Merge branches 'for-next/reorg-va-space', 'for-next/rust-for-arm64', 'for-next/misc', 'for-next/daif-cleanup', 'for-next/kselftest', 'for-next/documentation', 'for-next/sysreg' and 'for-next/dpisa', remote-tracking branch 'arm64/for-next/perf' into for-next/core

* arm64/for-next/perf: (39 commits)
  docs: perf: Fix build warning of hisi-pcie-pmu.rst
  perf: starfive: Only allow COMPILE_TEST for 64-bit architectures
  MAINTAINERS: Add entry for StarFive StarLink PMU
  docs: perf: Add description for StarFive's StarLink PMU
  dt-bindings: perf: starfive: Add JH8100 StarLink PMU
  perf: starfive: Add StarLink PMU support
  docs: perf: Update usage for target filter of hisi-pcie-pmu
  drivers/perf: hisi_pcie: Merge find_related_event() and get_event_idx()
  drivers/perf: hisi_pcie: Relax the check on related events
  drivers/perf: hisi_pcie: Check the target filter properly
  drivers/perf: hisi_pcie: Add more events for counting TLP bandwidth
  drivers/perf: hisi_pcie: Fix incorrect counting under metric mode
  drivers/perf: hisi_pcie: Introduce hisi_pcie_pmu_get_event_ctrl_val()
  drivers/perf: hisi_pcie: Rename hisi_pcie_pmu_{config,clear}_filter()
  drivers/perf: hisi: Enable HiSilicon Erratum 162700402 quirk for HIP09
  perf/arm_cspmu: Add devicetree support
  dt-bindings/perf: Add Arm CoreSight PMU
  perf/arm_cspmu: Simplify counter reset
  perf/arm_cspmu: Simplify attribute groups
  perf/arm_cspmu: Simplify initialisation
  ...

* for-next/reorg-va-space:
  : Reorganise the arm64 kernel VA space in preparation for LPA2 support
  : (52-bit VA/PA).
  arm64: kaslr: Adjust randomization range dynamically
  arm64: mm: Reclaim unused vmemmap region for vmalloc use
  arm64: vmemmap: Avoid base2 order of struct page size to dimension region
  arm64: ptdump: Discover start of vmemmap region at runtime
  arm64: ptdump: Allow all region boundaries to be defined at boot time
  arm64: mm: Move fixmap region above vmemmap region
  arm64: mm: Move PCI I/O emulation region above the vmemmap region

* for-next/rust-for-arm64:
  : Enable Rust support for arm64
  arm64: rust: Enable Rust support for AArch64
  rust: Refactor the build target to allow the use of builtin targets

* for-next/misc:
  : Miscellaneous arm64 patches
  ARM64: Dynamically allocate cpumasks and increase supported CPUs to 512
  arm64: Remove enable_daif macro
  arm64/hw_breakpoint: Directly use ESR_ELx_WNR for an watchpoint exception
  arm64: cpufeatures: Clean up temporary variable to simplify code
  arm64: Update setup_arch() comment on interrupt masking
  arm64: remove unnecessary ifdefs around is_compat_task()
  arm64: ftrace: Don't forbid CALL_OPS+CC_OPTIMIZE_FOR_SIZE with Clang
  arm64/sme: Ensure that all fields in SMCR_EL1 are set to known values
  arm64/sve: Ensure that all fields in ZCR_EL1 are set to known values
  arm64/sve: Document that __SVE_VQ_MAX is much larger than needed
  arm64: make member of struct pt_regs and it's offset macro in the same order
  arm64: remove unneeded BUILD_BUG_ON assertion
  arm64: kretprobes: acquire the regs via a BRK exception
  arm64: io: permit offset addressing
  arm64: errata: Don't enable workarounds for "rare" errata by default

* for-next/daif-cleanup:
  : Clean up DAIF handling for EL0 returns
  arm64: Unmask Debug + SError in do_notify_resume()
  arm64: Move do_notify_resume() to entry-common.c
  arm64: Simplify do_notify_resume() DAIF masking

* for-next/kselftest:
  : Miscellaneous arm64 kselftest patches
  kselftest/arm64: Test that ptrace takes effect in the target process

* for-next/documentation:
  : arm64 documentation patches
  arm64/sme: Remove spurious 'is' in SME documentation
  arm64/fp: Clarify effect of setting an unsupported system VL
  arm64/sme: Fix cut'n'paste in ABI document
  arm64/sve: Remove bitrotted comment about syscall behaviour

* for-next/sysreg:
  : sysreg updates
  arm64/sysreg: Update ID_AA64DFR0_EL1 register
  arm64/sysreg: Update ID_DFR0_EL1 register fields
  arm64/sysreg: Add register fields for ID_AA64DFR1_EL1

* for-next/dpisa:
  : Support for 2023 dpISA extensions
  kselftest/arm64: Add 2023 DPISA hwcap test coverage
  kselftest/arm64: Add basic FPMR test
  kselftest/arm64: Handle FPMR context in generic signal frame parser
  arm64/hwcap: Define hwcaps for 2023 DPISA features
  arm64/ptrace: Expose FPMR via ptrace
  arm64/signal: Add FPMR signal handling
  arm64/fpsimd: Support FEAT_FPMR
  arm64/fpsimd: Enable host kernel access to FPMR
  arm64/cpufeature: Hook new identification registers up to cpufeature

Author: ctmarinas

Documentation/arch/arm64/elf_hwcaps.rst

@@ -317,6 +317,55 @@ HWCAP2_LRCPC3
 HWCAP2_LSE128
     Functionality implied by ID_AA64ISAR0_EL1.Atomic == 0b0011.
 
+HWCAP2_FPMR
+    Functionality implied by ID_AA64PFR2_EL1.FMR == 0b0001.
+
+HWCAP2_LUT
+    Functionality implied by ID_AA64ISAR2_EL1.LUT == 0b0001.
+
+HWCAP2_FAMINMAX
+    Functionality implied by ID_AA64ISAR3_EL1.FAMINMAX == 0b0001.
+
+HWCAP2_F8CVT
+    Functionality implied by ID_AA64FPFR0_EL1.F8CVT == 0b1.
+
+HWCAP2_F8FMA
+    Functionality implied by ID_AA64FPFR0_EL1.F8FMA == 0b1.
+
+HWCAP2_F8DP4
+    Functionality implied by ID_AA64FPFR0_EL1.F8DP4 == 0b1.
+
+HWCAP2_F8DP2
+    Functionality implied by ID_AA64FPFR0_EL1.F8DP2 == 0b1.
+
+HWCAP2_F8E4M3
+    Functionality implied by ID_AA64FPFR0_EL1.F8E4M3 == 0b1.
+
+HWCAP2_F8E5M2
+    Functionality implied by ID_AA64FPFR0_EL1.F8E5M2 == 0b1.
+
+HWCAP2_SME_LUTV2
+    Functionality implied by ID_AA64SMFR0_EL1.LUTv2 == 0b1.
+
+HWCAP2_SME_F8F16
+    Functionality implied by ID_AA64SMFR0_EL1.F8F16 == 0b1.
+
+HWCAP2_SME_F8F32
+    Functionality implied by ID_AA64SMFR0_EL1.F8F32 == 0b1.
+
+HWCAP2_SME_SF8FMA
+    Functionality implied by ID_AA64SMFR0_EL1.SF8FMA == 0b1.
+
+HWCAP2_SME_SF8DP4
+    Functionality implied by ID_AA64SMFR0_EL1.SF8DP4 == 0b1.
+
+HWCAP2_SME_SF8DP2
+    Functionality implied by ID_AA64SMFR0_EL1.SF8DP2 == 0b1.
+
+HWCAP2_SME_SF8DP4
+    Functionality implied by ID_AA64SMFR0_EL1.SF8DP4 == 0b1.
+
+
 4. Unused AT_HWCAP bits
 -----------------------
 

Documentation/arch/arm64/silicon-errata.rst

@@ -35,8 +35,9 @@ can be triggered by Linux).
 For software workarounds that may adversely impact systems unaffected by
 the erratum in question, a Kconfig entry is added under "Kernel
 Features" -> "ARM errata workarounds via the alternatives framework".
-These are enabled by default and patched in at runtime when an affected
-CPU is detected. For less-intrusive workarounds, a Kconfig option is not
+With the exception of workarounds for errata deemed "rare" by Arm, these
+are enabled by default and patched in at runtime when an affected CPU is
+detected. For less-intrusive workarounds, a Kconfig option is not
 available and the code is structured (preferably with a comment) in such
 a way that the erratum will not be hit.
 

Documentation/arch/arm64/sme.rst

@@ -75,7 +75,7 @@ model features for SME is included in Appendix A.
 2.  Vector lengths
 ------------------
 
-SME defines a second vector length similar to the SVE vector length which is
+SME defines a second vector length similar to the SVE vector length which
 controls the size of the streaming mode SVE vectors and the ZA matrix array.
 The ZA matrix is square with each side having as many bytes as a streaming
 mode SVE vector.
@@ -238,12 +238,12 @@ prctl(PR_SME_SET_VL, unsigned long arg)
       bits of Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become
       unspecified, including both streaming and non-streaming SVE state.
       Calling PR_SME_SET_VL with vl equal to the thread's current vector
-      length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag,
+      length, or calling PR_SME_SET_VL with the PR_SME_SET_VL_ONEXEC flag,
       does not constitute a change to the vector length for this purpose.
 
     * Changing the vector length causes PSTATE.ZA and PSTATE.SM to be cleared.
       Calling PR_SME_SET_VL with vl equal to the thread's current vector
-      length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag,
+      length, or calling PR_SME_SET_VL with the PR_SME_SET_VL_ONEXEC flag,
       does not constitute a change to the vector length for this purpose.
 
 
@@ -379,9 +379,8 @@ The regset data starts with struct user_za_header, containing:
 /proc/sys/abi/sme_default_vector_length
 
     Writing the text representation of an integer to this file sets the system
-    default vector length to the specified value, unless the value is greater
-    than the maximum vector length supported by the system in which case the
-    default vector length is set to that maximum.
+    default vector length to the specified value rounded to a supported value
+    using the same rules as for setting vector length via PR_SME_SET_VL.
 
     The result can be determined by reopening the file and reading its
     contents.

Documentation/arch/arm64/sve.rst

@@ -117,11 +117,6 @@ the SVE instruction set architecture.
 * The SVE registers are not used to pass arguments to or receive results from
   any syscall.
 
-* In practice the affected registers/bits will be preserved or will be replaced
-  with zeros on return from a syscall, but userspace should not make
-  assumptions about this.  The kernel behaviour may vary on a case-by-case
-  basis.
-
 * All other SVE state of a thread, including the currently configured vector
   length, the state of the PR_SVE_VL_INHERIT flag, and the deferred vector
   length (if any), is preserved across all syscalls, subject to the specific
@@ -428,9 +423,8 @@ The regset data starts with struct user_sve_header, containing:
 /proc/sys/abi/sve_default_vector_length
 
     Writing the text representation of an integer to this file sets the system
-    default vector length to the specified value, unless the value is greater
-    than the maximum vector length supported by the system in which case the
-    default vector length is set to that maximum.
+    default vector length to the specified value rounded to a supported value
+    using the same rules as for setting vector length via PR_SVE_SET_VL.
 
     The result can be determined by reopening the file and reading its
     contents.

Documentation/rust/arch-support.rst

@@ -15,6 +15,7 @@ support corresponds to ``S`` values in the ``MAINTAINERS`` file.
 =============  ================  ==============================================
 Architecture   Level of support  Constraints
 =============  ================  ==============================================
+``arm64``      Maintained        Little Endian only.
 ``loongarch``  Maintained        -
 ``um``         Maintained        ``x86_64`` only.
 ``x86``        Maintained        ``x86_64`` only.

Makefile

@@ -561,7 +561,6 @@ KBUILD_CFLAGS += -fno-strict-aliasing
 
 KBUILD_CPPFLAGS := -D__KERNEL__
 KBUILD_RUSTFLAGS := $(rust_common_flags) \
-		    --target=$(objtree)/scripts/target.json \
 		    -Cpanic=abort -Cembed-bitcode=n -Clto=n \
 		    -Cforce-unwind-tables=n -Ccodegen-units=1 \
 		    -Csymbol-mangling-version=v0 \

arch/arm64/Kconfig

@@ -120,6 +120,7 @@ config ARM64
 	select CLONE_BACKWARDS
 	select COMMON_CLK
 	select CPU_PM if (SUSPEND || CPU_IDLE)
+	select CPUMASK_OFFSTACK if NR_CPUS > 256
 	select CRC32
 	select DCACHE_WORD_ACCESS
 	select DYNAMIC_FTRACE if FUNCTION_TRACER
@@ -198,7 +199,7 @@ config ARM64
 		if DYNAMIC_FTRACE_WITH_ARGS && DYNAMIC_FTRACE_WITH_CALL_OPS
 	select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \
 		if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG && \
-		    !CC_OPTIMIZE_FOR_SIZE)
+		    (CC_IS_CLANG || !CC_OPTIMIZE_FOR_SIZE))
 	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
 		if DYNAMIC_FTRACE_WITH_ARGS
 	select HAVE_SAMPLE_FTRACE_DIRECT
@@ -229,6 +230,7 @@ config ARM64
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select MMU_GATHER_RCU_TABLE_FREE
 	select HAVE_RSEQ
+	select HAVE_RUST if CPU_LITTLE_ENDIAN
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_KPROBES
@@ -547,9 +549,8 @@ config ARM64_ERRATUM_832075
 	  If unsure, say Y.
 
 config ARM64_ERRATUM_834220
-	bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault"
+	bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault (rare)"
 	depends on KVM
-	default y
 	help
 	  This option adds an alternative code sequence to work around ARM
 	  erratum 834220 on Cortex-A57 parts up to r1p2.
@@ -565,7 +566,7 @@ config ARM64_ERRATUM_834220
 	  as it depends on the alternative framework, which will only patch
 	  the kernel if an affected CPU is detected.
 
-	  If unsure, say Y.
+	  If unsure, say N.
 
 config ARM64_ERRATUM_1742098
 	bool "Cortex-A57/A72: 1742098: ELR recorded incorrectly on interrupt taken between cryptographic instructions in a sequence"
@@ -692,8 +693,7 @@ config ARM64_WORKAROUND_REPEAT_TLBI
 	bool
 
 config ARM64_ERRATUM_2441007
-	bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI"
-	default y
+	bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI (rare)"
 	select ARM64_WORKAROUND_REPEAT_TLBI
 	help
 	  This option adds a workaround for ARM Cortex-A55 erratum #2441007.
@@ -706,11 +706,10 @@ config ARM64_ERRATUM_2441007
 	  Work around this by adding the affected CPUs to the list that needs
 	  TLB sequences to be done twice.
 
-	  If unsure, say Y.
+	  If unsure, say N.
 
 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
+	bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation (rare)"
 	select ARM64_WORKAROUND_REPEAT_TLBI
 	help
 	  This option adds a workaround for ARM Cortex-A76 erratum 1286807.
@@ -724,6 +723,8 @@ config ARM64_ERRATUM_1286807
 	  invalidated has been observed by other observers. The
 	  workaround repeats the TLBI+DSB operation.
 
+	  If unsure, say N.
+
 config ARM64_ERRATUM_1463225
 	bool "Cortex-A76: Software Step might prevent interrupt recognition"
 	default y
@@ -743,8 +744,7 @@ config ARM64_ERRATUM_1463225
 	  If unsure, say Y.
 
 config ARM64_ERRATUM_1542419
-	bool "Neoverse-N1: workaround mis-ordering of instruction fetches"
-	default y
+	bool "Neoverse-N1: workaround mis-ordering of instruction fetches (rare)"
 	help
 	  This option adds a workaround for ARM Neoverse-N1 erratum
 	  1542419.
@@ -756,7 +756,7 @@ config ARM64_ERRATUM_1542419
 	  Workaround the issue by hiding the DIC feature from EL0. This
 	  forces user-space to perform cache maintenance.
 
-	  If unsure, say Y.
+	  If unsure, say N.
 
 config ARM64_ERRATUM_1508412
 	bool "Cortex-A77: 1508412: workaround deadlock on sequence of NC/Device load and store exclusive or PAR read"
@@ -931,8 +931,7 @@ config ARM64_ERRATUM_2224489
 	  If unsure, say Y.
 
 config ARM64_ERRATUM_2441009
-	bool "Cortex-A510: Completion of affected memory accesses might not be guaranteed by completion of a TLBI"
-	default y
+	bool "Cortex-A510: Completion of affected memory accesses might not be guaranteed by completion of a TLBI (rare)"
 	select ARM64_WORKAROUND_REPEAT_TLBI
 	help
 	  This option adds a workaround for ARM Cortex-A510 erratum #2441009.
@@ -945,7 +944,7 @@ config ARM64_ERRATUM_2441009
 	  Work around this by adding the affected CPUs to the list that needs
 	  TLB sequences to be done twice.
 
-	  If unsure, say Y.
+	  If unsure, say N.
 
 config ARM64_ERRATUM_2064142
 	bool "Cortex-A510: 2064142: workaround TRBE register writes while disabled"
@@ -1427,7 +1426,7 @@ config SCHED_SMT
 config NR_CPUS
 	int "Maximum number of CPUs (2-4096)"
 	range 2 4096
-	default "256"
+	default "512"
 
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"

arch/arm64/Makefile

@@ -41,6 +41,8 @@ KBUILD_CFLAGS	+= -mgeneral-regs-only	\
 KBUILD_CFLAGS	+= $(call cc-disable-warning, psabi)
 KBUILD_AFLAGS	+= $(compat_vdso)
 
+KBUILD_RUSTFLAGS += --target=aarch64-unknown-none -Ctarget-feature="-neon"
+
 KBUILD_CFLAGS	+= $(call cc-option,-mabi=lp64)
 KBUILD_AFLAGS	+= $(call cc-option,-mabi=lp64)
 
@@ -65,7 +67,9 @@ endif
 
 ifeq ($(CONFIG_ARM64_BTI_KERNEL),y)
   KBUILD_CFLAGS += -mbranch-protection=pac-ret+bti
+  KBUILD_RUSTFLAGS += -Zbranch-protection=bti,pac-ret
 else ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y)
+  KBUILD_RUSTFLAGS += -Zbranch-protection=pac-ret
   ifeq ($(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET),y)
     KBUILD_CFLAGS += -mbranch-protection=pac-ret
   else

arch/arm64/include/asm/assembler.h

@@ -38,10 +38,6 @@
 	msr	daifset, #0xf
 	.endm
 
-	.macro enable_daif
-	msr	daifclr, #0xf
-	.endm
-
 /*
  * Save/restore interrupts.
  */

arch/arm64/include/asm/brk-imm.h

@@ -11,6 +11,7 @@
  * 0x004: for installing kprobes
  * 0x005: for installing uprobes
  * 0x006: for kprobe software single-step
+ * 0x007: for kretprobe return
  * Allowed values for kgdb are 0x400 - 0x7ff
  * 0x100: for triggering a fault on purpose (reserved)
  * 0x400: for dynamic BRK instruction
@@ -23,6 +24,7 @@
 #define KPROBES_BRK_IMM			0x004
 #define UPROBES_BRK_IMM			0x005
 #define KPROBES_BRK_SS_IMM		0x006
+#define KRETPROBES_BRK_IMM		0x007
 #define FAULT_BRK_IMM			0x100
 #define KGDB_DYN_DBG_BRK_IMM		0x400
 #define KGDB_COMPILED_DBG_BRK_IMM	0x401