Merge tag 'riscv-for-linus-6.9-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - Support for various vector-accelerated crypto routines

 - Hibernation is now enabled for portable kernel builds

 - mmap_rnd_bits_max is larger on systems with larger VAs

 - Support for fast GUP

 - Support for membarrier-based instruction cache synchronization

 - Support for the Andes hart-level interrupt controller and PMU

 - Some cleanups around unaligned access speed probing and Kconfig
   settings

 - Support for ACPI LPI and CPPC

 - Various cleanus related to barriers

 - A handful of fixes

* tag 'riscv-for-linus-6.9-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (66 commits)
  riscv: Fix syscall wrapper for >word-size arguments
  crypto: riscv - add vector crypto accelerated AES-CBC-CTS
  crypto: riscv - parallelize AES-CBC decryption
  riscv: Only flush the mm icache when setting an exec pte
  riscv: Use kcalloc() instead of kzalloc()
  riscv/barrier: Add missing space after ','
  riscv/barrier: Consolidate fence definitions
  riscv/barrier: Define RISCV_FULL_BARRIER
  riscv/barrier: Define __{mb,rmb,wmb}
  RISC-V: defconfig: Enable CONFIG_ACPI_CPPC_CPUFREQ
  cpufreq: Move CPPC configs to common Kconfig and add RISC-V
  ACPI: RISC-V: Add CPPC driver
  ACPI: Enable ACPI_PROCESSOR for RISC-V
  ACPI: RISC-V: Add LPI driver
  cpuidle: RISC-V: Move few functions to arch/riscv
  riscv: Introduce set_compat_task() in asm/compat.h
  riscv: Introduce is_compat_thread() into compat.h
  riscv: add compile-time test into is_compat_task()
  riscv: Replace direct thread flag check with is_compat_task()
  riscv: Improve arch_get_mmap_end() macro
  ...

Author: torvalds

Documentation/arch/riscv/vm-layout.rst

@@ -144,14 +144,8 @@ passing 0 into the hint address parameter of mmap. On CPUs with an address space
 smaller than sv48, the CPU maximum supported address space will be the default.
 
 Software can "opt-in" to receiving VAs from another VA space by providing
-a hint address to mmap. A hint address passed to mmap will cause the largest
-address space that fits entirely into the hint to be used, unless there is no
-space left in the address space. If there is no space available in the requested
-address space, an address in the next smallest available address space will be
-returned.
-
-For example, in order to obtain 48-bit VA space, a hint address greater than
-:code:`1 << 47` must be provided. Note that this is 47 due to sv48 userspace
-ending at :code:`1 << 47` and the addresses beyond this are reserved for the
-kernel. Similarly, to obtain 57-bit VA space addresses, a hint address greater
-than or equal to :code:`1 << 56` must be provided.
+a hint address to mmap. When a hint address is passed to mmap, the returned
+address will never use more bits than the hint address. For example, if a hint
+address of `1 << 40` is passed to mmap, a valid returned address will never use
+bits 41 through 63. If no mappable addresses are available in that range, mmap
+will return `MAP_FAILED`.

Documentation/devicetree/bindings/riscv/cpus.yaml

@@ -110,7 +110,11 @@ properties:
         const: 1
 
       compatible:
-        const: riscv,cpu-intc
+        oneOf:
+          - items:
+              - const: andestech,cpu-intc
+              - const: riscv,cpu-intc
+          - const: riscv,cpu-intc
 
       interrupt-controller: true
 

Documentation/devicetree/bindings/riscv/extensions.yaml

@@ -477,5 +477,12 @@ properties:
             latency, as ratified in commit 56ed795 ("Update
             riscv-crypto-spec-vector.adoc") of riscv-crypto.
 
+        - const: xandespmu
+          description:
+            The Andes Technology performance monitor extension for counter overflow
+            and privilege mode filtering. For more details, see Counter Related
+            Registers in the AX45MP datasheet.
+            https://www.andestech.com/wp-content/uploads/AX45MP-1C-Rev.-5.0.0-Datasheet.pdf
+
 additionalProperties: true
 ...

Documentation/features/sched/membarrier-sync-core/arch-support.txt

@@ -10,6 +10,22 @@
 # Rely on implicit context synchronization as a result of exception return
 # when returning from IPI handler, and when returning to user-space.
 #
+# * riscv
+#
+# riscv uses xRET as return from interrupt and to return to user-space.
+#
+# Given that xRET is not core serializing, we rely on FENCE.I for providing
+# core serialization:
+#
+#  - by calling sync_core_before_usermode() on return from interrupt (cf.
+#    ipi_sync_core()),
+#
+#  - via switch_mm() and sync_core_before_usermode() (respectively, for
+#    uthread->uthread and kthread->uthread transitions) before returning
+#    to user-space.
+#
+#  The serialization in switch_mm() is activated by prepare_sync_core_cmd().
+#
 # * x86
 #
 # x86-32 uses IRET as return from interrupt, which takes care of the IPI.
@@ -43,7 +59,7 @@
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
-    |       riscv: | TODO |
+    |       riscv: |  ok  |
     |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: | TODO |

Documentation/scheduler/index.rst

@@ -7,6 +7,7 @@ Scheduler
 
 
     completion
+    membarrier
     sched-arch
     sched-bwc
     sched-deadline

Documentation/scheduler/membarrier.rst

@@ -0,0 +1,39 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+========================
+membarrier() System Call
+========================
+
+MEMBARRIER_CMD_{PRIVATE,GLOBAL}_EXPEDITED - Architecture requirements
+=====================================================================
+
+Memory barriers before updating rq->curr
+----------------------------------------
+
+The commands MEMBARRIER_CMD_PRIVATE_EXPEDITED and MEMBARRIER_CMD_GLOBAL_EXPEDITED
+require each architecture to have a full memory barrier after coming from
+user-space, before updating rq->curr.  This barrier is implied by the sequence
+rq_lock(); smp_mb__after_spinlock() in __schedule().  The barrier matches a full
+barrier in the proximity of the membarrier system call exit, cf.
+membarrier_{private,global}_expedited().
+
+Memory barriers after updating rq->curr
+---------------------------------------
+
+The commands MEMBARRIER_CMD_PRIVATE_EXPEDITED and MEMBARRIER_CMD_GLOBAL_EXPEDITED
+require each architecture to have a full memory barrier after updating rq->curr,
+before returning to user-space.  The schemes providing this barrier on the various
+architectures are as follows.
+
+ - alpha, arc, arm, hexagon, mips rely on the full barrier implied by
+   spin_unlock() in finish_lock_switch().
+
+ - arm64 relies on the full barrier implied by switch_to().
+
+ - powerpc, riscv, s390, sparc, x86 rely on the full barrier implied by
+   switch_mm(), if mm is not NULL; they rely on the full barrier implied
+   by mmdrop(), otherwise.  On powerpc and riscv, switch_mm() relies on
+   membarrier_arch_switch_mm().
+
+The barrier matches a full barrier in the proximity of the membarrier system call
+entry, cf. membarrier_{private,global}_expedited().

MAINTAINERS

@@ -14134,7 +14134,9 @@ M:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
 M:	"Paul E. McKenney" <paulmck@kernel.org>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
-F:	arch/powerpc/include/asm/membarrier.h
+F:	Documentation/scheduler/membarrier.rst
+F:	arch/*/include/asm/membarrier.h
+F:	arch/*/include/asm/sync_core.h
 F:	include/uapi/linux/membarrier.h
 F:	kernel/sched/membarrier.c
 

arch/riscv/Kbuild

@@ -2,6 +2,7 @@
 
 obj-y += kernel/ mm/ net/
 obj-$(CONFIG_BUILTIN_DTB) += boot/dts/
+obj-$(CONFIG_CRYPTO) += crypto/
 obj-y += errata/
 obj-$(CONFIG_KVM) += kvm/
 

arch/riscv/Kconfig

@@ -27,14 +27,18 @@ config RISCV
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_MEMBARRIER_CALLBACKS
+	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_MMIOWB
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PMEM_API
+	select ARCH_HAS_PREPARE_SYNC_CORE_CMD
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_DIRECT_MAP if MMU
 	select ARCH_HAS_SET_MEMORY if MMU
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
 	select ARCH_HAS_STRICT_MODULE_RWX if MMU && !XIP_KERNEL
+	select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
 	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UBSAN
@@ -47,6 +51,9 @@ config RISCV
 	select ARCH_SUPPORTS_CFI_CLANG
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
 	select ARCH_SUPPORTS_HUGETLBFS if MMU
+	# LLD >= 14: https://github.com/llvm/llvm-project/issues/50505
+	select ARCH_SUPPORTS_LTO_CLANG if LLD_VERSION >= 140000
+	select ARCH_SUPPORTS_LTO_CLANG_THIN if LLD_VERSION >= 140000
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU
 	select ARCH_SUPPORTS_PER_VMA_LOCK if MMU
 	select ARCH_SUPPORTS_SHADOW_CALL_STACK if HAVE_SHADOW_CALL_STACK
@@ -106,6 +113,7 @@ config RISCV
 	select HAVE_ARCH_KGDB_QXFER_PKT
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
+	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
@@ -124,6 +132,7 @@ config RISCV
 	select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION
 	select HAVE_EBPF_JIT if MMU
+	select HAVE_FAST_GUP if MMU
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_GCC_PLUGINS
@@ -155,6 +164,7 @@ config RISCV
 	select IRQ_FORCED_THREADING
 	select KASAN_VMALLOC if KASAN
 	select LOCK_MM_AND_FIND_VMA
+	select MMU_GATHER_RCU_TABLE_FREE if SMP && MMU
 	select MODULES_USE_ELF_RELA if MODULES
 	select MODULE_SECTIONS if MODULES
 	select OF
@@ -576,6 +586,13 @@ config TOOLCHAIN_HAS_ZBB
 	depends on LLD_VERSION >= 150000 || LD_VERSION >= 23900
 	depends on AS_HAS_OPTION_ARCH
 
+# This symbol indicates that the toolchain supports all v1.0 vector crypto
+# extensions, including Zvk*, Zvbb, and Zvbc.  LLVM added all of these at once.
+# binutils added all except Zvkb, then added Zvkb.  So we just check for Zvkb.
+config TOOLCHAIN_HAS_VECTOR_CRYPTO
+	def_bool $(as-instr, .option arch$(comma) +v$(comma) +zvkb)
+	depends on AS_HAS_OPTION_ARCH
+
 config RISCV_ISA_ZBB
 	bool "Zbb extension support for bit manipulation instructions"
 	depends on TOOLCHAIN_HAS_ZBB
@@ -686,27 +703,61 @@ config THREAD_SIZE_ORDER
 	  affects irq stack size, which is equal to thread stack size.
 
 config RISCV_MISALIGNED
-	bool "Support misaligned load/store traps for kernel and userspace"
+	bool
 	select SYSCTL_ARCH_UNALIGN_ALLOW
-	default y
 	help
-	  Say Y here if you want the kernel to embed support for misaligned
-	  load/store for both kernel and userspace. When disable, misaligned
-	  accesses will generate SIGBUS in userspace and panic in kernel.
+	  Embed support for emulating misaligned loads and stores.
+
+choice
+	prompt "Unaligned Accesses Support"
+	default RISCV_PROBE_UNALIGNED_ACCESS
+	help
+	  This determines the level of support for unaligned accesses. This
+	  information is used by the kernel to perform optimizations. It is also
+	  exposed to user space via the hwprobe syscall. The hardware will be
+	  probed at boot by default.
+
+config RISCV_PROBE_UNALIGNED_ACCESS
+	bool "Probe for hardware unaligned access support"
+	select RISCV_MISALIGNED
+	help
+	  During boot, the kernel will run a series of tests to determine the
+	  speed of unaligned accesses. This probing will dynamically determine
+	  the speed of unaligned accesses on the underlying system. If unaligned
+	  memory accesses trap into the kernel as they are not supported by the
+	  system, the kernel will emulate the unaligned accesses to preserve the
+	  UABI.
+
+config RISCV_EMULATED_UNALIGNED_ACCESS
+	bool "Emulate unaligned access where system support is missing"
+	select RISCV_MISALIGNED
+	help
+	  If unaligned memory accesses trap into the kernel as they are not
+	  supported by the system, the kernel will emulate the unaligned
+	  accesses to preserve the UABI. When the underlying system does support
+	  unaligned accesses, the unaligned accesses are assumed to be slow.
+
+config RISCV_SLOW_UNALIGNED_ACCESS
+	bool "Assume the system supports slow unaligned memory accesses"
+	depends on NONPORTABLE
+	help
+	  Assume that the system supports slow unaligned memory accesses. The
+	  kernel and userspace programs may not be able to run at all on systems
+	  that do not support unaligned memory accesses.
 
 config RISCV_EFFICIENT_UNALIGNED_ACCESS
-	bool "Assume the CPU supports fast unaligned memory accesses"
+	bool "Assume the system supports fast unaligned memory accesses"
 	depends on NONPORTABLE
 	select DCACHE_WORD_ACCESS if MMU
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	help
-	  Say Y here if you want the kernel to assume that the CPU supports
-	  efficient unaligned memory accesses.  When enabled, this option
-	  improves the performance of the kernel on such CPUs.  However, the
-	  kernel will run much more slowly, or will not be able to run at all,
-	  on CPUs that do not support efficient unaligned memory accesses.
+	  Assume that the system supports fast unaligned memory accesses. When
+	  enabled, this option improves the performance of the kernel on such
+	  systems. However, the kernel and userspace programs will run much more
+	  slowly, or will not be able to run at all, on systems that do not
+	  support efficient unaligned memory accesses.
 
-	  If unsure what to do here, say N.
+endchoice
 
 endmenu # "Platform type"
 
@@ -1011,11 +1062,8 @@ menu "Power management options"
 
 source "kernel/power/Kconfig"
 
-# Hibernation is only possible on systems where the SBI implementation has
-# marked its reserved memory as not accessible from, or does not run
-# from the same memory as, Linux
 config ARCH_HIBERNATION_POSSIBLE
-	def_bool NONPORTABLE
+	def_bool y
 
 config ARCH_HIBERNATION_HEADER
 	def_bool HIBERNATION

arch/riscv/Makefile

@@ -50,6 +50,11 @@ ifndef CONFIG_AS_IS_LLVM
 	KBUILD_CFLAGS += -Wa,-mno-relax
 	KBUILD_AFLAGS += -Wa,-mno-relax
 endif
+# LLVM has an issue with target-features and LTO: https://github.com/llvm/llvm-project/issues/59350
+# Ensure it is aware of linker relaxation with LTO, otherwise relocations may
+# be incorrect: https://github.com/llvm/llvm-project/issues/65090
+else ifeq ($(CONFIG_LTO_CLANG),y)
+	KBUILD_LDFLAGS += -mllvm -mattr=+c -mllvm -mattr=+relax
 endif
 
 ifeq ($(CONFIG_SHADOW_CALL_STACK),y)