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

Pull arm64 updates from Will Deacon:
 "There's a little less than normal, probably due to LPC & Christmas/New
  Year meaning that a few series weren't quite ready or reviewed in
  time. It's still useful across the board, despite the only real
  feature being support for the LS64 feature enabling 64-byte atomic
  accesses to endpoints that support it.

  ACPI:
   - Add interrupt signalling support to the AGDI handler
   - Add Catalin and myself to the arm64 ACPI MAINTAINERS entry

  CPU features:
   - Drop Kconfig options for PAN and LSE (these are detected at runtime)
   - Add support for 64-byte single-copy atomic instructions (LS64/LS64V)
   - Reduce MTE overhead when executing in the kernel on Ampere CPUs
   - Ensure POR_EL0 value exposed via ptrace is up-to-date
   - Fix error handling on GCS allocation failure

  CPU frequency:
   - Add CPU hotplug support to the FIE setup in the AMU driver

  Entry code:
   - Minor optimisations and cleanups to the syscall entry path
   - Preparatory rework for moving to the generic syscall entry code

  Hardware errata:
   - Work around Spectre-BHB on TSV110 processors
   - Work around broken CMO propagation on some systems with the SI-L1
     interconnect

  Miscellaneous:
   - Disable branch profiling for arch/arm64/ to avoid issues with
     noinstr
   - Minor fixes and cleanups (kexec + ubsan, WARN_ONCE() instead of
     WARN_ON(), reduction of boolean expression)
   - Fix custom __READ_ONCE() implementation for LTO builds when
     operating on non-atomic types

  Perf and PMUs:
   - Support for CMN-600AE
   - Be stricter about supported hardware in the CMN driver
   - Support for DSU-110 and DSU-120
   - Support for the cycles event in the DSU driver (alongside the
     dedicated cycles counter)
   - Use IRQF_NO_THREAD instead of IRQF_ONESHOT in the cxlpmu driver
   - Use !bitmap_empty() as a faster alternative to bitmap_weight()
   - Fix SPE error handling when failing to resume profiling

  Selftests:
   - Add support for the FORCE_TARGETS option to the arm64 kselftests
   - Avoid nolibc-specific my_syscall() function
   - Add basic test for the LS64 HWCAP
   - Extend fp-pidbench to cover additional workload patterns"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (43 commits)
  perf/arm-cmn: Reject unsupported hardware configurations
  perf: arm_spe: Properly set hw.state on failures
  arm64/gcs: Fix error handling in arch_set_shadow_stack_status()
  arm64: Fix non-atomic __READ_ONCE() with CONFIG_LTO=y
  arm64: poe: fix stale POR_EL0 values for ptrace
  kselftest/arm64: Raise default number of loops in fp-pidbench
  kselftest/arm64: Add a no-SVE loop after SVE in fp-pidbench
  perf/cxlpmu: Replace IRQF_ONESHOT with IRQF_NO_THREAD
  arm64: mte: Set TCMA1 whenever MTE is present in the kernel
  arm64/ptrace: Return early for ptrace_report_syscall_entry() error
  arm64/ptrace: Split report_syscall()
  arm64: Remove unused _TIF_WORK_MASK
  kselftest/arm64: Add missing file in .gitignore
  arm64: errata: Workaround for SI L1 downstream coherency issue
  kselftest/arm64: Add HWCAP test for FEAT_LS64
  arm64: Add support for FEAT_{LS64, LS64_V}
  KVM: arm64: Enable FEAT_{LS64, LS64_V} in the supported guest
  arm64: Provide basic EL2 setup for FEAT_{LS64, LS64_V} usage at EL0/1
  KVM: arm64: Handle DABT caused by LS64* instructions on unsupported memory
  KVM: arm64: Add documentation for KVM_EXIT_ARM_LDST64B
  ...

Author: torvalds

Documentation/arch/arm64/booting.rst

@@ -556,6 +556,18 @@ Before jumping into the kernel, the following conditions must be met:
 
    - MDCR_EL3.TPM (bit 6) must be initialized to 0b0
 
+  For CPUs with support for 64-byte loads and stores without status (FEAT_LS64):
+
+  - If the kernel is entered at EL1 and EL2 is present:
+
+    - HCRX_EL2.EnALS (bit 1) must be initialised to 0b1.
+
+  For CPUs with support for 64-byte stores with status (FEAT_LS64_V):
+
+  - If the kernel is entered at EL1 and EL2 is present:
+
+    - HCRX_EL2.EnASR (bit 2) must be initialised to 0b1.
+
 The requirements described above for CPU mode, caches, MMUs, architected
 timers, coherency and system registers apply to all CPUs.  All CPUs must
 enter the kernel in the same exception level.  Where the values documented

Documentation/arch/arm64/elf_hwcaps.rst

@@ -444,6 +444,13 @@ HWCAP3_MTE_STORE_ONLY
 HWCAP3_LSFE
     Functionality implied by ID_AA64ISAR3_EL1.LSFE == 0b0001
 
+HWCAP3_LS64
+    Functionality implied by ID_AA64ISAR1_EL1.LS64 == 0b0001. Note that
+    the function of instruction ld64b/st64b requires support by CPU, system
+    and target (device) memory location and HWCAP3_LS64 implies the support
+    of CPU. User should only use ld64b/st64b on supported target (device)
+    memory location, otherwise fallback to the non-atomic alternatives.
+
 
 4. Unused AT_HWCAP bits
 -----------------------

Documentation/arch/arm64/silicon-errata.rst

@@ -212,6 +212,7 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | GIC-700         | #2941627        | ARM64_ERRATUM_2941627       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | SI L1           | #4311569        | ARM64_ERRATUM_4311569       |
 +----------------+-----------------+-----------------+-----------------------------+
 | Broadcom       | Brahma-B53      | N/A             | ARM64_ERRATUM_845719        |
 +----------------+-----------------+-----------------+-----------------------------+

Documentation/virt/kvm/api.rst

@@ -1303,12 +1303,13 @@ userspace, for example because of missing instruction syndrome decode
 information or because there is no device mapped at the accessed IPA, then
 userspace can ask the kernel to inject an external abort using the address
 from the exiting fault on the VCPU. It is a programming error to set
-ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO or
-KVM_EXIT_ARM_NISV. This feature is only available if the system supports
-KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which provides commonality in
-how userspace reports accesses for the above cases to guests, across different
-userspace implementations. Nevertheless, userspace can still emulate all Arm
-exceptions by manipulating individual registers using the KVM_SET_ONE_REG API.
+ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO,
+KVM_EXIT_ARM_NISV, or KVM_EXIT_ARM_LDST64B. This feature is only available if
+the system supports KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which
+provides commonality in how userspace reports accesses for the above cases to
+guests, across different userspace implementations. Nevertheless, userspace
+can still emulate all Arm exceptions by manipulating individual registers
+using the KVM_SET_ONE_REG API.
 
 See KVM_GET_VCPU_EVENTS for the data structure.
 
@@ -7050,12 +7051,14 @@ in send_page or recv a buffer to recv_page).
 
 ::
 
-		/* KVM_EXIT_ARM_NISV */
+		/* KVM_EXIT_ARM_NISV / KVM_EXIT_ARM_LDST64B */
 		struct {
 			__u64 esr_iss;
 			__u64 fault_ipa;
 		} arm_nisv;
 
+- KVM_EXIT_ARM_NISV:
+
 Used on arm64 systems. If a guest accesses memory not in a memslot,
 KVM will typically return to userspace and ask it to do MMIO emulation on its
 behalf. However, for certain classes of instructions, no instruction decode
@@ -7089,6 +7092,32 @@ Note that although KVM_CAP_ARM_NISV_TO_USER will be reported if
 queried outside of a protected VM context, the feature will not be
 exposed if queried on a protected VM file descriptor.
 
+- KVM_EXIT_ARM_LDST64B:
+
+Used on arm64 systems. When a guest using a LD64B, ST64B, ST64BV, ST64BV0,
+outside of a memslot, KVM will return to userspace with KVM_EXIT_ARM_LDST64B,
+exposing the relevant ESR_EL2 information and faulting IPA, similarly to
+KVM_EXIT_ARM_NISV.
+
+Userspace is supposed to fully emulate the instructions, which includes:
+
+	- fetch of the operands for a store, including ACCDATA_EL1 in the case
+	  of a ST64BV0 instruction
+	- deal with the endianness if the guest is big-endian
+	- emulate the access, including the delivery of an exception if the
+	  access didn't succeed
+	- provide a return value in the case of ST64BV/ST64BV0
+	- return the data in the case of a load
+	- increment PC if the instruction was successfully executed
+
+Note that there is no expectation of performance for this emulation, as it
+involves a large number of interaction with the guest state. It is, however,
+expected that the instruction's semantics are preserved, specially the
+single-copy atomicity property of the 64 byte access.
+
+This exit reason must be handled if userspace sets ID_AA64ISAR1_EL1.LS64 to a
+non-zero value, indicating that FEAT_LS64* is enabled.
+
 ::
 
 		/* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */

MAINTAINERS

@@ -336,6 +336,8 @@ ACPI FOR ARM64 (ACPI/arm64)
 M:	Lorenzo Pieralisi <lpieralisi@kernel.org>
 M:	Hanjun Guo <guohanjun@huawei.com>
 M:	Sudeep Holla <sudeep.holla@kernel.org>
+M:	Catalin Marinas <catalin.marinas@arm.com>
+M:	Will Deacon <will@kernel.org>
 L:	linux-acpi@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained

arch/arm/include/asm/syscall.h

@@ -92,8 +92,6 @@ static inline void syscall_set_nr(struct task_struct *task,
 		(nr & __NR_SYSCALL_MASK);
 }
 
-#define SYSCALL_MAX_ARGS 7
-
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
 					 unsigned long *args)

arch/arm64/Kbuild

@@ -1,4 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
+
+# Branch profiling isn't noinstr-safe
+subdir-ccflags-$(CONFIG_TRACE_BRANCH_PROFILING) += -DDISABLE_BRANCH_PROFILING
+
 obj-y			+= kernel/ mm/ net/
 obj-$(CONFIG_KVM)	+= kvm/
 obj-$(CONFIG_XEN)	+= xen/

arch/arm64/Kconfig

@@ -1155,6 +1155,25 @@ config ARM64_ERRATUM_3194386
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_4311569
+	bool "SI L1: 4311569: workaround for premature CMO completion erratum"
+	default y
+	help
+	  This option adds the workaround for ARM SI L1 erratum 4311569.
+
+	  The erratum of SI L1 can cause an early response to a combined write
+	  and cache maintenance operation (WR+CMO) before the operation is fully
+	  completed to the Point of Serialization (POS).
+	  This can result in a non-I/O coherent agent observing stale data,
+	  potentially leading to system instability or incorrect behavior.
+
+	  Enabling this option implements a software workaround by inserting a
+	  second loop of Cache Maintenance Operation (CMO) immediately following the
+	  end of function to do CMOs. This ensures that the data is correctly serialized
+	  before the buffer is handed off to a non-coherent agent.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
@@ -1680,7 +1699,6 @@ config MITIGATE_SPECTRE_BRANCH_HISTORY
 config ARM64_SW_TTBR0_PAN
 	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
 	depends on !KCSAN
-	select ARM64_PAN
 	help
 	  Enabling this option prevents the kernel from accessing
 	  user-space memory directly by pointing TTBR0_EL1 to a reserved
@@ -1859,36 +1877,6 @@ config ARM64_HW_AFDBM
 	  to work on pre-ARMv8.1 hardware and the performance impact is
 	  minimal. If unsure, say Y.
 
-config ARM64_PAN
-	bool "Enable support for Privileged Access Never (PAN)"
-	default y
-	help
-	  Privileged Access Never (PAN; part of the ARMv8.1 Extensions)
-	  prevents the kernel or hypervisor from accessing user-space (EL0)
-	  memory directly.
-
-	  Choosing this option will cause any unprotected (not using
-	  copy_to_user et al) memory access to fail with a permission fault.
-
-	  The feature is detected at runtime, and will remain as a 'nop'
-	  instruction if the cpu does not implement the feature.
-
-config ARM64_LSE_ATOMICS
-	bool
-	default ARM64_USE_LSE_ATOMICS
-
-config ARM64_USE_LSE_ATOMICS
-	bool "Atomic instructions"
-	default y
-	help
-	  As part of the Large System Extensions, ARMv8.1 introduces new
-	  atomic instructions that are designed specifically to scale in
-	  very large systems.
-
-	  Say Y here to make use of these instructions for the in-kernel
-	  atomic routines. This incurs a small overhead on CPUs that do
-	  not support these instructions.
-
 endmenu # "ARMv8.1 architectural features"
 
 menu "ARMv8.2 architectural features"
@@ -2125,7 +2113,6 @@ config ARM64_MTE
 	depends on ARM64_AS_HAS_MTE && ARM64_TAGGED_ADDR_ABI
 	depends on AS_HAS_ARMV8_5
 	# Required for tag checking in the uaccess routines
-	select ARM64_PAN
 	select ARCH_HAS_SUBPAGE_FAULTS
 	select ARCH_USES_HIGH_VMA_FLAGS
 	select ARCH_USES_PG_ARCH_2
@@ -2157,7 +2144,6 @@ menu "ARMv8.7 architectural features"
 config ARM64_EPAN
 	bool "Enable support for Enhanced Privileged Access Never (EPAN)"
 	default y
-	depends on ARM64_PAN
 	help
 	  Enhanced Privileged Access Never (EPAN) allows Privileged
 	  Access Never to be used with Execute-only mappings.

arch/arm64/include/asm/assembler.h

@@ -381,6 +381,9 @@ alternative_endif
 	.macro dcache_by_myline_op op, domain, start, end, linesz, tmp, fixup
 	sub	\tmp, \linesz, #1
 	bic	\start, \start, \tmp
+alternative_if ARM64_WORKAROUND_4311569
+	mov	\tmp, \start
+alternative_else_nop_endif
 .Ldcache_op\@:
 	.ifc	\op, cvau
 	__dcache_op_workaround_clean_cache \op, \start
@@ -402,6 +405,13 @@ alternative_endif
 	add	\start, \start, \linesz
 	cmp	\start, \end
 	b.lo	.Ldcache_op\@
+alternative_if ARM64_WORKAROUND_4311569
+	.ifnc	\op, cvau
+	mov	\start, \tmp
+	mov	\tmp, xzr
+	cbnz	\start, .Ldcache_op\@
+	.endif
+alternative_else_nop_endif
 	dsb	\domain
 
 	_cond_uaccess_extable .Ldcache_op\@, \fixup

arch/arm64/include/asm/cpucaps.h

@@ -19,8 +19,6 @@ cpucap_is_possible(const unsigned int cap)
 			   "cap must be < ARM64_NCAPS");
 
 	switch (cap) {
-	case ARM64_HAS_PAN:
-		return IS_ENABLED(CONFIG_ARM64_PAN);
 	case ARM64_HAS_EPAN:
 		return IS_ENABLED(CONFIG_ARM64_EPAN);
 	case ARM64_SVE: