Merge branches 'for-next/acpi', 'for-next/cpufeatures', 'for-next/csum', 'for-next/e0pd', 'for-next/entry', 'for-next/kbuild', 'for-next/kexec/cleanup', 'for-next/kexec/file-kdump', 'for-next/misc', 'for-next/nofpsimd', 'for-next/perf' and 'for-next/scs' into for-next/core

* for-next/acpi:
  ACPI/IORT: Fix 'Number of IDs' handling in iort_id_map()

* for-next/cpufeatures: (2 commits)
  arm64: Introduce ID_ISAR6 CPU register
  ...

* for-next/csum: (2 commits)
  arm64: csum: Fix pathological zero-length calls
  ...

* for-next/e0pd: (7 commits)
  arm64: kconfig: Fix alignment of E0PD help text
  ...

* for-next/entry: (5 commits)
  arm64: entry: cleanup sp_el0 manipulation
  ...

* for-next/kbuild: (4 commits)
  arm64: kbuild: remove compressed images on 'make ARCH=arm64 (dist)clean'
  ...

* for-next/kexec/cleanup: (11 commits)
  Revert "arm64: kexec: make dtb_mem always enabled"
  ...

* for-next/kexec/file-kdump: (2 commits)
  arm64: kexec_file: add crash dump support
  ...

* for-next/misc: (12 commits)
  arm64: entry: Avoid empty alternatives entries
  ...

* for-next/nofpsimd: (7 commits)
  arm64: nofpsmid: Handle TIF_FOREIGN_FPSTATE flag cleanly
  ...

* for-next/perf: (2 commits)
  perf/imx_ddr: Fix cpu hotplug state cleanup
  ...

* for-next/scs: (6 commits)
  arm64: kernel: avoid x18 in __cpu_soft_restart
  ...

Author: willdeacon

Documentation/arm64/cpu-feature-registers.rst

@@ -200,6 +200,12 @@ 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 +240,18 @@ 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 +204,33 @@ 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.
 
 4. Unused AT_HWCAP bits
 -----------------------

arch/arm64/Kconfig

@@ -161,6 +161,7 @@ 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
@@ -301,6 +302,9 @@ 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
@@ -1363,6 +1367,11 @@ 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
@@ -1484,6 +1493,22 @@ 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.
+
+endmenu
+
 config ARM64_SVE
 	bool "ARM Scalable Vector Extension support"
 	default y
@@ -1544,7 +1569,7 @@ 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 */
@@ -62,33 +65,40 @@ 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"							\
 	"664:\n\t"							\
 	".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/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
  */

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"						\