Merge tag 'riscv-for-linus-6.13-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux into HEAD

RISC-V Paches for the 6.13 Merge Window, Part 1

* Support for pointer masking in userspace,
* Support for probing vector misaligned access performance.
* Support for qspinlock on systems with Zacas and Zabha.

Author: bonzini

Documentation/arch/riscv/hwprobe.rst

@@ -239,6 +239,9 @@ The following keys are defined:
        ratified in commit 98918c844281 ("Merge pull request #1217 from
        riscv/zawrs") of riscv-isa-manual.
 
+  * :c:macro:`RISCV_HWPROBE_EXT_SUPM`: The Supm extension is supported as
+       defined in version 1.0 of the RISC-V Pointer Masking extensions.
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: Deprecated.  Returns similar values to
      :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF`, but the key was
      mistakenly classified as a bitmask rather than a value.
@@ -274,3 +277,19 @@ The following keys are defined:
   represent the highest userspace virtual address usable.
 
 * :c:macro:`RISCV_HWPROBE_KEY_TIME_CSR_FREQ`: Frequency (in Hz) of `time CSR`.
+
+* :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF`: An enum value describing the
+     performance of misaligned vector accesses on the selected set of processors.
+
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN`: The performance of misaligned
+    vector accesses is unknown.
+
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW`: 32-bit misaligned accesses using vector
+    registers are slower than the equivalent quantity of byte accesses via vector registers.
+    Misaligned accesses may be supported directly in hardware, or trapped and emulated by software.
+
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_FAST`: 32-bit misaligned accesses using vector
+    registers are faster than the equivalent quantity of byte accesses via vector registers.
+
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED`: Misaligned vector accesses are
+    not supported at all and will generate a misaligned address fault.

Documentation/arch/riscv/uabi.rst

@@ -68,3 +68,19 @@ Misaligned accesses
 Misaligned scalar accesses are supported in userspace, but they may perform
 poorly.  Misaligned vector accesses are only supported if the Zicclsm extension
 is supported.
+
+Pointer masking
+---------------
+
+Support for pointer masking in userspace (the Supm extension) is provided via
+the ``PR_SET_TAGGED_ADDR_CTRL`` and ``PR_GET_TAGGED_ADDR_CTRL`` ``prctl()``
+operations. Pointer masking is disabled by default. To enable it, userspace
+must call ``PR_SET_TAGGED_ADDR_CTRL`` with the ``PR_PMLEN`` field set to the
+number of mask/tag bits needed by the application. ``PR_PMLEN`` is interpreted
+as a lower bound; if the kernel is unable to satisfy the request, the
+``PR_SET_TAGGED_ADDR_CTRL`` operation will fail. The actual number of tag bits
+is returned in ``PR_PMLEN`` by the ``PR_GET_TAGGED_ADDR_CTRL`` operation.
+
+Additionally, when pointer masking is enabled (``PR_PMLEN`` is greater than 0),
+a tagged address ABI is supported, with the same interface and behavior as
+documented for AArch64 (Documentation/arch/arm64/tagged-address-abi.rst).

Documentation/devicetree/bindings/riscv/extensions.yaml

@@ -128,6 +128,18 @@ properties:
             changes to interrupts as frozen at commit ccbddab ("Merge pull
             request #42 from riscv/jhauser-2023-RC4") of riscv-aia.
 
+        - const: smmpm
+          description: |
+            The standard Smmpm extension for M-mode pointer masking as
+            ratified at commit d70011dde6c2 ("Update to ratified state")
+            of riscv-j-extension.
+
+        - const: smnpm
+          description: |
+            The standard Smnpm extension for next-mode pointer masking as
+            ratified at commit d70011dde6c2 ("Update to ratified state")
+            of riscv-j-extension.
+
         - const: smstateen
           description: |
             The standard Smstateen extension for controlling access to CSRs
@@ -147,6 +159,12 @@ properties:
             and mode-based filtering as ratified at commit 01d1df0 ("Add ability
             to manually trigger workflow. (#2)") of riscv-count-overflow.
 
+        - const: ssnpm
+          description: |
+            The standard Ssnpm extension for next-mode pointer masking as
+            ratified at commit d70011dde6c2 ("Update to ratified state")
+            of riscv-j-extension.
+
         - const: sstc
           description: |
             The standard Sstc supervisor-level extension for time compare as
@@ -178,6 +196,12 @@ properties:
             as ratified at commit 4a69197e5617 ("Update to ratified state") of
             riscv-svvptc.
 
+        - const: zabha
+          description: |
+            The Zabha extension for Byte and Halfword Atomic Memory Operations
+            as ratified at commit 49f49c842ff9 ("Update to Rafified state") of
+            riscv-zabha.
+
         - const: zacas
           description: |
             The Zacas extension for Atomic Compare-and-Swap (CAS) instructions
@@ -290,6 +314,12 @@ properties:
             in commit 64074bc ("Update version numbers for Zfh/Zfinx") of
             riscv-isa-manual.
 
+        - const: ziccrse
+          description:
+            The standard Ziccrse extension which provides forward progress
+            guarantee on LR/SC sequences, as ratified in commit b1d806605f87
+            ("Updated to ratified state.") of the riscv profiles specification.
+
         - const: zk
           description:
             The standard Zk Standard Scalar cryptography extension as ratified

Documentation/features/locking/queued-spinlocks/arch-support.txt

@@ -20,7 +20,7 @@
     |    openrisc: |  ok  |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
-    |       riscv: | TODO |
+    |       riscv: |  ok  |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: |  ok  |

arch/riscv/Kconfig

@@ -82,6 +82,7 @@ config RISCV
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select ARCH_WEAK_RELEASE_ACQUIRE if ARCH_USE_QUEUED_SPINLOCKS
 	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
 	select BUILDTIME_TABLE_SORT if MMU
 	select CLINT_TIMER if RISCV_M_MODE
@@ -115,6 +116,7 @@ config RISCV
 	select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO
 	select HARDIRQS_SW_RESEND
 	select HAS_IOPORT if MMU
+	select HAVE_ALIGNED_STRUCT_PAGE
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT
@@ -506,6 +508,39 @@ config NODES_SHIFT
 	  Specify the maximum number of NUMA Nodes available on the target
 	  system.  Increases memory reserved to accommodate various tables.
 
+choice
+	prompt "RISC-V spinlock type"
+	default RISCV_COMBO_SPINLOCKS
+
+config RISCV_TICKET_SPINLOCKS
+	bool "Using ticket spinlock"
+
+config RISCV_QUEUED_SPINLOCKS
+	bool "Using queued spinlock"
+	depends on SMP && MMU && NONPORTABLE
+	select ARCH_USE_QUEUED_SPINLOCKS
+	help
+	  The queued spinlock implementation requires the forward progress
+	  guarantee of cmpxchg()/xchg() atomic operations: CAS with Zabha or
+	  LR/SC with Ziccrse provide such guarantee.
+
+	  Select this if and only if Zabha or Ziccrse is available on your
+	  platform, RISCV_QUEUED_SPINLOCKS must not be selected for platforms
+	  without one of those extensions.
+
+	  If unsure, select RISCV_COMBO_SPINLOCKS, which will use qspinlocks
+	  when supported and otherwise ticket spinlocks.
+
+config RISCV_COMBO_SPINLOCKS
+	bool "Using combo spinlock"
+	depends on SMP && MMU
+	select ARCH_USE_QUEUED_SPINLOCKS
+	help
+	  Embed both queued spinlock and ticket lock so that the spinlock
+	  implementation can be chosen at runtime.
+
+endchoice
+
 config RISCV_ALTERNATIVE
 	bool
 	depends on !XIP_KERNEL
@@ -531,6 +566,17 @@ config RISCV_ISA_C
 
 	  If you don't know what to do here, say Y.
 
+config RISCV_ISA_SUPM
+	bool "Supm extension for userspace pointer masking"
+	depends on 64BIT
+	default y
+	help
+	  Add support for pointer masking in userspace (Supm) when the
+	  underlying hardware extension (Smnpm or Ssnpm) is detected at boot.
+
+	  If this option is disabled, userspace will be unable to use
+	  the prctl(PR_{SET,GET}_TAGGED_ADDR_CTRL) API.
+
 config RISCV_ISA_SVNAPOT
 	bool "Svnapot extension support for supervisor mode NAPOT pages"
 	depends on 64BIT && MMU
@@ -632,6 +678,40 @@ config RISCV_ISA_ZAWRS
 	  use of these instructions in the kernel when the Zawrs extension is
 	  detected at boot.
 
+config TOOLCHAIN_HAS_ZABHA
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zabha)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zabha)
+	depends on AS_HAS_OPTION_ARCH
+
+config RISCV_ISA_ZABHA
+	bool "Zabha extension support for atomic byte/halfword operations"
+	depends on TOOLCHAIN_HAS_ZABHA
+	depends on RISCV_ALTERNATIVE
+	default y
+	help
+	  Enable the use of the Zabha ISA-extension to implement kernel
+	  byte/halfword atomic memory operations when it is detected at boot.
+
+	  If you don't know what to do here, say Y.
+
+config TOOLCHAIN_HAS_ZACAS
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zacas)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zacas)
+	depends on AS_HAS_OPTION_ARCH
+
+config RISCV_ISA_ZACAS
+	bool "Zacas extension support for atomic CAS"
+	depends on TOOLCHAIN_HAS_ZACAS
+	depends on RISCV_ALTERNATIVE
+	default y
+	help
+	  Enable the use of the Zacas ISA-extension to implement kernel atomic
+	  cmpxchg operations when it is detected at boot.
+
 	  If you don't know what to do here, say Y.
 
 config TOOLCHAIN_HAS_ZBB
@@ -785,10 +865,24 @@ config THREAD_SIZE_ORDER
 
 config RISCV_MISALIGNED
 	bool
+	help
+	  Embed support for detecting and emulating misaligned
+	  scalar or vector loads and stores.
+
+config RISCV_SCALAR_MISALIGNED
+	bool
+	select RISCV_MISALIGNED
 	select SYSCTL_ARCH_UNALIGN_ALLOW
 	help
 	  Embed support for emulating misaligned loads and stores.
 
+config RISCV_VECTOR_MISALIGNED
+	bool
+	select RISCV_MISALIGNED
+	depends on RISCV_ISA_V
+	help
+	  Enable detecting support for vector misaligned loads and stores.
+
 choice
 	prompt "Unaligned Accesses Support"
 	default RISCV_PROBE_UNALIGNED_ACCESS
@@ -800,7 +894,7 @@ choice
 
 config RISCV_PROBE_UNALIGNED_ACCESS
 	bool "Probe for hardware unaligned access support"
-	select RISCV_MISALIGNED
+	select RISCV_SCALAR_MISALIGNED
 	help
 	  During boot, the kernel will run a series of tests to determine the
 	  speed of unaligned accesses. This probing will dynamically determine
@@ -811,7 +905,7 @@ config RISCV_PROBE_UNALIGNED_ACCESS
 
 config RISCV_EMULATED_UNALIGNED_ACCESS
 	bool "Emulate unaligned access where system support is missing"
-	select RISCV_MISALIGNED
+	select RISCV_SCALAR_MISALIGNED
 	help
 	  If unaligned memory accesses trap into the kernel as they are not
 	  supported by the system, the kernel will emulate the unaligned
@@ -840,6 +934,46 @@ config RISCV_EFFICIENT_UNALIGNED_ACCESS
 
 endchoice
 
+choice
+	prompt "Vector unaligned Accesses Support"
+	depends on RISCV_ISA_V
+	default RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+	help
+	  This determines the level of support for vector 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_VECTOR_UNALIGNED_ACCESS
+	bool "Probe speed of vector unaligned accesses"
+	select RISCV_VECTOR_MISALIGNED
+	depends on RISCV_ISA_V
+	help
+	  During boot, the kernel will run a series of tests to determine the
+	  speed of vector unaligned accesses if they are supported. This probing
+	  will dynamically determine the speed of vector unaligned accesses on
+	  the underlying system if they are supported.
+
+config RISCV_SLOW_VECTOR_UNALIGNED_ACCESS
+	bool "Assume the system supports slow vector unaligned memory accesses"
+	depends on NONPORTABLE
+	help
+	  Assume that the system supports slow vector 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_VECTOR_UNALIGNED_ACCESS
+	bool "Assume the system supports fast vector unaligned memory accesses"
+	depends on NONPORTABLE
+	help
+	  Assume that the system supports fast vector 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.
+
+endchoice
+
 source "arch/riscv/Kconfig.vendor"
 
 endmenu # "Platform type"

arch/riscv/Makefile

@@ -82,6 +82,12 @@ else
 riscv-march-$(CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI) := $(riscv-march-y)_zicsr_zifencei
 endif
 
+# Check if the toolchain supports Zacas
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZACAS) := $(riscv-march-y)_zacas
+
+# Check if the toolchain supports Zabha
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZABHA) := $(riscv-march-y)_zabha
+
 # Remove F,D,V from isa string for all. Keep extensions between "fd" and "v" by
 # matching non-v and non-multi-letter extensions out with the filter ([^v_]*)
 KBUILD_CFLAGS += -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)fd([^v_]*)v?/\1\2/')

arch/riscv/configs/defconfig

@@ -167,6 +167,7 @@ CONFIG_PINCTRL_SOPHGO_CV1800B=y
 CONFIG_PINCTRL_SOPHGO_CV1812H=y
 CONFIG_PINCTRL_SOPHGO_SG2000=y
 CONFIG_PINCTRL_SOPHGO_SG2002=y
+CONFIG_GPIO_DWAPB=y
 CONFIG_GPIO_SIFIVE=y
 CONFIG_POWER_RESET_GPIO_RESTART=y
 CONFIG_SENSORS_SFCTEMP=m

arch/riscv/include/asm/Kbuild

@@ -6,10 +6,12 @@ generic-y += early_ioremap.h
 generic-y += flat.h
 generic-y += kvm_para.h
 generic-y += mmzone.h
+generic-y += mcs_spinlock.h
 generic-y += parport.h
-generic-y += spinlock.h
 generic-y += spinlock_types.h
+generic-y += ticket_spinlock.h
 generic-y += qrwlock.h
 generic-y += qrwlock_types.h
+generic-y += qspinlock.h
 generic-y += user.h
 generic-y += vmlinux.lds.h