instr(unsigned int esr, struct pt_regs *regs);
-void el0_svc_handler(struct pt_regs *regs);
-void el0_svc_compat_handler(struct pt_regs *regs);
+void do_el0_svc(struct pt_regs *regs);
+void do_el0_svc_compat(struct pt_regs *regs);
 void do_el0_ia_bp_hardening(unsigned long addr,  unsigned int esr,
 			    struct pt_regs *regs);
 

arch/arm64/include/asm/hwcap.h

@@ -86,6 +86,14 @@
 #define KERNEL_HWCAP_SVESM4		__khwcap2_feature(SVESM4)
 #define KERNEL_HWCAP_FLAGM2		__khwcap2_feature(FLAGM2)
 #define KERNEL_HWCAP_FRINT		__khwcap2_feature(FRINT)
+#define KERNEL_HWCAP_SVEI8MM		__khwcap2_feature(SVEI8MM)
+#define KERNEL_HWCAP_SVEF32MM		__khwcap2_feature(SVEF32MM)
+#define KERNEL_HWCAP_SVEF64MM		__khwcap2_feature(SVEF64MM)
+#define KERNEL_HWCAP_SVEBF16		__khwcap2_feature(SVEBF16)
+#define KERNEL_HWCAP_I8MM		__khwcap2_feature(I8MM)
+#define KERNEL_HWCAP_BF16		__khwcap2_feature(BF16)
+#define KERNEL_HWCAP_DGH		__khwcap2_feature(DGH)
+#define KERNEL_HWCAP_RNG		__khwcap2_feature(RNG)
 
 /*
  * This yields a mask that user programs can use to figure out what

arch/arm64/include/asm/kexec.h

@@ -96,6 +96,10 @@ static inline void crash_post_resume(void) {}
 struct kimage_arch {
 	void *dtb;
 	unsigned long dtb_mem;
+	/* Core ELF header buffer */
+	void *elf_headers;
+	unsigned long elf_headers_mem;
+	unsigned long elf_headers_sz;
 };
 
 extern const struct kexec_file_ops kexec_image_ops;

arch/arm64/include/asm/kvm_host.h

@@ -547,7 +547,7 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 	 * wrong, and hyp will crash and burn when it uses any
 	 * cpus_have_const_cap() wrapper.
 	 */
-	BUG_ON(!static_branch_likely(&arm64_const_caps_ready));
+	BUG_ON(!system_capabilities_finalized());
 	__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2);
 
 	/*
@@ -571,7 +571,7 @@ static inline bool kvm_arch_requires_vhe(void)
 		return true;
 
 	/* Some implementations have defects that confine them to VHE */
-	if (cpus_have_cap(ARM64_WORKAROUND_1165522))
+	if (cpus_have_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE))
 		return true;
 
 	return false;

arch/arm64/include/asm/kvm_hyp.h

@@ -91,11 +91,11 @@ static __always_inline void __hyp_text __load_guest_stage2(struct kvm *kvm)
 	write_sysreg(kvm_get_vttbr(kvm), vttbr_el2);
 
 	/*
-	 * ARM erratum 1165522 requires the actual execution of the above
-	 * before we can switch to the EL1/EL0 translation regime used by
+	 * ARM errata 1165522 and 1530923 require the actual execution of the
+	 * above before we can switch to the EL1/EL0 translation regime used by
 	 * the guest.
 	 */
-	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_1165522));
+	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT_VHE));
 }
 
 #endif /* __ARM64_KVM_HYP_H__ */

arch/arm64/include/asm/linkage.h

@@ -4,4 +4,20 @@
 #define __ALIGN		.align 2
 #define __ALIGN_STR	".align 2"
 
+/*
+ * Annotate a function as position independent, i.e., safe to be called before
+ * the kernel virtual mapping is activated.
+ */
+#define SYM_FUNC_START_PI(x)			\
+		SYM_FUNC_START_ALIAS(__pi_##x);	\
+		SYM_FUNC_START(x)
+
+#define SYM_FUNC_START_WEAK_PI(x)		\
+		SYM_FUNC_START_ALIAS(__pi_##x);	\
+		SYM_FUNC_START_WEAK(x)
+
+#define SYM_FUNC_END_PI(x)			\
+		SYM_FUNC_END(x);		\
+		SYM_FUNC_END_ALIAS(__pi_##x)
+
 #endif

arch/arm64/include/asm/lse.h

@@ -4,7 +4,9 @@
 
 #include <asm/atomic_ll_sc.h>
 
-#if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS)
+#ifdef CONFIG_ARM64_LSE_ATOMICS
+
+#define __LSE_PREAMBLE	".arch armv8-a+lse\n"
 
 #include <linux/compiler_types.h>
 #include <linux/export.h>
@@ -14,8 +16,6 @@
 #include <asm/atomic_lse.h>
 #include <asm/cpucaps.h>
 
-__asm__(".arch_extension	lse");
-
 extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
 extern struct static_key_false arm64_const_caps_ready;
 
@@ -34,9 +34,9 @@ static inline bool system_uses_lse_atomics(void)
 
 /* In-line patching at runtime */
 #define ARM64_LSE_ATOMIC_INSN(llsc, lse)				\
-	ALTERNATIVE(llsc, lse, ARM64_HAS_LSE_ATOMICS)
+	ALTERNATIVE(llsc, __LSE_PREAMBLE lse, ARM64_HAS_LSE_ATOMICS)
 
-#else	/* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
+#else	/* CONFIG_ARM64_LSE_ATOMICS */
 
 static inline bool system_uses_lse_atomics(void) { return false; }
 
@@ -44,5 +44,5 @@ static inline bool system_uses_lse_atomics(void) { return false; }
 
 #define ARM64_LSE_ATOMIC_INSN(llsc, lse)	llsc
 
-#endif	/* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
+#endif	/* CONFIG_ARM64_LSE_ATOMICS */
 #endif	/* __ASM_LSE_H */

arch/arm64/include/asm/mmu.h

@@ -29,52 +29,11 @@ typedef struct {
  */
 #define ASID(mm)	((mm)->context.id.counter & 0xffff)
 
-static inline bool arm64_kernel_unmapped_at_el0(void)
-{
-	return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) &&
-	       cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0);
-}
+extern bool arm64_use_ng_mappings;
 
-static inline bool arm64_kernel_use_ng_mappings(void)
+static inline bool arm64_kernel_unmapped_at_el0(void)
 {
-	bool tx1_bug;
-
-	/* What's a kpti? Use global mappings if we don't know. */
-	if (!IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0))
-		return false;
-
-	/*
-	 * Note: this function is called before the CPU capabilities have
-	 * been configured, so our early mappings will be global. If we
-	 * later determine that kpti is required, then
-	 * kpti_install_ng_mappings() will make them non-global.
-	 */
-	if (arm64_kernel_unmapped_at_el0())
-		return true;
-
-	if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE))
-		return false;
-
-	/*
-	 * KASLR is enabled so we're going to be enabling kpti on non-broken
-	 * CPUs regardless of their susceptibility to Meltdown. Rather
-	 * than force everybody to go through the G -> nG dance later on,
-	 * just put down non-global mappings from the beginning.
-	 */
-	if (!IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) {
-		tx1_bug = false;
-#ifndef MODULE
-	} else if (!static_branch_likely(&arm64_const_caps_ready)) {
-		extern const struct midr_range cavium_erratum_27456_cpus[];
-
-		tx1_bug = is_midr_in_range_list(read_cpuid_id(),
-						cavium_erratum_27456_cpus);
-#endif
-	} else {
-		tx1_bug = __cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_27456);
-	}
-
-	return !tx1_bug && kaslr_offset() > 0;
+	return arm64_use_ng_mappings;
 }
 
 typedef void (*bp_hardening_cb_t)(void);
@@ -128,6 +87,7 @@ extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       pgprot_t prot, bool page_mappings_only);
 extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot);
 extern void mark_linear_text_alias_ro(void);
+extern bool kaslr_requires_kpti(void);
 
 #define INIT_MM_CONTEXT(name)	\
 	.pgd = init_pg_dir,

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

@@ -110,6 +110,7 @@
 #define PUD_TABLE_BIT		(_AT(pudval_t, 1) << 1)
 #define PUD_TYPE_MASK		(_AT(pudval_t, 3) << 0)
 #define PUD_TYPE_SECT		(_AT(pudval_t, 1) << 0)
+#define PUD_SECT_RDONLY		(_AT(pudval_t, 1) << 7)		/* AP[2] */
 
 /*
  * Level 2 descriptor (PMD).
@@ -292,6 +293,8 @@
 #define TCR_HD			(UL(1) << 40)
 #define TCR_NFD0		(UL(1) << 53)
 #define TCR_NFD1		(UL(1) << 54)
+#define TCR_E0PD0		(UL(1) << 55)
+#define TCR_E0PD1		(UL(1) << 56)
 
 /*
  * TTBR.

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

@@ -26,8 +26,8 @@
 #define _PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
 #define _PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
 
-#define PTE_MAYBE_NG		(arm64_kernel_use_ng_mappings() ? PTE_NG : 0)
-#define PMD_MAYBE_NG		(arm64_kernel_use_ng_mappings() ? PMD_SECT_NG : 0)
+#define PTE_MAYBE_NG		(arm64_kernel_unmapped_at_el0() ? PTE_NG : 0)
+#define PMD_MAYBE_NG		(arm64_kernel_unmapped_at_el0() ? PMD_SECT_NG : 0)
 
 #define PROT_DEFAULT		(_PROT_DEFAULT | PTE_MAYBE_NG)
 #define PROT_SECT_DEFAULT	(_PROT_SECT_DEFAULT | PMD_MAYBE_NG)

arch/arm64/include/asm/sections.h

@@ -8,7 +8,6 @@
 #include <asm-generic/sections.h>
 
 extern char __alt_instructions[], __alt_instructions_end[];
-extern char __exception_text_start[], __exception_text_end[];
 extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
 extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
 extern char __hyp_text_start[], __hyp_text_end[];

arch/arm64/include/asm/simd.h

@@ -26,6 +26,8 @@ DECLARE_PER_CPU(bool, fpsimd_context_busy);
 static __must_check inline bool may_use_simd(void)
 {
 	/*
+	 * We must make sure that the SVE has been initialized properly
+	 * before using the SIMD in kernel.
 	 * fpsimd_context_busy is only set while preemption is disabled,
 	 * and is clear whenever preemption is enabled. Since
 	 * this_cpu_read() is atomic w.r.t. preemption, fpsimd_context_busy
@@ -33,7 +35,9 @@ static __must_check inline bool may_use_simd(void)
 	 * migrated, and if it's clear we cannot be migrated to a CPU
 	 * where it is set.
 	 */
-	return !in_irq() && !irqs_disabled() && !in_nmi() &&
+	return !WARN_ON(!system_capabilities_finalized()) &&
+	       system_supports_fpsimd() &&
+	       !in_irq() && !irqs_disabled() && !in_nmi() &&
 	       !this_cpu_read(fpsimd_context_busy);
 }
 

arch/arm64/include/asm/sysreg.h

@@ -146,6 +146,7 @@
 #define SYS_ID_ISAR4_EL1		sys_reg(3, 0, 0, 2, 4)
 #define SYS_ID_ISAR5_EL1		sys_reg(3, 0, 0, 2, 5)
 #define SYS_ID_MMFR4_EL1		sys_reg(3, 0, 0, 2, 6)
+#define SYS_ID_ISAR6_EL1		sys_reg(3, 0, 0, 2, 7)
 
 #define SYS_MVFR0_EL1			sys_reg(3, 0, 0, 3, 0)
 #define SYS_MVFR1_EL1			sys_reg(3, 0, 0, 3, 1)
@@ -365,6 +366,9 @@
 #define SYS_CTR_EL0			sys_reg(3, 3, 0, 0, 1)
 #define SYS_DCZID_EL0			sys_reg(3, 3, 0, 0, 7)
 
+#define SYS_RNDR_EL0			sys_reg(3, 3, 2, 4, 0)
+#define SYS_RNDRRS_EL0			sys_reg(3, 3, 2, 4, 1)
+
 #define SYS_PMCR_EL0			sys_reg(3, 3, 9, 12, 0)
 #define SYS_PMCNTENSET_EL0		sys_reg(3, 3, 9, 12, 1)
 #define SYS_PMCNTENCLR_EL0		sys_reg(3, 3, 9, 12, 2)
@@ -538,7 +542,20 @@
 			 SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN |\
 			 ENDIAN_SET_EL1 | SCTLR_EL1_UCI  | SCTLR_EL1_RES1)
 
+/* MAIR_ELx memory attributes (used by Linux) */
+#define MAIR_ATTR_DEVICE_nGnRnE		UL(0x00)
+#define MAIR_ATTR_DEVICE_nGnRE		UL(0x04)
+#define MAIR_ATTR_DEVICE_GRE		UL(0x0c)
+#define MAIR_ATTR_NORMAL_NC		UL(0x44)
+#define MAIR_ATTR_NORMAL_WT		UL(0xbb)
+#define MAIR_ATTR_NORMAL		UL(0xff)
+#define MAIR_ATTR_MASK			UL(0xff)
+
+/* Position the attr at the correct index */
+#define MAIR_ATTRIDX(attr, idx)		((attr) << ((idx) * 8))
+
 /* id_aa64isar0 */
+#define ID_AA64ISAR0_RNDR_SHIFT		60
 #define ID_AA64ISAR0_TS_SHIFT		52
 #define ID_AA64ISAR0_FHM_SHIFT		48
 #define ID_AA64ISAR0_DP_SHIFT		44
@@ -553,6 +570,10 @@
 #define ID_AA64ISAR0_AES_SHIFT		4
 
 /* id_aa64isar1 */
+#define ID_AA64ISAR1_I8MM_SHIFT		52
+#define ID_AA64ISAR1_DGH_SHIFT		48
+#define ID_AA64ISAR1_BF16_SHIFT		44
+#define ID_AA64ISAR1_SPECRES_SHIFT	40
 #define ID_AA64ISAR1_SB_SHIFT		36
 #define ID_AA64ISAR1_FRINTTS_SHIFT	32
 #define ID_AA64ISAR1_GPI_SHIFT		28
@@ -605,12 +626,20 @@
 #define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
 
 /* id_aa64zfr0 */
+#define ID_AA64ZFR0_F64MM_SHIFT		56
+#define ID_AA64ZFR0_F32MM_SHIFT		52
+#define ID_AA64ZFR0_I8MM_SHIFT		44
 #define ID_AA64ZFR0_SM4_SHIFT		40
 #define ID_AA64ZFR0_SHA3_SHIFT		32
+#define ID_AA64ZFR0_BF16_SHIFT		20
 #define ID_AA64ZFR0_BITPERM_SHIFT	16
 #define ID_AA64ZFR0_AES_SHIFT		4
 #define ID_AA64ZFR0_SVEVER_SHIFT	0
 
+#define ID_AA64ZFR0_F64MM		0x1
+#define ID_AA64ZFR0_F32MM		0x1
+#define ID_AA64ZFR0_I8MM		0x1
+#define ID_AA64ZFR0_BF16		0x1
 #define ID_AA64ZFR0_SM4			0x1
 #define ID_AA64ZFR0_SHA3		0x1
 #define ID_AA64ZFR0_BITPERM		0x1
@@ -655,6 +684,7 @@
 #define ID_AA64MMFR1_VMIDBITS_16	2
 
 /* id_aa64mmfr2 */
+#define ID_AA64MMFR2_E0PD_SHIFT		60
 #define ID_AA64MMFR2_FWB_SHIFT		40
 #define ID_AA64MMFR2_AT_SHIFT		32
 #define ID_AA64MMFR2_LVA_SHIFT		16
@@ -679,6 +709,14 @@
 #define ID_ISAR5_AES_SHIFT		4
 #define ID_ISAR5_SEVL_SHIFT		0
 
+#define ID_ISAR6_I8MM_SHIFT		24
+#define ID_ISAR6_BF16_SHIFT		20
+#define ID_ISAR6_SPECRES_SHIFT		16
+#define ID_ISAR6_SB_SHIFT		12
+#define ID_ISAR6_FHM_SHIFT		8
+#define ID_ISAR6_DP_SHIFT		4
+#define ID_ISAR6_JSCVT_SHIFT		0
+
 #define MVFR0_FPROUND_SHIFT		28
 #define MVFR0_FPSHVEC_SHIFT		24
 #define MVFR0_FPSQRT_SHIFT		20

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

@@ -65,5 +65,13 @@
 #define HWCAP2_SVESM4		(1 << 6)
 #define HWCAP2_FLAGM2		(1 << 7)
 #define HWCAP2_FRINT		(1 << 8)
+#define HWCAP2_SVEI8MM		(1 << 9)
+#define HWCAP2_SVEF32MM		(1 << 10)
+#define HWCAP2_SVEF64MM		(1 << 11)
+#define HWCAP2_SVEBF16		(1 << 12)
+#define HWCAP2_I8MM		(1 << 13)
+#define HWCAP2_BF16		(1 << 14)
+#define HWCAP2_DGH		(1 << 15)
+#define HWCAP2_RNG		(1 << 16)
 
 #endif /* _UAPI__ASM_HWCAP_H */

arch/arm64/kernel/acpi.c

@@ -274,7 +274,7 @@ int apei_claim_sea(struct pt_regs *regs)
 	if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES))
 		return err;
 
-	current_flags = arch_local_save_flags();
+	current_flags = local_daif_save_flags();
 
 	/*
 	 * SEA can interrupt SError, mask it and describe this as an NMI so

arch/arm64/kernel/armv8_deprecated.c

@@ -618,7 +618,8 @@ static struct insn_emulation_ops setend_ops = {
 };
 
 /*
- * Invoked as late_initcall, since not needed before init spawned.
+ * Invoked as core_initcall, which guarantees that the instruction
+ * emulation is ready for userspace.
  */
 static int __init armv8_deprecated_init(void)
 {

arch/arm64/kernel/cpu-reset.S

@@ -42,11 +42,11 @@ ENTRY(__cpu_soft_restart)
 	mov	x0, #HVC_SOFT_RESTART
 	hvc	#0				// no return
 
-1:	mov	x18, x1				// entry
+1:	mov	x8, x1				// entry
 	mov	x0, x2				// arg0
 	mov	x1, x3				// arg1
 	mov	x2, x4				// arg2
-	br	x18
+	br	x8
 ENDPROC(__cpu_soft_restart)
 
 .popsection

arch/arm64/kernel/cpu_errata.c

@@ -548,6 +548,8 @@ static const struct midr_range spectre_v2_safe_list[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
 	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
 	MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
+	MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
+	MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
 	{ /* sentinel */ }
 };
 
@@ -757,6 +759,20 @@ static const struct arm64_cpu_capabilities erratum_843419_list[] = {
 };
 #endif
 
+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT_VHE
+static const struct midr_range erratum_speculative_at_vhe_list[] = {
+#ifdef CONFIG_ARM64_ERRATUM_1165522
+	/* Cortex A76 r0p0 to r2p0 */
+	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_1530923
+	/* Cortex A55 r0p0 to r2p0 */
+	MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 2, 0),
+#endif
+	{},
+};
+#endif
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
@@ -883,12 +899,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(erratum_1418040_list),
 	},
 #endif
-#ifdef CONFIG_ARM64_ERRATUM_1165522
+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT_VHE
 	{
-		/* Cortex-A76 r0p0 to r2p0 */
-		.desc = "ARM erratum 1165522",
-		.capability = ARM64_WORKAROUND_1165522,
-		ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
+		.desc = "ARM errata 1165522, 1530923",
+		.capability = ARM64_WORKAROUND_SPECULATIVE_AT_VHE,
+		ERRATA_MIDR_RANGE_LIST(erratum_speculative_at_vhe_list),
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_1463225
@@ -925,7 +940,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_ERRATUM_1319367
 	{
 		.desc = "ARM erratum 1319367",
-		.capability = ARM64_WORKAROUND_1319367,
+		.capability = ARM64_WORKAROUND_SPECULATIVE_AT_NVHE,
 		ERRATA_MIDR_RANGE_LIST(ca57_a72),
 	},
 #endif

arch/arm64/kernel/cpuinfo.c

@@ -84,6 +84,14 @@ static const char *const hwcap_str[] = {
 	"svesm4",
 	"flagm2",
 	"frint",
+	"svei8mm",
+	"svef32mm",
+	"svef64mm",
+	"svebf16",
+	"i8mm",
+	"bf16",
+	"dgh",
+	"rng",
 	NULL
 };
 
@@ -360,6 +368,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 		info->reg_id_isar3 = read_cpuid(ID_ISAR3_EL1);
 		info->reg_id_isar4 = read_cpuid(ID_ISAR4_EL1);
 		info->reg_id_isar5 = read_cpuid(ID_ISAR5_EL1);
+		info->reg_id_isar6 = read_cpuid(ID_ISAR6_EL1);
 		info->reg_id_mmfr0 = read_cpuid(ID_MMFR0_EL1);
 		info->reg_id_mmfr1 = read_cpuid(ID_MMFR1_EL1);
 		info->reg_id_mmfr2 = read_cpuid(ID_MMFR2_EL1);

arch/arm64/kernel/entry-common.c

@@ -36,14 +36,14 @@ static void notrace el1_pc(struct pt_regs *regs, unsigned long esr)
 }
 NOKPROBE_SYMBOL(el1_pc);
 
-static void el1_undef(struct pt_regs *regs)
+static void notrace el1_undef(struct pt_regs *regs)
 {
 	local_daif_inherit(regs);
 	do_undefinstr(regs);
 }
 NOKPROBE_SYMBOL(el1_undef);
 
-static void el1_inv(struct pt_regs *regs, unsigned long esr)
+static void notrace el1_inv(struct pt_regs *regs, unsigned long esr)
 {
 	local_daif_inherit(regs);
 	bad_mode(regs, 0, esr);
@@ -215,7 +215,7 @@ static void notrace el0_svc(struct pt_regs *regs)
 	if (system_uses_irq_prio_masking())
 		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
 
-	el0_svc_handler(regs);
+	do_el0_svc(regs);
 }
 NOKPROBE_SYMBOL(el0_svc);
 
@@ -281,7 +281,7 @@ static void notrace el0_svc_compat(struct pt_regs *regs)
 	if (system_uses_irq_prio_masking())
 		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
 
-	el0_svc_compat_handler(regs);
+	do_el0_svc_compat(regs);
 }
 NOKPROBE_SYMBOL(el0_svc_compat);
 

arch/arm64/kernel/entry.S

@@ -60,16 +60,16 @@
 	.macro kernel_ventry, el, label, regsize = 64
 	.align 7
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-alternative_if ARM64_UNMAP_KERNEL_AT_EL0
 	.if	\el == 0
+alternative_if ARM64_UNMAP_KERNEL_AT_EL0
 	.if	\regsize == 64
 	mrs	x30, tpidrro_el0
 	msr	tpidrro_el0, xzr
 	.else
 	mov	x30, xzr
 	.endif
-	.endif
 alternative_else_nop_endif
+	.endif
 #endif
 
 	sub	sp, sp, #S_FRAME_SIZE
@@ -167,9 +167,13 @@ alternative_cb_end
 	.if	\el == 0
 	clear_gp_regs
 	mrs	x21, sp_el0
-	ldr_this_cpu	tsk, __entry_task, x20	// Ensure MDSCR_EL1.SS is clear,
-	ldr	x19, [tsk, #TSK_TI_FLAGS]	// since we can unmask debug
-	disable_step_tsk x19, x20		// exceptions when scheduling.
+	ldr_this_cpu	tsk, __entry_task, x20
+	msr	sp_el0, tsk
+
+	// Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions
+	// when scheduling.
+	ldr	x19, [tsk, #TSK_TI_FLAGS]
+	disable_step_tsk x19, x20
 
 	apply_ssbd 1, x22, x23
 
@@ -232,13 +236,6 @@ alternative_else_nop_endif
 	str	w21, [sp, #S_SYSCALLNO]
 	.endif
 
-	/*
-	 * Set sp_el0 to current thread_info.
-	 */
-	.if	\el == 0
-	msr	sp_el0, tsk
-	.endif
-
 	/* Save pmr */
 alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	mrs_s	x20, SYS_ICC_PMR_EL1
@@ -653,6 +650,7 @@ el0_sync:
 	mov	x0, sp
 	bl	el0_sync_handler
 	b	ret_to_user
+ENDPROC(el0_sync)
 
 #ifdef CONFIG_COMPAT
 	.align	6
@@ -661,16 +659,18 @@ el0_sync_compat:
 	mov	x0, sp
 	bl	el0_sync_compat_handler
 	b	ret_to_user
-ENDPROC(el0_sync)
+ENDPROC(el0_sync_compat)
 
 	.align	6
 el0_irq_compat:
 	kernel_entry 0, 32
 	b	el0_irq_naked
+ENDPROC(el0_irq_compat)
 
 el0_error_compat:
 	kernel_entry 0, 32
 	b	el0_error_naked
+ENDPROC(el0_error_compat)
 #endif
 
 	.align	6

arch/arm64/kernel/fpsimd.c

@@ -269,6 +269,7 @@ static void sve_free(struct task_struct *task)
  */
 static void task_fpsimd_load(void)
 {
+	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
 
 	if (system_supports_sve() && test_thread_flag(TIF_SVE))
@@ -289,6 +290,7 @@ static void fpsimd_save(void)
 		this_cpu_ptr(&fpsimd_last_state);
 	/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
 
+	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
 
 	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
@@ -1092,6 +1094,7 @@ void fpsimd_bind_task_to_cpu(void)
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
 
+	WARN_ON(!system_supports_fpsimd());
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
 	last->sve_vl = current->thread.sve_vl;
@@ -1114,6 +1117,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
 
+	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!in_softirq() && !irqs_disabled());
 
 	last->st = st;
@@ -1128,8 +1132,19 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
  */
 void fpsimd_restore_current_state(void)
 {
-	if (!system_supports_fpsimd())
+	/*
+	 * For the tasks that were created before we detected the absence of
+	 * FP/SIMD, the TIF_FOREIGN_FPSTATE could be set via fpsimd_thread_switch(),
+	 * e.g, init. This could be then inherited by the children processes.
+	 * If we later detect that the system doesn't support FP/SIMD,
+	 * we must clear the flag for  all the tasks to indicate that the
+	 * FPSTATE is clean (as we can't have one) to avoid looping for ever in
+	 * do_notify_resume().
+	 */
+	if (!system_supports_fpsimd()) {
+		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		return;
+	}
 
 	get_cpu_fpsimd_context();
 
@@ -1148,7 +1163,7 @@ void fpsimd_restore_current_state(void)
  */
 void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 {
-	if (!system_supports_fpsimd())
+	if (WARN_ON(!system_supports_fpsimd()))
 		return;
 
 	get_cpu_fpsimd_context();
@@ -1179,7 +1194,13 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 void fpsimd_flush_task_state(struct task_struct *t)
 {
 	t->thread.fpsimd_cpu = NR_CPUS;
-
+	/*
+	 * If we don't support fpsimd, bail out after we have
+	 * reset the fpsimd_cpu for this task and clear the
+	 * FPSTATE.
+	 */
+	if (!system_supports_fpsimd())
+		return;
 	barrier();
 	set_tsk_thread_flag(t, TIF_FOREIGN_FPSTATE);
 
@@ -1193,6 +1214,7 @@ void fpsimd_flush_task_state(struct task_struct *t)
  */
 static void fpsimd_flush_cpu_state(void)
 {
+	WARN_ON(!system_supports_fpsimd());
 	__this_cpu_write(fpsimd_last_state.st, NULL);
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
 }
@@ -1203,6 +1225,8 @@ static void fpsimd_flush_cpu_state(void)
  */
 void fpsimd_save_and_flush_cpu_state(void)
 {
+	if (!system_supports_fpsimd())
+		return;
 	WARN_ON(preemptible());
 	__get_cpu_fpsimd_context();
 	fpsimd_save();

arch/arm64/kernel/hibernate.c

@@ -182,78 +182,79 @@ int arch_hibernation_header_restore(void *addr)
 }
 EXPORT_SYMBOL(arch_hibernation_header_restore);
 
-/*
- * Copies length bytes, starting at src_start into an new page,
- * perform cache maintentance, then maps it at the specified address low
- * address as executable.
- *
- * This is used by hibernate to copy the code it needs to execute when
- * overwriting the kernel text. This function generates a new set of page
- * tables, which it loads into ttbr0.
- *
- * Length is provided as we probably only want 4K of data, even on a 64K
- * page system.
- */
-static int create_safe_exec_page(void *src_start, size_t length,
+static int trans_pgd_map_page(pgd_t *trans_pgd, void *page,
 		       unsigned long dst_addr,
-				 phys_addr_t *phys_dst_addr,
-				 void *(*allocator)(gfp_t mask),
-				 gfp_t mask)
+		       pgprot_t pgprot)
 {
-	int rc = 0;
-	pgd_t *trans_pgd;
 	pgd_t *pgdp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
-	unsigned long dst = (unsigned long)allocator(mask);
-
-	if (!dst) {
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	memcpy((void *)dst, src_start, length);
-	__flush_icache_range(dst, dst + length);
-
-	trans_pgd = allocator(mask);
-	if (!trans_pgd) {
-		rc = -ENOMEM;
-		goto out;
-	}
 
 	pgdp = pgd_offset_raw(trans_pgd, dst_addr);
 	if (pgd_none(READ_ONCE(*pgdp))) {
-		pudp = allocator(mask);
-		if (!pudp) {
-			rc = -ENOMEM;
-			goto out;
-		}
+		pudp = (void *)get_safe_page(GFP_ATOMIC);
+		if (!pudp)
+			return -ENOMEM;
 		pgd_populate(&init_mm, pgdp, pudp);
 	}
 
 	pudp = pud_offset(pgdp, dst_addr);
 	if (pud_none(READ_ONCE(*pudp))) {
-		pmdp = allocator(mask);
-		if (!pmdp) {
-			rc = -ENOMEM;
-			goto out;
-		}
+		pmdp = (void *)get_safe_page(GFP_ATOMIC);
+		if (!pmdp)
+			return -ENOMEM;
 		pud_populate(&init_mm, pudp, pmdp);
 	}
 
 	pmdp = pmd_offset(pudp, dst_addr);
 	if (pmd_none(READ_ONCE(*pmdp))) {
-		ptep = allocator(mask);
-		if (!ptep) {
-			rc = -ENOMEM;
-			goto out;
-		}
+		ptep = (void *)get_safe_page(GFP_ATOMIC);
+		if (!ptep)
+			return -ENOMEM;
 		pmd_populate_kernel(&init_mm, pmdp, ptep);
 	}
 
 	ptep = pte_offset_kernel(pmdp, dst_addr);
-	set_pte(ptep, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC));
+	set_pte(ptep, pfn_pte(virt_to_pfn(page), PAGE_KERNEL_EXEC));
+
+	return 0;
+}
+
+/*
+ * Copies length bytes, starting at src_start into an new page,
+ * perform cache maintenance, then maps it at the specified address low
+ * address as executable.
+ *
+ * This is used by hibernate to copy the code it needs to execute when
+ * overwriting the kernel text. This function generates a new set of page
+ * tables, which it loads into ttbr0.
+ *
+ * Length is provided as we probably only want 4K of data, even on a 64K
+ * page system.
+ */
+static int create_safe_exec_page(void *src_start, size_t length,
+				 unsigned long dst_addr,
+				 phys_addr_t *phys_dst_addr)
+{
+	void *page = (void *)get_safe_page(GFP_ATOMIC);
+	pgd_t *trans_pgd;
+	int rc;
+
+	if (!page)
+		return -ENOMEM;
+
+	memcpy(page, src_start, length);
+	__flush_icache_range((unsigned long)page, (unsigned long)page + length);
+
+	trans_pgd = (void *)get_safe_page(GFP_ATOMIC);
+	if (!trans_pgd)
+		return -ENOMEM;
+
+	rc = trans_pgd_map_page(trans_pgd, page, dst_addr,
+				PAGE_KERNEL_EXEC);
+	if (rc)
+		return rc;
 
 	/*
 	 * Load our new page tables. A strict BBM approach requires that we
@@ -269,13 +270,12 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	 */
 	cpu_set_reserved_ttbr0();
 	local_flush_tlb_all();
-	write_sysreg(phys_to_ttbr(virt_to_phys(pgdp)), ttbr0_el1);
+	write_sysreg(phys_to_ttbr(virt_to_phys(trans_pgd)), ttbr0_el1);
 	isb();
 
-	*phys_dst_addr = virt_to_phys((void *)dst);
+	*phys_dst_addr = virt_to_phys(page);
 
-out:
-	return rc;
+	return 0;
 }
 
 #define dcache_clean_range(start, end)	__flush_dcache_area(start, (end - start))
@@ -450,7 +450,7 @@ static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
 				return -ENOMEM;
 		} else {
 			set_pud(dst_pudp,
-				__pud(pud_val(pud) & ~PMD_SECT_RDONLY));
+				__pud(pud_val(pud) & ~PUD_SECT_RDONLY));
 		}
 	} while (dst_pudp++, src_pudp++, addr = next, addr != end);
 
@@ -476,6 +476,24 @@ static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
 	return 0;
 }
 
+static int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
+			  unsigned long end)
+{
+	int rc;
+	pgd_t *trans_pgd = (pgd_t *)get_safe_page(GFP_ATOMIC);
+
+	if (!trans_pgd) {
+		pr_err("Failed to allocate memory for temporary page tables.\n");
+		return -ENOMEM;
+	}
+
+	rc = copy_page_tables(trans_pgd, start, end);
+	if (!rc)
+		*dst_pgdp = trans_pgd;
+
+	return rc;
+}
+
 /*
  * Setup then Resume from the hibernate image using swsusp_arch_suspend_exit().
  *
@@ -484,7 +502,7 @@ static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
  */
 int swsusp_arch_resume(void)
 {
-	int rc = 0;
+	int rc;
 	void *zero_page;
 	size_t exit_size;
 	pgd_t *tmp_pg_dir;
@@ -497,15 +515,9 @@ int swsusp_arch_resume(void)
 	 * Create a second copy of just the linear map, and use this when
 	 * restoring.
 	 */
-	tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
-	if (!tmp_pg_dir) {
-		pr_err("Failed to allocate memory for temporary page tables.\n");
-		rc = -ENOMEM;
-		goto out;
-	}
-	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, PAGE_END);
+	rc = trans_pgd_create_copy(&tmp_pg_dir, PAGE_OFFSET, PAGE_END);
 	if (rc)
-		goto out;
+		return rc;
 
 	/*
 	 * We need a zero page that is zero before & after resume in order to
@@ -514,8 +526,7 @@ int swsusp_arch_resume(void)
 	zero_page = (void *)get_safe_page(GFP_ATOMIC);
 	if (!zero_page) {
 		pr_err("Failed to allocate zero page.\n");
-		rc = -ENOMEM;
-		goto out;
+		return -ENOMEM;
 	}
 
 	/*
@@ -530,11 +541,10 @@ int swsusp_arch_resume(void)
 	 */
 	rc = create_safe_exec_page(__hibernate_exit_text_start, exit_size,
 				   (unsigned long)hibernate_exit,
-				   &phys_hibernate_exit,
-				   (void *)get_safe_page, GFP_ATOMIC);
+				   &phys_hibernate_exit);
 	if (rc) {
 		pr_err("Failed to create safe executable page for hibernate_exit code.\n");
-		goto out;
+		return rc;
 	}
 
 	/*
@@ -561,8 +571,7 @@ int swsusp_arch_resume(void)
 		       resume_hdr.reenter_kernel, restore_pblist,
 		       resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page));
 
-out:
-	return rc;
+	return 0;
 }
 
 int hibernate_resume_nonboot_cpu_disable(void)

arch/arm64/kernel/kaslr.c

@@ -120,6 +120,17 @@ u64 __init kaslr_early_init(u64 dt_phys)
 		return 0;
 	}
 
+	/*
+	 * Mix in any entropy obtainable architecturally, open coded
+	 * since this runs extremely early.
+	 */
+	if (__early_cpu_has_rndr()) {
+		unsigned long raw;
+
+		if (__arm64_rndr(&raw))
+			seed ^= raw;
+	}
+
 	if (!seed) {
 		kaslr_status = KASLR_DISABLED_NO_SEED;
 		return 0;

arch/arm64/kernel/kexec_image.c

@@ -47,10 +47,6 @@ static void *image_load(struct kimage *image,
 	struct kexec_segment *kernel_segment;
 	int ret;
 
-	/* We don't support crash kernels yet. */
-	if (image->type == KEXEC_TYPE_CRASH)
-		return ERR_PTR(-EOPNOTSUPP);
-
 	/*
 	 * We require a kernel with an unambiguous Image header. Per
 	 * Documentation/arm64/booting.rst, this is the case when image_size

arch/arm64/kernel/machine_kexec.c

@@ -160,18 +160,6 @@ void machine_kexec(struct kimage *kimage)
 
 	kexec_image_info(kimage);
 
-	pr_debug("%s:%d: control_code_page:        %p\n", __func__, __LINE__,
-		kimage->control_code_page);
-	pr_debug("%s:%d: reboot_code_buffer_phys:  %pa\n", __func__, __LINE__,
-		&reboot_code_buffer_phys);
-	pr_debug("%s:%d: reboot_code_buffer:       %p\n", __func__, __LINE__,
-		reboot_code_buffer);
-	pr_debug("%s:%d: relocate_new_kernel:      %p\n", __func__, __LINE__,
-		arm64_relocate_new_kernel);
-	pr_debug("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n",
-		__func__, __LINE__, arm64_relocate_new_kernel_size,
-		arm64_relocate_new_kernel_size);
-
 	/*
 	 * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use
 	 * after the kernel is shut down.

arch/arm64/kernel/machine_kexec_file.c

@@ -17,12 +17,15 @@
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/random.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 #include <asm/byteorder.h>
 
 /* relevant device tree properties */
+#define FDT_PROP_KEXEC_ELFHDR	"linux,elfcorehdr"
+#define FDT_PROP_MEM_RANGE	"linux,usable-memory-range"
 #define FDT_PROP_INITRD_START	"linux,initrd-start"
 #define FDT_PROP_INITRD_END	"linux,initrd-end"
 #define FDT_PROP_BOOTARGS	"bootargs"
@@ -40,6 +43,10 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image)
 	vfree(image->arch.dtb);
 	image->arch.dtb = NULL;
 
+	vfree(image->arch.elf_headers);
+	image->arch.elf_headers = NULL;
+	image->arch.elf_headers_sz = 0;
+
 	return kexec_image_post_load_cleanup_default(image);
 }
 
@@ -55,6 +62,31 @@ static int setup_dtb(struct kimage *image,
 
 	off = ret;
 
+	ret = fdt_delprop(dtb, off, FDT_PROP_KEXEC_ELFHDR);
+	if (ret && ret != -FDT_ERR_NOTFOUND)
+		goto out;
+	ret = fdt_delprop(dtb, off, FDT_PROP_MEM_RANGE);
+	if (ret && ret != -FDT_ERR_NOTFOUND)
+		goto out;
+
+	if (image->type == KEXEC_TYPE_CRASH) {
+		/* add linux,elfcorehdr */
+		ret = fdt_appendprop_addrrange(dtb, 0, off,
+				FDT_PROP_KEXEC_ELFHDR,
+				image->arch.elf_headers_mem,
+				image->arch.elf_headers_sz);
+		if (ret)
+			return (ret == -FDT_ERR_NOSPACE ? -ENOMEM : -EINVAL);
+
+		/* add linux,usable-memory-range */
+		ret = fdt_appendprop_addrrange(dtb, 0, off,
+				FDT_PROP_MEM_RANGE,
+				crashk_res.start,
+				crashk_res.end - crashk_res.start + 1);
+		if (ret)
+			return (ret == -FDT_ERR_NOSPACE ? -ENOMEM : -EINVAL);
+	}
+
 	/* add bootargs */
 	if (cmdline) {
 		ret = fdt_setprop_string(dtb, off, FDT_PROP_BOOTARGS, cmdline);
@@ -125,8 +157,8 @@ static int setup_dtb(struct kimage *image,
 }
 
 /*
- * More space needed so that we can add initrd, bootargs, kaslr-seed, and
- * rng-seed.
+ * More space needed so that we can add initrd, bootargs, kaslr-seed,
+ * rng-seed, userable-memory-range and elfcorehdr.
  */
 #define DTB_EXTRA_SPACE 0x1000
 
@@ -174,6 +206,43 @@ static int create_dtb(struct kimage *image,
 	}
 }
 
+static int prepare_elf_headers(void **addr, unsigned long *sz)
+{
+	struct crash_mem *cmem;
+	unsigned int nr_ranges;
+	int ret;
+	u64 i;
+	phys_addr_t start, end;
+
+	nr_ranges = 1; /* for exclusion of crashkernel region */
+	for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
+					MEMBLOCK_NONE, &start, &end, NULL)
+		nr_ranges++;
+
+	cmem = kmalloc(sizeof(struct crash_mem) +
+			sizeof(struct crash_mem_range) * nr_ranges, GFP_KERNEL);
+	if (!cmem)
+		return -ENOMEM;
+
+	cmem->max_nr_ranges = nr_ranges;
+	cmem->nr_ranges = 0;
+	for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
+					MEMBLOCK_NONE, &start, &end, NULL) {
+		cmem->ranges[cmem->nr_ranges].start = start;
+		cmem->ranges[cmem->nr_ranges].end = end - 1;
+		cmem->nr_ranges++;
+	}
+
+	/* Exclude crashkernel region */
+	ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
+
+	if (!ret)
+		ret =  crash_prepare_elf64_headers(cmem, true, addr, sz);
+
+	kfree(cmem);
+	return ret;
+}
+
 int load_other_segments(struct kimage *image,
 			unsigned long kernel_load_addr,
 			unsigned long kernel_size,
@@ -181,14 +250,43 @@ int load_other_segments(struct kimage *image,
 			char *cmdline)
 {
 	struct kexec_buf kbuf;
-	void *dtb = NULL;
-	unsigned long initrd_load_addr = 0, dtb_len;
+	void *headers, *dtb = NULL;
+	unsigned long headers_sz, initrd_load_addr = 0, dtb_len;
 	int ret = 0;
 
 	kbuf.image = image;
 	/* not allocate anything below the kernel */
 	kbuf.buf_min = kernel_load_addr + kernel_size;
 
+	/* load elf core header */
+	if (image->type == KEXEC_TYPE_CRASH) {
+		ret = prepare_elf_headers(&headers, &headers_sz);
+		if (ret) {
+			pr_err("Preparing elf core header failed\n");
+			goto out_err;
+		}
+
+		kbuf.buffer = headers;
+		kbuf.bufsz = headers_sz;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+		kbuf.memsz = headers_sz;
+		kbuf.buf_align = SZ_64K; /* largest supported page size */
+		kbuf.buf_max = ULONG_MAX;
+		kbuf.top_down = true;
+
+		ret = kexec_add_buffer(&kbuf);
+		if (ret) {
+			vfree(headers);
+			goto out_err;
+		}
+		image->arch.elf_headers = headers;
+		image->arch.elf_headers_mem = kbuf.mem;
+		image->arch.elf_headers_sz = headers_sz;
+
+		pr_debug("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+			 image->arch.elf_headers_mem, headers_sz, headers_sz);
+	}
+
 	/* load initrd */
 	if (initrd) {
 		kbuf.buffer = initrd;

arch/arm64/kernel/process.c

@@ -646,6 +646,6 @@ asmlinkage void __sched arm64_preempt_schedule_irq(void)
 	 * Only allow a task to be preempted once cpufeatures have been
 	 * enabled.
 	 */
-	if (static_branch_likely(&arm64_const_caps_ready))
+	if (system_capabilities_finalized())
 		preempt_schedule_irq();
 }

arch/arm64/kernel/ptrace.c

@@ -615,6 +615,13 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
 	return 0;
 }
 
+static int fpr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!system_supports_fpsimd())
+		return -ENODEV;
+	return regset->n;
+}
+
 /*
  * TODO: update fp accessors for lazy context switching (sync/flush hwstate)
  */
@@ -637,6 +644,9 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset,
 		   unsigned int pos, unsigned int count,
 		   void *kbuf, void __user *ubuf)
 {
+	if (!system_supports_fpsimd())
+		return -EINVAL;
+
 	if (target == current)
 		fpsimd_preserve_current_state();
 
@@ -676,6 +686,9 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 {
 	int ret;
 
+	if (!system_supports_fpsimd())
+		return -EINVAL;
+
 	ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0);
 	if (ret)
 		return ret;
@@ -1134,6 +1147,7 @@ static const struct user_regset aarch64_regsets[] = {
 		 */
 		.size = sizeof(u32),
 		.align = sizeof(u32),
+		.active = fpr_active,
 		.get = fpr_get,
 		.set = fpr_set
 	},
@@ -1348,6 +1362,9 @@ static int compat_vfp_get(struct task_struct *target,
 	compat_ulong_t fpscr;
 	int ret, vregs_end_pos;
 
+	if (!system_supports_fpsimd())
+		return -EINVAL;
+
 	uregs = &target->thread.uw.fpsimd_state;
 
 	if (target == current)
@@ -1381,6 +1398,9 @@ static int compat_vfp_set(struct task_struct *target,
 	compat_ulong_t fpscr;
 	int ret, vregs_end_pos;
 
+	if (!system_supports_fpsimd())
+		return -EINVAL;
+
 	uregs = &target->thread.uw.fpsimd_state;
 
 	vregs_end_pos = VFP_STATE_SIZE - sizeof(compat_ulong_t);
@@ -1438,6 +1458,7 @@ static const struct user_regset aarch32_regsets[] = {
 		.n = VFP_STATE_SIZE / sizeof(compat_ulong_t),
 		.size = sizeof(compat_ulong_t),
 		.align = sizeof(compat_ulong_t),
+		.active = fpr_active,
 		.get = compat_vfp_get,
 		.set = compat_vfp_set
 	},

arch/arm64/kernel/setup.c

@@ -285,6 +285,13 @@ void __init setup_arch(char **cmdline_p)
 
 	*cmdline_p = boot_command_line;
 
+	/*
+	 * If know now we are going to need KPTI then use non-global
+	 * mappings from the start, avoiding the cost of rewriting
+	 * everything later.
+	 */
+	arm64_use_ng_mappings = kaslr_requires_kpti();
+
 	early_fixmap_init();
 	early_ioremap_init();
 

arch/arm64/kernel/signal.c

@@ -371,6 +371,8 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			goto done;
 
 		case FPSIMD_MAGIC:
+			if (!system_supports_fpsimd())
+				goto invalid;
 			if (user->fpsimd)
 				goto invalid;
 
@@ -506,7 +508,7 @@ static int restore_sigframe(struct pt_regs *regs,
 	if (err == 0)
 		err = parse_user_sigframe(&user, sf);
 
-	if (err == 0) {
+	if (err == 0 && system_supports_fpsimd()) {
 		if (!user.fpsimd)
 			return -EINVAL;
 
@@ -623,7 +625,7 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set));
 
-	if (err == 0) {
+	if (err == 0 && system_supports_fpsimd()) {
 		struct fpsimd_context __user *fpsimd_ctx =
 			apply_user_offset(user, user->fpsimd_offset);
 		err |= preserve_fpsimd_context(fpsimd_ctx);

arch/arm64/kernel/signal32.c

@@ -223,7 +223,7 @@ static int compat_restore_sigframe(struct pt_regs *regs,
 	err |= !valid_user_regs(&regs->user_regs, current);
 
 	aux = (struct compat_aux_sigframe __user *) sf->uc.uc_regspace;
-	if (err == 0)
+	if (err == 0 && system_supports_fpsimd())
 		err |= compat_restore_vfp_context(&aux->vfp);
 
 	return err;
@@ -419,7 +419,7 @@ static int compat_setup_sigframe(struct compat_sigframe __user *sf,
 
 	aux = (struct compat_aux_sigframe __user *) sf->uc.uc_regspace;
 
-	if (err == 0)
+	if (err == 0 && system_supports_fpsimd())
 		err |= compat_preserve_vfp_context(&aux->vfp);
 	__put_user_error(0, &aux->end_magic, err);
 

arch/arm64/kernel/ssbd.c

@@ -37,7 +37,7 @@ static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl)
 
 	/* Unsupported */
 	if (state == ARM64_SSBD_UNKNOWN)
-		return -EINVAL;
+		return -ENODEV;
 
 	/* Treat the unaffected/mitigated state separately */
 	if (state == ARM64_SSBD_MITIGATED) {
@@ -102,7 +102,7 @@ static int ssbd_prctl_get(struct task_struct *task)
 {
 	switch (arm64_get_ssbd_state()) {
 	case ARM64_SSBD_UNKNOWN:
-		return -EINVAL;
+		return -ENODEV;
 	case ARM64_SSBD_FORCE_ENABLE:
 		return PR_SPEC_DISABLE;
 	case ARM64_SSBD_KERNEL:

arch/arm64/kernel/syscall.c

@@ -154,14 +154,14 @@ static inline void sve_user_discard(void)
 	sve_user_disable();
 }
 
-void el0_svc_handler(struct pt_regs *regs)
+void do_el0_svc(struct pt_regs *regs)
 {
 	sve_user_discard();
 	el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
 }
 
 #ifdef CONFIG_COMPAT
-void el0_svc_compat_handler(struct pt_regs *regs)
+void do_el0_svc_compat(struct pt_regs *regs)
 {
 	el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls,
 		       compat_sys_call_table);

arch/arm64/kvm/hyp/entry.S

@@ -22,7 +22,12 @@
 	.text
 	.pushsection	.hyp.text, "ax"
 
+/*
+ * We treat x18 as callee-saved as the host may use it as a platform
+ * register (e.g. for shadow call stack).
+ */
 .macro save_callee_saved_regs ctxt
+	str	x18,      [\ctxt, #CPU_XREG_OFFSET(18)]
 	stp	x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)]
 	stp	x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)]
 	stp	x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)]
@@ -32,6 +37,8 @@
 .endm
 
 .macro restore_callee_saved_regs ctxt
+	// We require \ctxt is not x18-x28
+	ldr	x18,      [\ctxt, #CPU_XREG_OFFSET(18)]
 	ldp	x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)]
 	ldp	x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)]
 	ldp	x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)]
@@ -48,7 +55,7 @@ ENTRY(__guest_enter)
 	// x0: vcpu
 	// x1: host context
 	// x2-x17: clobbered by macros
-	// x18: guest context
+	// x29: guest context
 
 	// Store the host regs
 	save_callee_saved_regs x1
@@ -67,31 +74,28 @@ alternative_else_nop_endif
 	ret
 
 1:
-	add	x18, x0, #VCPU_CONTEXT
+	add	x29, x0, #VCPU_CONTEXT
 
 	// Macro ptrauth_switch_to_guest format:
 	// 	ptrauth_switch_to_guest(guest cxt, tmp1, tmp2, tmp3)
 	// The below macro to restore guest keys is not implemented in C code
 	// as it may cause Pointer Authentication key signing mismatch errors
 	// when this feature is enabled for kernel code.
-	ptrauth_switch_to_guest x18, x0, x1, x2
+	ptrauth_switch_to_guest x29, x0, x1, x2
 
 	// Restore guest regs x0-x17
-	ldp	x0, x1,   [x18, #CPU_XREG_OFFSET(0)]
-	ldp	x2, x3,   [x18, #CPU_XREG_OFFSET(2)]
-	ldp	x4, x5,   [x18, #CPU_XREG_OFFSET(4)]
-	ldp	x6, x7,   [x18, #CPU_XREG_OFFSET(6)]
-	ldp	x8, x9,   [x18, #CPU_XREG_OFFSET(8)]
-	ldp	x10, x11, [x18, #CPU_XREG_OFFSET(10)]
-	ldp	x12, x13, [x18, #CPU_XREG_OFFSET(12)]
-	ldp	x14, x15, [x18, #CPU_XREG_OFFSET(14)]
-	ldp	x16, x17, [x18, #CPU_XREG_OFFSET(16)]
-
-	// Restore guest regs x19-x29, lr
-	restore_callee_saved_regs x18
-
-	// Restore guest reg x18
-	ldr	x18,      [x18, #CPU_XREG_OFFSET(18)]
+	ldp	x0, x1,   [x29, #CPU_XREG_OFFSET(0)]
+	ldp	x2, x3,   [x29, #CPU_XREG_OFFSET(2)]
+	ldp	x4, x5,   [x29, #CPU_XREG_OFFSET(4)]
+	ldp	x6, x7,   [x29, #CPU_XREG_OFFSET(6)]
+	ldp	x8, x9,   [x29, #CPU_XREG_OFFSET(8)]
+	ldp	x10, x11, [x29, #CPU_XREG_OFFSET(10)]
+	ldp	x12, x13, [x29, #CPU_XREG_OFFSET(12)]
+	ldp	x14, x15, [x29, #CPU_XREG_OFFSET(14)]
+	ldp	x16, x17, [x29, #CPU_XREG_OFFSET(16)]
+
+	// Restore guest regs x18-x29, lr
+	restore_callee_saved_regs x29
 
 	// Do not touch any register after this!
 	eret
@@ -114,7 +118,7 @@ ENTRY(__guest_exit)
 	// Retrieve the guest regs x0-x1 from the stack
 	ldp	x2, x3, [sp], #16	// x0, x1
 
-	// Store the guest regs x0-x1 and x4-x18
+	// Store the guest regs x0-x1 and x4-x17
 	stp	x2, x3,   [x1, #CPU_XREG_OFFSET(0)]
 	stp	x4, x5,   [x1, #CPU_XREG_OFFSET(4)]
 	stp	x6, x7,   [x1, #CPU_XREG_OFFSET(6)]
@@ -123,9 +127,8 @@ ENTRY(__guest_exit)
 	stp	x12, x13, [x1, #CPU_XREG_OFFSET(12)]
 	stp	x14, x15, [x1, #CPU_XREG_OFFSET(14)]
 	stp	x16, x17, [x1, #CPU_XREG_OFFSET(16)]
-	str	x18,      [x1, #CPU_XREG_OFFSET(18)]
 
-	// Store the guest regs x19-x29, lr
+	// Store the guest regs x18-x29, lr
 	save_callee_saved_regs x1
 
 	get_host_ctxt	x2, x3

arch/arm64/kvm/hyp/switch.c

@@ -28,7 +28,15 @@
 /* Check whether the FP regs were dirtied while in the host-side run loop: */
 static bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
+	/*
+	 * When the system doesn't support FP/SIMD, we cannot rely on
+	 * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an
+	 * abort on the very first access to FP and thus we should never
+	 * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always
+	 * trap the accesses.
+	 */
+	if (!system_supports_fpsimd() ||
+	    vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
 		vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
 				      KVM_ARM64_FP_HOST);
 
@@ -119,7 +127,7 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
 
 	write_sysreg(val, cptr_el2);
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
 		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
 
 		isb();
@@ -158,11 +166,11 @@ static void deactivate_traps_vhe(void)
 	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
 
 	/*
-	 * ARM erratum 1165522 requires the actual execution of the above
-	 * before we can switch to the EL2/EL0 translation regime used by
+	 * ARM errata 1165522 and 1530923 require the actual execution of the
+	 * above before we can switch to the EL2/EL0 translation regime used by
 	 * the host.
 	 */
-	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_1165522));
+	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT_VHE));
 
 	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
 	write_sysreg(vectors, vbar_el1);
@@ -173,7 +181,7 @@ static void __hyp_text __deactivate_traps_nvhe(void)
 {
 	u64 mdcr_el2 = read_sysreg(mdcr_el2);
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
 		u64 val;
 
 		/*

arch/arm64/kvm/hyp/sysreg-sr.c

@@ -118,7 +118,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
 	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
 
-	if (!cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+	if (!cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
 		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
 		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
 	} else	if (!ctxt->__hyp_running_vcpu) {
@@ -149,7 +149,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL1],		tpidr_el1);
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367) &&
+	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE) &&
 	    ctxt->__hyp_running_vcpu) {
 		/*
 		 * Must only be done for host registers, hence the context

arch/arm64/kvm/hyp/tlb.c

@@ -23,10 +23,10 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
 
 	local_irq_save(cxt->flags);
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_1165522)) {
+	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
 		/*
-		 * For CPUs that are affected by ARM erratum 1165522, we
-		 * cannot trust stage-1 to be in a correct state at that
+		 * For CPUs that are affected by ARM errata 1165522 or 1530923,
+		 * we cannot trust stage-1 to be in a correct state at that
 		 * point. Since we do not want to force a full load of the
 		 * vcpu state, we prevent the EL1 page-table walker to
 		 * allocate new TLBs. This is done by setting the EPD bits
@@ -63,7 +63,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
 static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
 						  struct tlb_inv_context *cxt)
 {
-	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
 		u64 val;
 
 		/*
@@ -103,7 +103,7 @@ static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
 	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
 	isb();
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_1165522)) {
+	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
 		/* Restore the registers to what they were */
 		write_sysreg_el1(cxt->tcr, SYS_TCR);
 		write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
@@ -117,7 +117,7 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
 {
 	write_sysreg(0, vttbr_el2);
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
 		/* Ensure write of the host VMID */
 		isb();
 		/* Restore the host's TCR_EL1 */

arch/arm64/kvm/sys_regs.c

@@ -1424,7 +1424,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_SANITISED(ID_ISAR4_EL1),
 	ID_SANITISED(ID_ISAR5_EL1),
 	ID_SANITISED(ID_MMFR4_EL1),
-	ID_UNALLOCATED(2,7),
+	ID_SANITISED(ID_ISAR6_EL1),
 
 	/* CRm=3 */
 	ID_SANITISED(MVFR0_EL1),

arch/arm64/lib/Makefile

 # SPDX-License-Identifier: GPL-2.0
 lib-y		:= clear_user.o delay.o copy_from_user.o		\
 		   copy_to_user.o copy_in_user.o copy_page.o		\
-		   clear_page.o memchr.o memcpy.o memmove.o memset.o	\
-		   memcmp.o strcmp.o strncmp.o strlen.o strnlen.o	\
-		   strchr.o strrchr.o tishift.o
+		   clear_page.o csum.o memchr.o memcpy.o memmove.o	\
+		   memset.o memcmp.o strcmp.o strncmp.o strlen.o	\
+		   strnlen.o strchr.o strrchr.o tishift.o
 
 ifeq ($(CONFIG_KERNEL_MODE_NEON), y)
 obj-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o

arch/arm64/lib/clear_page.S

@@ -14,7 +14,7 @@
  * Parameters:
  *	x0 - dest
  */
-ENTRY(clear_page)
+SYM_FUNC_START(clear_page)
 	mrs	x1, dczid_el0
 	and	w1, w1, #0xf
 	mov	x2, #4
@@ -25,5 +25,5 @@ ENTRY(clear_page)
 	tst	x0, #(PAGE_SIZE - 1)
 	b.ne	1b
 	ret
-ENDPROC(clear_page)
+SYM_FUNC_END(clear_page)
 EXPORT_SYMBOL(clear_page)

arch/arm64/lib/clear_user.S

@@ -19,7 +19,7 @@
  *
  * Alignment fixed up by hardware.
  */
-ENTRY(__arch_clear_user)
+SYM_FUNC_START(__arch_clear_user)
 	mov	x2, x1			// save the size for fixup return
 	subs	x1, x1, #8
 	b.mi	2f
@@ -40,7 +40,7 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2
 uao_user_alternative 9f, strb, sttrb, wzr, x0, 0
 5:	mov	x0, #0
 	ret
-ENDPROC(__arch_clear_user)
+SYM_FUNC_END(__arch_clear_user)
 EXPORT_SYMBOL(__arch_clear_user)
 
 	.section .fixup,"ax"

arch/arm64/lib/copy_from_user.S

@@ -53,12 +53,12 @@
 	.endm
 
 end	.req	x5
-ENTRY(__arch_copy_from_user)
+SYM_FUNC_START(__arch_copy_from_user)
 	add	end, x0, x2
 #include "copy_template.S"
 	mov	x0, #0				// Nothing to copy
 	ret
-ENDPROC(__arch_copy_from_user)
+SYM_FUNC_END(__arch_copy_from_user)
 EXPORT_SYMBOL(__arch_copy_from_user)
 
 	.section .fixup,"ax"

arch/arm64/lib/copy_in_user.S

@@ -55,12 +55,12 @@
 
 end	.req	x5
 
-ENTRY(__arch_copy_in_user)
+SYM_FUNC_START(__arch_copy_in_user)
 	add	end, x0, x2
 #include "copy_template.S"
 	mov	x0, #0
 	ret
-ENDPROC(__arch_copy_in_user)
+SYM_FUNC_END(__arch_copy_in_user)
 EXPORT_SYMBOL(__arch_copy_in_user)
 
 	.section .fixup,"ax"

arch/arm64/lib/copy_page.S

@@ -17,7 +17,7 @@
  *	x0 - dest
  *	x1 - src
  */
-ENTRY(copy_page)
+SYM_FUNC_START(copy_page)
 alternative_if ARM64_HAS_NO_HW_PREFETCH
 	// Prefetch three cache lines ahead.
 	prfm	pldl1strm, [x1, #128]
@@ -34,46 +34,46 @@ alternative_else_nop_endif
 	ldp	x14, x15, [x1, #96]
 	ldp	x16, x17, [x1, #112]
 
-	mov	x18, #(PAGE_SIZE - 128)
+	add	x0, x0, #256
 	add	x1, x1, #128
 1:
-	subs	x18, x18, #128
+	tst	x0, #(PAGE_SIZE - 1)
 
 alternative_if ARM64_HAS_NO_HW_PREFETCH
 	prfm	pldl1strm, [x1, #384]
 alternative_else_nop_endif
 
-	stnp	x2, x3, [x0]
+	stnp	x2, x3, [x0, #-256]
 	ldp	x2, x3, [x1]
-	stnp	x4, x5, [x0, #16]
+	stnp	x4, x5, [x0, #16 - 256]
 	ldp	x4, x5, [x1, #16]
-	stnp	x6, x7, [x0, #32]
+	stnp	x6, x7, [x0, #32 - 256]
 	ldp	x6, x7, [x1, #32]
-	stnp	x8, x9, [x0, #48]
+	stnp	x8, x9, [x0, #48 - 256]
 	ldp	x8, x9, [x1, #48]
-	stnp	x10, x11, [x0, #64]
+	stnp	x10, x11, [x0, #64 - 256]
 	ldp	x10, x11, [x1, #64]
-	stnp	x12, x13, [x0, #80]
+	stnp	x12, x13, [x0, #80 - 256]
 	ldp	x12, x13, [x1, #80]
-	stnp	x14, x15, [x0, #96]
+	stnp	x14, x15, [x0, #96 - 256]
 	ldp	x14, x15, [x1, #96]
-	stnp	x16, x17, [x0, #112]
+	stnp	x16, x17, [x0, #112 - 256]
 	ldp	x16, x17, [x1, #112]
 
 	add	x0, x0, #128
 	add	x1, x1, #128
 
-	b.gt	1b
+	b.ne	1b
 
-	stnp	x2, x3, [x0]
-	stnp	x4, x5, [x0, #16]
-	stnp	x6, x7, [x0, #32]
-	stnp	x8, x9, [x0, #48]
-	stnp	x10, x11, [x0, #64]
-	stnp	x12, x13, [x0, #80]
-	stnp	x14, x15, [x0, #96]
-	stnp	x16, x17, [x0, #112]
+	stnp	x2, x3, [x0, #-256]
+	stnp	x4, x5, [x0, #16 - 256]
+	stnp	x6, x7, [x0, #32 - 256]
+	stnp	x8, x9, [x0, #48 - 256]
+	stnp	x10, x11, [x0, #64 - 256]
+	stnp	x12, x13, [x0, #80 - 256]
+	stnp	x14, x15, [x0, #96 - 256]
+	stnp	x16, x17, [x0, #112 - 256]
 
 	ret
-ENDPROC(copy_page)
+SYM_FUNC_END(copy_page)
 EXPORT_SYMBOL(copy_page)

arch/arm64/lib/copy_to_user.S

@@ -52,12 +52,12 @@
 	.endm
 
 end	.req	x5
-ENTRY(__arch_copy_to_user)
+SYM_FUNC_START(__arch_copy_to_user)
 	add	end, x0, x2
 #include "copy_template.S"
 	mov	x0, #0
 	ret
-ENDPROC(__arch_copy_to_user)
+SYM_FUNC_END(__arch_copy_to_user)
 EXPORT_SYMBOL(__arch_copy_to_user)
 
 	.section .fixup,"ax"

arch/arm64/lib/crc32.S

@@ -85,17 +85,17 @@ CPU_BE(	rev16		w3, w3		)
 	.endm
 
 	.align		5
-ENTRY(crc32_le)
+SYM_FUNC_START(crc32_le)
 alternative_if_not ARM64_HAS_CRC32
 	b		crc32_le_base
 alternative_else_nop_endif
 	__crc32
-ENDPROC(crc32_le)
+SYM_FUNC_END(crc32_le)
 
 	.align		5
-ENTRY(__crc32c_le)
+SYM_FUNC_START(__crc32c_le)
 alternative_if_not ARM64_HAS_CRC32
 	b		__crc32c_le_base
 alternative_else_nop_endif
 	__crc32		c
-ENDPROC(__crc32c_le)
+SYM_FUNC_END(__crc32c_le)

arch/arm64/lib/csum.c

+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019-2020 Arm Ltd.
+
+#include <linux/compiler.h>
+#include <linux/kasan-checks.h>
+#include <linux/kernel.h>
+
+#include <net/checksum.h>
+
+/* Looks dumb, but generates nice-ish code */
+static u64 accumulate(u64 sum, u64 data)
+{
+	__uint128_t tmp = (__uint128_t)sum + data;
+	return tmp + (tmp >> 64);
+}
+
+unsigned int do_csum(const unsigned char *buff, int len)
+{
+	unsigned int offset, shift, sum;
+	const u64 *ptr;
+	u64 data, sum64 = 0;
+
+	if (unlikely(len == 0))
+		return 0;
+
+	offset = (unsigned long)buff & 7;
+	/*
+	 * This is to all intents and purposes safe, since rounding down cannot
+	 * result in a different page or cache line being accessed, and @buff
+	 * should absolutely not be pointing to anything read-sensitive. We do,
+	 * however, have to be careful not to piss off KASAN, which means using
+	 * unchecked reads to accommodate the head and tail, for which we'll
+	 * compensate with an explicit check up-front.
+	 */
+	kasan_check_read(buff, len);
+	ptr = (u64 *)(buff - offset);
+	len = len + offset - 8;
+
+	/*
+	 * Head: zero out any excess leading bytes. Shifting back by the same
+	 * amount should be at least as fast as any other way of handling the
+	 * odd/even alignment, and means we can ignore it until the very end.
+	 */
+	shift = offset * 8;
+	data = READ_ONCE_NOCHECK(*ptr++);
+#ifdef __LITTLE_ENDIAN
+	data = (data >> shift) << shift;
+#else
+	data = (data << shift) >> shift;
+#endif
+
+	/*
+	 * Body: straightforward aligned loads from here on (the paired loads
+	 * underlying the quadword type still only need dword alignment). The
+	 * main loop strictly excludes the tail, so the second loop will always
+	 * run at least once.
+	 */
+	while (unlikely(len > 64)) {
+		__uint128_t tmp1, tmp2, tmp3, tmp4;
+
+		tmp1 = READ_ONCE_NOCHECK(*(__uint128_t *)ptr);
+		tmp2 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 2));
+		tmp3 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 4));
+		tmp4 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 6));
+
+		len -= 64;
+		ptr += 8;
+
+		/* This is the "don't dump the carry flag into a GPR" idiom */
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp2 += (tmp2 >> 64) | (tmp2 << 64);
+		tmp3 += (tmp3 >> 64) | (tmp3 << 64);
+		tmp4 += (tmp4 >> 64) | (tmp4 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | (tmp2 >> 64);
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp3 = ((tmp3 >> 64) << 64) | (tmp4 >> 64);
+		tmp3 += (tmp3 >> 64) | (tmp3 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | (tmp3 >> 64);
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | sum64;
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		sum64 = tmp1 >> 64;
+	}
+	while (len > 8) {
+		__uint128_t tmp;
+
+		sum64 = accumulate(sum64, data);
+		tmp = READ_ONCE_NOCHECK(*(__uint128_t *)ptr);
+
+		len -= 16;
+		ptr += 2;
+
+#ifdef __LITTLE_ENDIAN
+		data = tmp >> 64;
+		sum64 = accumulate(sum64, tmp);
+#else
+		data = tmp;
+		sum64 = accumulate(sum64, tmp >> 64);
+#endif
+	}
+	if (len > 0) {
+		sum64 = accumulate(sum64, data);
+		data = READ_ONCE_NOCHECK(*ptr);
+		len -= 8;
+	}
+	/*
+	 * Tail: zero any over-read bytes similarly to the head, again
+	 * preserving odd/even alignment.
+	 */
+	shift = len * -8;
+#ifdef __LITTLE_ENDIAN
+	data = (data << shift) >> shift;
+#else
+	data = (data >> shift) << shift;
+#endif
+	sum64 = accumulate(sum64, data);
+
+	/* Finally, folding */
+	sum64 += (sum64 >> 32) | (sum64 << 32);
+	sum = sum64 >> 32;
+	sum += (sum >> 16) | (sum << 16);
+	if (offset & 1)
+		return (u16)swab32(sum);
+
+	return sum >> 16;
+}

arch/arm64/lib/memchr.S

@@ -19,7 +19,7 @@
  * Returns:
  *	x0 - address of first occurrence of 'c' or 0
  */
-WEAK(memchr)
+SYM_FUNC_START_WEAK_PI(memchr)
 	and	w1, w1, #0xff
 1:	subs	x2, x2, #1
 	b.mi	2f
@@ -30,5 +30,5 @@ WEAK(memchr)
 	ret
 2:	mov	x0, #0
 	ret
-ENDPIPROC(memchr)
+SYM_FUNC_END_PI(memchr)
 EXPORT_SYMBOL_NOKASAN(memchr)

arch/arm64/lib/memcmp.S

@@ -46,7 +46,7 @@ pos		.req	x11
 limit_wd	.req	x12
 mask		.req	x13
 
-WEAK(memcmp)
+SYM_FUNC_START_WEAK_PI(memcmp)
 	cbz	limit, .Lret0
 	eor	tmp1, src1, src2
 	tst	tmp1, #7
@@ -243,5 +243,5 @@ CPU_LE( rev	data2, data2 )
 .Lret0:
 	mov	result, #0
 	ret
-ENDPIPROC(memcmp)
+SYM_FUNC_END_PI(memcmp)
 EXPORT_SYMBOL_NOKASAN(memcmp)

arch/arm64/lib/memcpy.S

@@ -57,11 +57,11 @@
 	.endm
 
 	.weak memcpy
-ENTRY(__memcpy)
-ENTRY(memcpy)
+SYM_FUNC_START_ALIAS(__memcpy)
+SYM_FUNC_START_PI(memcpy)
 #include "copy_template.S"
 	ret
-ENDPIPROC(memcpy)
+SYM_FUNC_END_PI(memcpy)
 EXPORT_SYMBOL(memcpy)
-ENDPROC(__memcpy)
+SYM_FUNC_END_ALIAS(__memcpy)
 EXPORT_SYMBOL(__memcpy)

arch/arm64/lib/memmove.S

@@ -46,8 +46,8 @@ D_l	.req	x13
 D_h	.req	x14
 
 	.weak memmove
-ENTRY(__memmove)
-ENTRY(memmove)
+SYM_FUNC_START_ALIAS(__memmove)
+SYM_FUNC_START_PI(memmove)
 	cmp	dstin, src
 	b.lo	__memcpy
 	add	tmp1, src, count
@@ -184,7 +184,7 @@ ENTRY(memmove)
 	tst	count, #0x3f
 	b.ne	.Ltail63
 	ret
-ENDPIPROC(memmove)
+SYM_FUNC_END_PI(memmove)
 EXPORT_SYMBOL(memmove)
-ENDPROC(__memmove)
+SYM_FUNC_END_ALIAS(__memmove)
 EXPORT_SYMBOL(__memmove)

arch/arm64/lib/memset.S

@@ -43,8 +43,8 @@ tmp3w		.req	w9
 tmp3		.req	x9
 
 	.weak memset
-ENTRY(__memset)
-ENTRY(memset)
+SYM_FUNC_START_ALIAS(__memset)
+SYM_FUNC_START_PI(memset)
 	mov	dst, dstin	/* Preserve return value.  */
 	and	A_lw, val, #255
 	orr	A_lw, A_lw, A_lw, lsl #8
@@ -203,7 +203,7 @@ ENTRY(memset)
 	ands	count, count, zva_bits_x
 	b.ne	.Ltail_maybe_long
 	ret
-ENDPIPROC(memset)
+SYM_FUNC_END_PI(memset)
 EXPORT_SYMBOL(memset)
-ENDPROC(__memset)
+SYM_FUNC_END_ALIAS(__memset)
 EXPORT_SYMBOL(__memset)

arch/arm64/lib/strchr.S

@@ -18,7 +18,7 @@
  * Returns:
  *	x0 - address of first occurrence of 'c' or 0
  */
-WEAK(strchr)
+SYM_FUNC_START_WEAK(strchr)
 	and	w1, w1, #0xff
 1:	ldrb	w2, [x0], #1
 	cmp	w2, w1
@@ -28,5 +28,5 @@ WEAK(strchr)
 	cmp	w2, w1
 	csel	x0, x0, xzr, eq
 	ret
-ENDPROC(strchr)
+SYM_FUNC_END(strchr)
 EXPORT_SYMBOL_NOKASAN(strchr)

arch/arm64/lib/strcmp.S

@@ -48,7 +48,7 @@ tmp3		.req	x9
 zeroones	.req	x10
 pos		.req	x11
 
-WEAK(strcmp)
+SYM_FUNC_START_WEAK_PI(strcmp)
 	eor	tmp1, src1, src2
 	mov	zeroones, #REP8_01
 	tst	tmp1, #7
@@ -219,5 +219,5 @@ CPU_BE(	orr	syndrome, diff, has_nul )
 	lsr	data1, data1, #56
 	sub	result, data1, data2, lsr #56
 	ret
-ENDPIPROC(strcmp)
+SYM_FUNC_END_PI(strcmp)
 EXPORT_SYMBOL_NOKASAN(strcmp)

arch/arm64/lib/strlen.S

@@ -44,7 +44,7 @@ pos		.req	x12
 #define REP8_7f 0x7f7f7f7f7f7f7f7f
 #define REP8_80 0x8080808080808080
 
-WEAK(strlen)
+SYM_FUNC_START_WEAK_PI(strlen)
 	mov	zeroones, #REP8_01
 	bic	src, srcin, #15
 	ands	tmp1, srcin, #15
@@ -111,5 +111,5 @@ CPU_LE( lsr	tmp2, tmp2, tmp1 )	/* Shift (tmp1 & 63).  */
 	csinv	data1, data1, xzr, le
 	csel	data2, data2, data2a, le
 	b	.Lrealigned
-ENDPIPROC(strlen)
+SYM_FUNC_END_PI(strlen)
 EXPORT_SYMBOL_NOKASAN(strlen)

arch/arm64/lib/strncmp.S

@@ -52,7 +52,7 @@ limit_wd	.req	x13
 mask		.req	x14
 endloop		.req	x15
 
-WEAK(strncmp)
+SYM_FUNC_START_WEAK_PI(strncmp)
 	cbz	limit, .Lret0
 	eor	tmp1, src1, src2
 	mov	zeroones, #REP8_01
@@ -295,5 +295,5 @@ CPU_BE( orr	syndrome, diff, has_nul )
 .Lret0:
 	mov	result, #0
 	ret
-ENDPIPROC(strncmp)
+SYM_FUNC_END_PI(strncmp)
 EXPORT_SYMBOL_NOKASAN(strncmp)

arch/arm64/lib/strnlen.S

@@ -47,7 +47,7 @@ limit_wd	.req	x14
 #define REP8_7f 0x7f7f7f7f7f7f7f7f
 #define REP8_80 0x8080808080808080
 
-WEAK(strnlen)
+SYM_FUNC_START_WEAK_PI(strnlen)
 	cbz	limit, .Lhit_limit
 	mov	zeroones, #REP8_01
 	bic	src, srcin, #15
@@ -156,5 +156,5 @@ CPU_LE( lsr	tmp2, tmp2, tmp4 )	/* Shift (tmp1 & 63).  */
 .Lhit_limit:
 	mov	len, limit
 	ret
-ENDPIPROC(strnlen)
+SYM_FUNC_END_PI(strnlen)
 EXPORT_SYMBOL_NOKASAN(strnlen)

arch/arm64/lib/strrchr.S

@@ -18,7 +18,7 @@
  * Returns:
  *	x0 - address of last occurrence of 'c' or 0
  */
-WEAK(strrchr)
+SYM_FUNC_START_WEAK_PI(strrchr)
 	mov	x3, #0
 	and	w1, w1, #0xff
 1:	ldrb	w2, [x0], #1
@@ -29,5 +29,5 @@ WEAK(strrchr)
 	b	1b
 2:	mov	x0, x3
 	ret
-ENDPIPROC(strrchr)
+SYM_FUNC_END_PI(strrchr)
 EXPORT_SYMBOL_NOKASAN(strrchr)

arch/arm64/lib/tishift.S

@@ -7,7 +7,7 @@
 
 #include <asm/assembler.h>
 
-ENTRY(__ashlti3)
+SYM_FUNC_START(__ashlti3)
 	cbz	x2, 1f
 	mov	x3, #64
 	sub	x3, x3, x2
@@ -26,10 +26,10 @@ ENTRY(__ashlti3)
 	lsl	x1, x0, x1
 	mov	x0, x2
 	ret
-ENDPROC(__ashlti3)
+SYM_FUNC_END(__ashlti3)
 EXPORT_SYMBOL(__ashlti3)
 
-ENTRY(__ashrti3)
+SYM_FUNC_START(__ashrti3)
 	cbz	x2, 1f
 	mov	x3, #64
 	sub	x3, x3, x2
@@ -48,10 +48,10 @@ ENTRY(__ashrti3)
 	asr	x0, x1, x0
 	mov	x1, x2
 	ret
-ENDPROC(__ashrti3)
+SYM_FUNC_END(__ashrti3)
 EXPORT_SYMBOL(__ashrti3)
 
-ENTRY(__lshrti3)
+SYM_FUNC_START(__lshrti3)
 	cbz	x2, 1f
 	mov	x3, #64
 	sub	x3, x3, x2
@@ -70,5 +70,5 @@ ENTRY(__lshrti3)
 	lsr	x0, x1, x0
 	mov	x1, x2
 	ret
-ENDPROC(__lshrti3)
+SYM_FUNC_END(__lshrti3)
 EXPORT_SYMBOL(__lshrti3)

arch/arm64/mm/cache.S

@@ -24,7 +24,7 @@
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-ENTRY(__flush_icache_range)
+SYM_FUNC_START(__flush_icache_range)
 	/* FALLTHROUGH */
 
 /*
@@ -37,7 +37,7 @@ ENTRY(__flush_icache_range)
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-ENTRY(__flush_cache_user_range)
+SYM_FUNC_START(__flush_cache_user_range)
 	uaccess_ttbr0_enable x2, x3, x4
 alternative_if ARM64_HAS_CACHE_IDC
 	dsb	ishst
@@ -66,8 +66,8 @@ alternative_else_nop_endif
 9:
 	mov	x0, #-EFAULT
 	b	1b
-ENDPROC(__flush_icache_range)
-ENDPROC(__flush_cache_user_range)
+SYM_FUNC_END(__flush_icache_range)
+SYM_FUNC_END(__flush_cache_user_range)
 
 /*
  *	invalidate_icache_range(start,end)
@@ -77,7 +77,7 @@ ENDPROC(__flush_cache_user_range)
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-ENTRY(invalidate_icache_range)
+SYM_FUNC_START(invalidate_icache_range)
 alternative_if ARM64_HAS_CACHE_DIC
 	mov	x0, xzr
 	isb
@@ -94,7 +94,7 @@ alternative_else_nop_endif
 2:
 	mov	x0, #-EFAULT
 	b	1b
-ENDPROC(invalidate_icache_range)
+SYM_FUNC_END(invalidate_icache_range)
 
 /*
  *	__flush_dcache_area(kaddr, size)
@@ -105,10 +105,10 @@ ENDPROC(invalidate_icache_range)
  *	- kaddr   - kernel address
  *	- size    - size in question
  */
-ENTRY(__flush_dcache_area)
+SYM_FUNC_START_PI(__flush_dcache_area)
 	dcache_by_line_op civac, sy, x0, x1, x2, x3
 	ret
-ENDPIPROC(__flush_dcache_area)
+SYM_FUNC_END_PI(__flush_dcache_area)
 
 /*
  *	__clean_dcache_area_pou(kaddr, size)
@@ -119,14 +119,14 @@ ENDPIPROC(__flush_dcache_area)
  *	- kaddr   - kernel address
  *	- size    - size in question
  */
-ENTRY(__clean_dcache_area_pou)
+SYM_FUNC_START(__clean_dcache_area_pou)
 alternative_if ARM64_HAS_CACHE_IDC
 	dsb	ishst
 	ret
 alternative_else_nop_endif
 	dcache_by_line_op cvau, ish, x0, x1, x2, x3
 	ret
-ENDPROC(__clean_dcache_area_pou)
+SYM_FUNC_END(__clean_dcache_area_pou)
 
 /*
  *	__inval_dcache_area(kaddr, size)
@@ -138,7 +138,8 @@ ENDPROC(__clean_dcache_area_pou)
  *	- kaddr   - kernel address
  *	- size    - size in question
  */
-ENTRY(__inval_dcache_area)
+SYM_FUNC_START_LOCAL(__dma_inv_area)
+SYM_FUNC_START_PI(__inval_dcache_area)
 	/* FALLTHROUGH */
 
 /*
@@ -146,7 +147,6 @@ ENTRY(__inval_dcache_area)
  *	- start   - virtual start address of region
  *	- size    - size in question
  */
-__dma_inv_area:
 	add	x1, x1, x0
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
@@ -165,8 +165,8 @@ __dma_inv_area:
 	b.lo	2b
 	dsb	sy
 	ret
-ENDPIPROC(__inval_dcache_area)
-ENDPROC(__dma_inv_area)
+SYM_FUNC_END_PI(__inval_dcache_area)
+SYM_FUNC_END(__dma_inv_area)
 
 /*
  *	__clean_dcache_area_poc(kaddr, size)
@@ -177,7 +177,8 @@ ENDPROC(__dma_inv_area)
  *	- kaddr   - kernel address
  *	- size    - size in question
  */
-ENTRY(__clean_dcache_area_poc)
+SYM_FUNC_START_LOCAL(__dma_clean_area)
+SYM_FUNC_START_PI(__clean_dcache_area_poc)
 	/* FALLTHROUGH */
 
 /*
@@ -185,11 +186,10 @@ ENTRY(__clean_dcache_area_poc)
  *	- start   - virtual start address of region
  *	- size    - size in question
  */
-__dma_clean_area:
 	dcache_by_line_op cvac, sy, x0, x1, x2, x3
 	ret
-ENDPIPROC(__clean_dcache_area_poc)
-ENDPROC(__dma_clean_area)
+SYM_FUNC_END_PI(__clean_dcache_area_poc)
+SYM_FUNC_END(__dma_clean_area)
 
 /*
  *	__clean_dcache_area_pop(kaddr, size)
@@ -200,13 +200,13 @@ ENDPROC(__dma_clean_area)
  *	- kaddr   - kernel address
  *	- size    - size in question
  */
-ENTRY(__clean_dcache_area_pop)
+SYM_FUNC_START_PI(__clean_dcache_area_pop)
 	alternative_if_not ARM64_HAS_DCPOP
 	b	__clean_dcache_area_poc
 	alternative_else_nop_endif
 	dcache_by_line_op cvap, sy, x0, x1, x2, x3
 	ret
-ENDPIPROC(__clean_dcache_area_pop)
+SYM_FUNC_END_PI(__clean_dcache_area_pop)
 
 /*
  *	__dma_flush_area(start, size)
@@ -216,10 +216,10 @@ ENDPIPROC(__clean_dcache_area_pop)
  *	- start   - virtual start address of region
  *	- size    - size in question
  */
-ENTRY(__dma_flush_area)
+SYM_FUNC_START_PI(__dma_flush_area)
 	dcache_by_line_op civac, sy, x0, x1, x2, x3
 	ret
-ENDPIPROC(__dma_flush_area)
+SYM_FUNC_END_PI(__dma_flush_area)
 
 /*
  *	__dma_map_area(start, size, dir)
@@ -227,11 +227,11 @@ ENDPIPROC(__dma_flush_area)
  *	- size	- size of region
  *	- dir	- DMA direction
  */
-ENTRY(__dma_map_area)
+SYM_FUNC_START_PI(__dma_map_area)
 	cmp	w2, #DMA_FROM_DEVICE
 	b.eq	__dma_inv_area
 	b	__dma_clean_area
-ENDPIPROC(__dma_map_area)
+SYM_FUNC_END_PI(__dma_map_area)
 
 /*
  *	__dma_unmap_area(start, size, dir)
@@ -239,8 +239,8 @@ ENDPIPROC(__dma_map_area)
  *	- size	- size of region
  *	- dir	- DMA direction
  */
-ENTRY(__dma_unmap_area)
+SYM_FUNC_START_PI(__dma_unmap_area)
 	cmp	w2, #DMA_TO_DEVICE
 	b.ne	__dma_inv_area
 	ret
-ENDPIPROC(__dma_unmap_area)
+SYM_FUNC_END_PI(__dma_unmap_area)

arch/arm64/mm/context.c

@@ -29,15 +29,9 @@ static cpumask_t tlb_flush_pending;
 #define ASID_MASK		(~GENMASK(asid_bits - 1, 0))
 #define ASID_FIRST_VERSION	(1UL << asid_bits)
 
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-#define NUM_USER_ASIDS		(ASID_FIRST_VERSION >> 1)
-#define asid2idx(asid)		(((asid) & ~ASID_MASK) >> 1)
-#define idx2asid(idx)		(((idx) << 1) & ~ASID_MASK)
-#else
-#define NUM_USER_ASIDS		(ASID_FIRST_VERSION)
+#define NUM_USER_ASIDS		ASID_FIRST_VERSION
 #define asid2idx(asid)		((asid) & ~ASID_MASK)
 #define idx2asid(idx)		asid2idx(idx)
-#endif
 
 /* Get the ASIDBits supported by the current CPU */
 static u32 get_cpu_asid_bits(void)
@@ -77,13 +71,33 @@ void verify_cpu_asid_bits(void)
 	}
 }
 
+static void set_kpti_asid_bits(void)
+{
+	unsigned int len = BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(unsigned long);
+	/*
+	 * In case of KPTI kernel/user ASIDs are allocated in
+	 * pairs, the bottom bit distinguishes the two: if it
+	 * is set, then the ASID will map only userspace. Thus
+	 * mark even as reserved for kernel.
+	 */
+	memset(asid_map, 0xaa, len);
+}
+
+static void set_reserved_asid_bits(void)
+{
+	if (arm64_kernel_unmapped_at_el0())
+		set_kpti_asid_bits();
+	else
+		bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
+}
+
 static void flush_context(void)
 {
 	int i;
 	u64 asid;
 
 	/* Update the list of reserved ASIDs and the ASID bitmap. */
-	bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
+	set_reserved_asid_bits();
 
 	for_each_possible_cpu(i) {
 		asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0);
@@ -261,6 +275,14 @@ static int asids_init(void)
 		panic("Failed to allocate bitmap for %lu ASIDs\n",
 		      NUM_USER_ASIDS);
 
+	/*
+	 * We cannot call set_reserved_asid_bits() here because CPU
+	 * caps are not finalized yet, so it is safer to assume KPTI
+	 * and reserve kernel ASID's from beginning.
+	 */
+	if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0))
+		set_kpti_asid_bits();
+
 	pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS);
 	return 0;
 }

arch/arm64/mm/pageattr.c

@@ -54,7 +54,7 @@ static int change_memory_common(unsigned long addr, int numpages,
 				pgprot_t set_mask, pgprot_t clear_mask)
 {
 	unsigned long start = addr;
-	unsigned long size = PAGE_SIZE*numpages;
+	unsigned long size = PAGE_SIZE * numpages;
 	unsigned long end = start + size;
 	struct vm_struct *area;
 	int i;

arch/arm64/mm/proc.S

@@ -42,7 +42,14 @@
 #define TCR_KASAN_FLAGS 0
 #endif
 
-#define MAIR(attr, mt)	((attr) << ((mt) * 8))
+/* Default MAIR_EL1 */
+#define MAIR_EL1_SET							\
+	(MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRnE, MT_DEVICE_nGnRnE) |	\
+	 MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRE, MT_DEVICE_nGnRE) |	\
+	 MAIR_ATTRIDX(MAIR_ATTR_DEVICE_GRE, MT_DEVICE_GRE) |		\
+	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL_NC, MT_NORMAL_NC) |		\
+	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) |			\
+	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT))
 
 #ifdef CONFIG_CPU_PM
 /**
@@ -50,7 +57,7 @@
  *
  * x0: virtual address of context pointer
  */
-ENTRY(cpu_do_suspend)
+SYM_FUNC_START(cpu_do_suspend)
 	mrs	x2, tpidr_el0
 	mrs	x3, tpidrro_el0
 	mrs	x4, contextidr_el1
@@ -74,7 +81,7 @@ alternative_endif
 	stp	x10, x11, [x0, #64]
 	stp	x12, x13, [x0, #80]
 	ret
-ENDPROC(cpu_do_suspend)
+SYM_FUNC_END(cpu_do_suspend)
 
 /**
  * cpu_do_resume - restore CPU register context
@@ -82,7 +89,7 @@ ENDPROC(cpu_do_suspend)
  * x0: Address of context pointer
  */
 	.pushsection ".idmap.text", "awx"
-ENTRY(cpu_do_resume)
+SYM_FUNC_START(cpu_do_resume)
 	ldp	x2, x3, [x0]
 	ldp	x4, x5, [x0, #16]
 	ldp	x6, x8, [x0, #32]
@@ -131,7 +138,7 @@ alternative_else_nop_endif
 
 	isb
 	ret
-ENDPROC(cpu_do_resume)
+SYM_FUNC_END(cpu_do_resume)
 	.popsection
 #endif
 
@@ -142,7 +149,7 @@ ENDPROC(cpu_do_resume)
  *
  *	- pgd_phys - physical address of new TTB
  */
-ENTRY(cpu_do_switch_mm)
+SYM_FUNC_START(cpu_do_switch_mm)
 	mrs	x2, ttbr1_el1
 	mmid	x1, x1				// get mm->context.id
 	phys_to_ttbr x3, x0
@@ -161,7 +168,7 @@ alternative_else_nop_endif
 	msr	ttbr0_el1, x3			// now update TTBR0
 	isb
 	b	post_ttbr_update_workaround	// Back to C code...
-ENDPROC(cpu_do_switch_mm)
+SYM_FUNC_END(cpu_do_switch_mm)
 
 	.pushsection ".idmap.text", "awx"
 
@@ -182,7 +189,7 @@ ENDPROC(cpu_do_switch_mm)
  * This is the low-level counterpart to cpu_replace_ttbr1, and should not be
  * called by anything else. It can only be executed from a TTBR0 mapping.
  */
-ENTRY(idmap_cpu_replace_ttbr1)
+SYM_FUNC_START(idmap_cpu_replace_ttbr1)
 	save_and_disable_daif flags=x2
 
 	__idmap_cpu_set_reserved_ttbr1 x1, x3
@@ -194,7 +201,7 @@ ENTRY(idmap_cpu_replace_ttbr1)
 	restore_daif x2
 
 	ret
-ENDPROC(idmap_cpu_replace_ttbr1)
+SYM_FUNC_END(idmap_cpu_replace_ttbr1)
 	.popsection
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
@@ -222,7 +229,7 @@ ENDPROC(idmap_cpu_replace_ttbr1)
  */
 __idmap_kpti_flag:
 	.long	1
-ENTRY(idmap_kpti_install_ng_mappings)
+SYM_FUNC_START(idmap_kpti_install_ng_mappings)
 	cpu		.req	w0
 	num_cpus	.req	w1
 	swapper_pa	.req	x2
@@ -250,15 +257,15 @@ ENTRY(idmap_kpti_install_ng_mappings)
 	/* We're the boot CPU. Wait for the others to catch up */
 	sevl
 1:	wfe
-	ldaxr	w18, [flag_ptr]
-	eor	w18, w18, num_cpus
-	cbnz	w18, 1b
+	ldaxr	w17, [flag_ptr]
+	eor	w17, w17, num_cpus
+	cbnz	w17, 1b
 
 	/* We need to walk swapper, so turn off the MMU. */
 	pre_disable_mmu_workaround
-	mrs	x18, sctlr_el1
-	bic	x18, x18, #SCTLR_ELx_M
-	msr	sctlr_el1, x18
+	mrs	x17, sctlr_el1
+	bic	x17, x17, #SCTLR_ELx_M
+	msr	sctlr_el1, x17
 	isb
 
 	/* Everybody is enjoying the idmap, so we can rewrite swapper. */
@@ -281,9 +288,9 @@ skip_pgd:
 	isb
 
 	/* We're done: fire up the MMU again */
-	mrs	x18, sctlr_el1
-	orr	x18, x18, #SCTLR_ELx_M
-	msr	sctlr_el1, x18
+	mrs	x17, sctlr_el1
+	orr	x17, x17, #SCTLR_ELx_M
+	msr	sctlr_el1, x17
 	isb
 
 	/*
@@ -353,47 +360,48 @@ skip_pte:
 	b.ne	do_pte
 	b	next_pmd
 
+	.unreq	cpu
+	.unreq	num_cpus
+	.unreq	swapper_pa
+	.unreq	cur_pgdp
+	.unreq	end_pgdp
+	.unreq	pgd
+	.unreq	cur_pudp
+	.unreq	end_pudp
+	.unreq	pud
+	.unreq	cur_pmdp
+	.unreq	end_pmdp
+	.unreq	pmd
+	.unreq	cur_ptep
+	.unreq	end_ptep
+	.unreq	pte
+
 	/* Secondary CPUs end up here */
 __idmap_kpti_secondary:
 	/* Uninstall swapper before surgery begins */
-	__idmap_cpu_set_reserved_ttbr1 x18, x17
+	__idmap_cpu_set_reserved_ttbr1 x16, x17
 
 	/* Increment the flag to let the boot CPU we're ready */
-1:	ldxr	w18, [flag_ptr]
-	add	w18, w18, #1
-	stxr	w17, w18, [flag_ptr]
+1:	ldxr	w16, [flag_ptr]
+	add	w16, w16, #1
+	stxr	w17, w16, [flag_ptr]
 	cbnz	w17, 1b
 
 	/* Wait for the boot CPU to finish messing around with swapper */
 	sevl
 1:	wfe
-	ldxr	w18, [flag_ptr]
-	cbnz	w18, 1b
+	ldxr	w16, [flag_ptr]
+	cbnz	w16, 1b
 
 	/* All done, act like nothing happened */
-	offset_ttbr1 swapper_ttb, x18
+	offset_ttbr1 swapper_ttb, x16
 	msr	ttbr1_el1, swapper_ttb
 	isb
 	ret
 
-	.unreq	cpu
-	.unreq	num_cpus
-	.unreq	swapper_pa
 	.unreq	swapper_ttb
 	.unreq	flag_ptr
-	.unreq	cur_pgdp
-	.unreq	end_pgdp
-	.unreq	pgd
-	.unreq	cur_pudp
-	.unreq	end_pudp
-	.unreq	pud
-	.unreq	cur_pmdp
-	.unreq	end_pmdp
-	.unreq	pmd
-	.unreq	cur_ptep
-	.unreq	end_ptep
-	.unreq	pte
-ENDPROC(idmap_kpti_install_ng_mappings)
+SYM_FUNC_END(idmap_kpti_install_ng_mappings)
 	.popsection
 #endif
 
@@ -404,7 +412,7 @@ ENDPROC(idmap_kpti_install_ng_mappings)
  *	value of the SCTLR_EL1 register.
  */
 	.pushsection ".idmap.text", "awx"
-ENTRY(__cpu_setup)
+SYM_FUNC_START(__cpu_setup)
 	tlbi	vmalle1				// Invalidate local TLB
 	dsb	nsh
 
@@ -416,23 +424,9 @@ ENTRY(__cpu_setup)
 	enable_dbg				// since this is per-cpu
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
 	/*
-	 * Memory region attributes for LPAE:
-	 *
-	 *   n = AttrIndx[2:0]
-	 *			n	MAIR
-	 *   DEVICE_nGnRnE	000	00000000
-	 *   DEVICE_nGnRE	001	00000100
-	 *   DEVICE_GRE		010	00001100
-	 *   NORMAL_NC		011	01000100
-	 *   NORMAL		100	11111111
-	 *   NORMAL_WT		101	10111011
+	 * Memory region attributes
 	 */
-	ldr	x5, =MAIR(0x00, MT_DEVICE_nGnRnE) | \
-		     MAIR(0x04, MT_DEVICE_nGnRE) | \
-		     MAIR(0x0c, MT_DEVICE_GRE) | \
-		     MAIR(0x44, MT_NORMAL_NC) | \
-		     MAIR(0xff, MT_NORMAL) | \
-		     MAIR(0xbb, MT_NORMAL_WT)
+	mov_q	x5, MAIR_EL1_SET
 	msr	mair_el1, x5
 	/*
 	 * Prepare SCTLR
@@ -475,4 +469,4 @@ ENTRY(__cpu_setup)
 #endif	/* CONFIG_ARM64_HW_AFDBM */
 	msr	tcr_el1, x10
 	ret					// return to head.S
-ENDPROC(__cpu_setup)
+SYM_FUNC_END(__cpu_setup)

arch/arm64/xen/hypercall.S

@@ -56,11 +56,11 @@
 #define XEN_IMM 0xEA1
 
 #define HYPERCALL_SIMPLE(hypercall)		\
-ENTRY(HYPERVISOR_##hypercall)			\
+SYM_FUNC_START(HYPERVISOR_##hypercall)		\
 	mov x16, #__HYPERVISOR_##hypercall;	\
 	hvc XEN_IMM;				\
 	ret;					\
-ENDPROC(HYPERVISOR_##hypercall)
+SYM_FUNC_END(HYPERVISOR_##hypercall)
 
 #define HYPERCALL0 HYPERCALL_SIMPLE
 #define HYPERCALL1 HYPERCALL_SIMPLE
@@ -86,7 +86,7 @@ HYPERCALL2(multicall);
 HYPERCALL2(vm_assist);
 HYPERCALL3(dm_op);
 
-ENTRY(privcmd_call)
+SYM_FUNC_START(privcmd_call)
 	mov x16, x0
 	mov x0, x1
 	mov x1, x2
@@ -109,4 +109,4 @@ ENTRY(privcmd_call)
 	 */
 	uaccess_ttbr0_disable x6, x7
 	ret
-ENDPROC(privcmd_call);
+SYM_FUNC_END(privcmd_call);

drivers/acpi/arm64/iort.c

@@ -298,6 +298,59 @@ static acpi_status iort_match_node_callback(struct acpi_iort_node *node,
 	return status;
 }
 
+struct iort_workaround_oem_info {
+	char oem_id[ACPI_OEM_ID_SIZE + 1];
+	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
+	u32 oem_revision;
+};
+
+static bool apply_id_count_workaround;
+
+static struct iort_workaround_oem_info wa_info[] __initdata = {
+	{
+		.oem_id		= "HISI  ",
+		.oem_table_id	= "HIP07   ",
+		.oem_revision	= 0,
+	}, {
+		.oem_id		= "HISI  ",
+		.oem_table_id	= "HIP08   ",
+		.oem_revision	= 0,
+	}
+};
+
+static void __init
+iort_check_id_count_workaround(struct acpi_table_header *tbl)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(wa_info); i++) {
+		if (!memcmp(wa_info[i].oem_id, tbl->oem_id, ACPI_OEM_ID_SIZE) &&
+		    !memcmp(wa_info[i].oem_table_id, tbl->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) &&
+		    wa_info[i].oem_revision == tbl->oem_revision) {
+			apply_id_count_workaround = true;
+			pr_warn(FW_BUG "ID count for ID mapping entry is wrong, applying workaround\n");
+			break;
+		}
+	}
+}
+
+static inline u32 iort_get_map_max(struct acpi_iort_id_mapping *map)
+{
+	u32 map_max = map->input_base + map->id_count;
+
+	/*
+	 * The IORT specification revision D (Section 3, table 4, page 9) says
+	 * Number of IDs = The number of IDs in the range minus one, but the
+	 * IORT code ignored the "minus one", and some firmware did that too,
+	 * so apply a workaround here to keep compatible with both the spec
+	 * compliant and non-spec compliant firmwares.
+	 */
+	if (apply_id_count_workaround)
+		map_max--;
+
+	return map_max;
+}
+
 static int iort_id_map(struct acpi_iort_id_mapping *map, u8 type, u32 rid_in,
 		       u32 *rid_out)
 {
@@ -314,8 +367,7 @@ static int iort_id_map(struct acpi_iort_id_mapping *map, u8 type, u32 rid_in,
 		return -ENXIO;
 	}
 
-	if (rid_in < map->input_base ||
-	    (rid_in >= map->input_base + map->id_count))
+	if (rid_in < map->input_base || rid_in > iort_get_map_max(map))
 		return -ENXIO;
 
 	*rid_out = map->output_base + (rid_in - map->input_base);
@@ -1631,5 +1683,6 @@ void __init acpi_iort_init(void)
 		return;
 	}
 
+	iort_check_id_count_workaround(iort_table);
 	iort_init_platform_devices();
 }

drivers/perf/fsl_imx8_ddr_perf.c

@@ -633,13 +633,17 @@ static int ddr_perf_probe(struct platform_device *pdev)
 
 	if (ret < 0) {
 		dev_err(&pdev->dev, "cpuhp_setup_state_multi failed\n");
-		goto ddr_perf_err;
+		goto cpuhp_state_err;
 	}
 
 	pmu->cpuhp_state = ret;
 
 	/* Register the pmu instance for cpu hotplug */
-	cpuhp_state_add_instance_nocalls(pmu->cpuhp_state, &pmu->node);
+	ret = cpuhp_state_add_instance_nocalls(pmu->cpuhp_state, &pmu->node);
+	if (ret) {
+		dev_err(&pdev->dev, "Error %d registering hotplug\n", ret);
+		goto cpuhp_instance_err;
+	}
 
 	/* Request irq */
 	irq = of_irq_get(np, 0);
@@ -673,9 +677,10 @@ static int ddr_perf_probe(struct platform_device *pdev)
 	return 0;
 
 ddr_perf_err:
-	if (pmu->cpuhp_state)
 	cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node);
-
+cpuhp_instance_err:
+	cpuhp_remove_multi_state(pmu->cpuhp_state);
+cpuhp_state_err:
 	ida_simple_remove(&ddr_ida, pmu->id);
 	dev_warn(&pdev->dev, "i.MX8 DDR Perf PMU failed (%d), disabled\n", ret);
 	return ret;
@@ -686,6 +691,7 @@ static int ddr_perf_remove(struct platform_device *pdev)
 	struct ddr_pmu *pmu = platform_get_drvdata(pdev);
 
 	cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node);
+	cpuhp_remove_multi_state(pmu->cpuhp_state);
 	irq_set_affinity_hint(pmu->irq, NULL);
 
 	perf_pmu_unregister(&pmu->pmu);

drivers/perf/hisilicon/hisi_uncore_pmu.c

@@ -337,38 +337,44 @@ void hisi_uncore_pmu_disable(struct pmu *pmu)
 	hisi_pmu->ops->stop_counters(hisi_pmu);
 }
 
+
 /*
- * Read Super CPU cluster and CPU cluster ID from MPIDR_EL1.
- * If multi-threading is supported, On Huawei Kunpeng 920 SoC whose cpu
- * core is tsv110, CCL_ID is the low 3-bits in MPIDR[Aff2] and SCCL_ID
- * is the upper 5-bits of Aff2 field; while for other cpu types, SCCL_ID
- * is in MPIDR[Aff3] and CCL_ID is in MPIDR[Aff2], if not, SCCL_ID
- * is in MPIDR[Aff2] and CCL_ID is in MPIDR[Aff1].
+ * The Super CPU Cluster (SCCL) and CPU Cluster (CCL) IDs can be
+ * determined from the MPIDR_EL1, but the encoding varies by CPU:
+ *
+ * - For MT variants of TSV110:
+ *   SCCL is Aff2[7:3], CCL is Aff2[2:0]
+ *
+ * - For other MT parts:
+ *   SCCL is Aff3[7:0], CCL is Aff2[7:0]
+ *
+ * - For non-MT parts:
+ *   SCCL is Aff2[7:0], CCL is Aff1[7:0]
  */
-static void hisi_read_sccl_and_ccl_id(int *sccl_id, int *ccl_id)
+static void hisi_read_sccl_and_ccl_id(int *scclp, int *cclp)
 {
 	u64 mpidr = read_cpuid_mpidr();
-
-	if (mpidr & MPIDR_MT_BITMASK) {
-		if (read_cpuid_part_number() == HISI_CPU_PART_TSV110) {
+	int aff3 = MPIDR_AFFINITY_LEVEL(mpidr, 3);
 	int aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2);
-
-			if (sccl_id)
-				*sccl_id = aff2 >> 3;
-			if (ccl_id)
-				*ccl_id = aff2 & 0x7;
-		} else {
-			if (sccl_id)
-				*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 3);
-			if (ccl_id)
-				*ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
-		}
+	int aff1 = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	bool mt = mpidr & MPIDR_MT_BITMASK;
+	int sccl, ccl;
+
+	if (mt && read_cpuid_part_number() == HISI_CPU_PART_TSV110) {
+		sccl = aff2 >> 3;
+		ccl = aff2 & 0x7;
+	} else if (mt) {
+		sccl = aff3;
+		ccl = aff2;
 	} else {
-		if (sccl_id)
-			*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
-		if (ccl_id)
-			*ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+		sccl = aff2;
+		ccl = aff1;
 	}
+
+	if (scclp)
+		*scclp = sccl;
+	if (cclp)
+		*cclp = ccl;
 }
 
 /*

include/uapi/asm-generic/mman-common.h

@@ -11,6 +11,8 @@
 #define PROT_WRITE	0x2		/* page can be written */
 #define PROT_EXEC	0x4		/* page can be executed */
 #define PROT_SEM	0x8		/* page may be used for atomic ops */
+/*			0x10		   reserved for arch-specific use */
+/*			0x20		   reserved for arch-specific use */
 #define PROT_NONE	0x0		/* page can not be accessed */
 #define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
 #define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */

kernel/kexec.c

@@ -159,6 +159,10 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
 
 	kimage_terminate(image);
 
+	ret = machine_kexec_post_load(image);
+	if (ret)
+		goto out;
+
 	/* Install the new kernel and uninstall the old */
 	image = xchg(dest_image, image);
 

kernel/kexec_core.c

@@ -589,6 +589,12 @@ static void kimage_free_extra_pages(struct kimage *image)
 	kimage_free_page_list(&image->unusable_pages);
 
 }
+
+int __weak machine_kexec_post_load(struct kimage *image)
+{
+	return 0;
+}
+
 void kimage_terminate(struct kimage *image)
 {
 	if (*image->entry != 0)
@@ -1171,7 +1177,7 @@ int kernel_kexec(void)
 		 * CPU hotplug again; so re-enable it here.
 		 */
 		cpu_hotplug_enable();
-		pr_emerg("Starting new kernel\n");
+		pr_notice("Starting new kernel\n");
 		machine_shutdown();
 	}
 

kernel/kexec_file.c

@@ -441,6 +441,10 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 
 	kimage_terminate(image);
 
+	ret = machine_kexec_post_load(image);
+	if (ret)
+		goto out;
+
 	/*
 	 * Free up any temporary buffers allocated which are not needed
 	 * after image has been loaded

kernel/kexec_internal.h

@@ -13,6 +13,8 @@ void kimage_terminate(struct kimage *image);
 int kimage_is_destination_range(struct kimage *image,
 				unsigned long start, unsigned long end);
 
+int machine_kexec_post_load(struct kimage *image);
+
 extern struct mutex kexec_mutex;
 
 #ifdef CONFIG_KEXEC_FILE

lib/Makefile

@@ -223,7 +223,7 @@ KASAN_SANITIZE_stackdepot.o := n
 KCOV_INSTRUMENT_stackdepot.o := n
 
 libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \
-	       fdt_empty_tree.o
+	       fdt_empty_tree.o fdt_addresses.o
 $(foreach file, $(libfdt_files), \
 	$(eval CFLAGS_$(file) = -I $(srctree)/scripts/dtc/libfdt))
 lib-$(CONFIG_LIBFDT) += $(libfdt_files)

lib/fdt_addresses.c

+#include <linux/libfdt_env.h>
+#include "../scripts/dtc/libfdt/fdt_addresses.c"

scripts/Kconfig.include

@@ -31,6 +31,10 @@ cc-option = $(success,$(CC) -Werror $(CLANG_FLAGS) $(1) -E -x c /dev/null -o /de
 # Return y if the linker supports <flag>, n otherwise
 ld-option = $(success,$(LD) -v $(1))
 
+# $(as-instr,<instr>)
+# Return y if the assembler supports <instr>, n otherwise
+as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -c -x assembler -o /dev/null -)
+
 # check if $(CC) and $(LD) exist
 $(error-if,$(failure,command -v $(CC)),compiler '$(CC)' not found)
 $(error-if,$(failure,command -v $(LD)),linker '$(LD)' not found)