Merge tag 'riscv-for-linus-6.8-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - Support for many new extensions in hwprobe, along with a handful of
   cleanups

 - Various cleanups to our page table handling code, so we alwayse use
   {READ,WRITE}_ONCE

 - Support for the which-cpus flavor of hwprobe

 - Support for XIP kernels has been resurrected

* tag 'riscv-for-linus-6.8-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (52 commits)
  riscv: hwprobe: export Zicond extension
  riscv: hwprobe: export Zacas ISA extension
  riscv: add ISA extension parsing for Zacas
  dt-bindings: riscv: add Zacas ISA extension description
  riscv: hwprobe: export Ztso ISA extension
  riscv: add ISA extension parsing for Ztso
  use linux/export.h rather than asm-generic/export.h
  riscv: Remove SHADOW_OVERFLOW_STACK_SIZE macro
  riscv; fix __user annotation in save_v_state()
  riscv: fix __user annotation in traps_misaligned.c
  riscv: Select ARCH_WANTS_NO_INSTR
  riscv: Remove obsolete rv32_defconfig file
  riscv: Allow disabling of BUILTIN_DTB for XIP
  riscv: Fixed wrong register in XIP_FIXUP_FLASH_OFFSET macro
  riscv: Make XIP bootable again
  riscv: Fix set_direct_map_default_noflush() to reset _PAGE_EXEC
  riscv: Fix module_alloc() that did not reset the linear mapping permissions
  riscv: Fix wrong usage of lm_alias() when splitting a huge linear mapping
  riscv: Check if the code to patch lies in the exit section
  riscv: Use the same CPU operations for all CPUs
  ...

Documentation/arch/riscv/hwprobe.rst

@@ -12,7 +12,7 @@ is defined in <asm/hwprobe.h>::
     };
 
     long sys_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-                           size_t cpu_count, cpu_set_t *cpus,
+                           size_t cpusetsize, cpu_set_t *cpus,
                            unsigned int flags);
 
 The arguments are split into three groups: an array of key-value pairs, a CPU
@@ -20,12 +20,26 @@ set, and some flags. The key-value pairs are supplied with a count. Userspace
 must prepopulate the key field for each element, and the kernel will fill in the
 value if the key is recognized. If a key is unknown to the kernel, its key field
 will be cleared to -1, and its value set to 0. The CPU set is defined by
-CPU_SET(3). For value-like keys (eg. vendor/arch/impl), the returned value will
-be only be valid if all CPUs in the given set have the same value. Otherwise -1
-will be returned. For boolean-like keys, the value returned will be a logical
-AND of the values for the specified CPUs. Usermode can supply NULL for cpus and
-0 for cpu_count as a shortcut for all online CPUs. There are currently no flags,
-this value must be zero for future compatibility.
+CPU_SET(3) with size ``cpusetsize`` bytes. For value-like keys (eg. vendor,
+arch, impl), the returned value will only be valid if all CPUs in the given set
+have the same value. Otherwise -1 will be returned. For boolean-like keys, the
+value returned will be a logical AND of the values for the specified CPUs.
+Usermode can supply NULL for ``cpus`` and 0 for ``cpusetsize`` as a shortcut for
+all online CPUs. The currently supported flags are:
+
+* :c:macro:`RISCV_HWPROBE_WHICH_CPUS`: This flag basically reverses the behavior
+  of sys_riscv_hwprobe().  Instead of populating the values of keys for a given
+  set of CPUs, the values of each key are given and the set of CPUs is reduced
+  by sys_riscv_hwprobe() to only those which match each of the key-value pairs.
+  How matching is done depends on the key type.  For value-like keys, matching
+  means to be the exact same as the value.  For boolean-like keys, matching
+  means the result of a logical AND of the pair's value with the CPU's value is
+  exactly the same as the pair's value.  Additionally, when ``cpus`` is an empty
+  set, then it is initialized to all online CPUs which fit within it, i.e. the
+  CPU set returned is the reduction of all the online CPUs which can be
+  represented with a CPU set of size ``cpusetsize``.
+
+All other flags are reserved for future compatibility and must be zero.
 
 On success 0 is returned, on failure a negative error code is returned.
 
@@ -80,6 +94,100 @@ The following keys are defined:
   * :c:macro:`RISCV_HWPROBE_EXT_ZICBOZ`: The Zicboz extension is supported, as
        ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs.
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBC` The Zbc extension is supported, as defined
+       in version 1.0 of the Bit-Manipulation ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBKB` The Zbkb extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBKC` The Zbkc extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBKX` The Zbkx extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKND` The Zknd extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKNE` The Zkne extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKNH` The Zknh extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKSED` The Zksed extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKSH` The Zksh extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKT` The Zkt extension is supported, as defined
+       in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVBB`: The Zvbb extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVBC`: The Zvbc extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKB`: The Zvkb extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKG`: The Zvkg extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKNED`: The Zvkned extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKNHA`: The Zvknha extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKNHB`: The Zvknhb extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKSED`: The Zvksed extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKSH`: The Zvksh extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKT`: The Zvkt extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZFH`: The Zfh extension version 1.0 is supported
+       as defined in the RISC-V ISA manual.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZFHMIN`: The Zfhmin extension version 1.0 is
+       supported as defined in the RISC-V ISA manual.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZIHINTNTL`: The Zihintntl extension version 1.0
+       is supported as defined in the RISC-V ISA manual.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVFH`: The Zvfh extension is supported as
+       defined in the RISC-V Vector manual starting from commit e2ccd0548d6c
+       ("Remove draft warnings from Zvfh[min]").
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVFHMIN`: The Zvfhmin extension is supported as
+       defined in the RISC-V Vector manual starting from commit e2ccd0548d6c
+       ("Remove draft warnings from Zvfh[min]").
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZFA`: The Zfa extension is supported as
+       defined in the RISC-V ISA manual starting from commit 056b6ff467c7
+       ("Zfa is ratified").
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZTSO`: The Ztso extension is supported as
+       defined in the RISC-V ISA manual starting from commit 5618fb5a216b
+       ("Ztso is now ratified.")
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZACAS`: The Zacas extension is supported as
+       defined in the Atomic Compare-and-Swap (CAS) instructions manual starting
+       from commit 5059e0ca641c ("update to ratified").
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZICOND`: The Zicond extension is supported as
+       defined in the RISC-V Integer Conditional (Zicond) operations extension
+       manual starting from commit 95cf1f9 ("Add changes requested by Ved
+       during signoff")
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 

Documentation/devicetree/bindings/riscv/cpus.yaml

@@ -32,6 +32,7 @@ properties:
     oneOf:
       - items:
           - enum:
+              - amd,mbv32
               - andestech,ax45mp
               - canaan,k210
               - sifive,bullet0

arch/arm/include/asm/pgtable.h

@@ -151,6 +151,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
+#define pgdp_get(pgpd)		READ_ONCE(*pgdp)
+
 #define pud_page(pud)		pmd_page(__pmd(pud_val(pud)))
 #define pud_write(pud)		pmd_write(__pmd(pud_val(pud)))
 

arch/riscv/Kconfig

@@ -59,6 +59,7 @@ config RISCV
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select ARCH_WANT_LD_ORPHAN_WARN if !XIP_KERNEL
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
+	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
 	select BUILDTIME_TABLE_SORT if MMU
@@ -902,13 +903,13 @@ config RISCV_ISA_FALLBACK
 	  on the replacement properties, "riscv,isa-base" and
 	  "riscv,isa-extensions".
 
-endmenu # "Boot options"
-
 config BUILTIN_DTB
-	bool
+	bool "Built-in device tree"
 	depends on OF && NONPORTABLE
 	default y if XIP_KERNEL
 
+endmenu # "Boot options"
+
 config PORTABLE
 	bool
 	default !NONPORTABLE

arch/riscv/configs/rv32_defconfig

-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ_IDLE=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BPF_SYSCALL=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_CGROUPS=y
-CONFIG_CGROUP_SCHED=y
-CONFIG_CFS_BANDWIDTH=y
-CONFIG_CGROUP_BPF=y
-CONFIG_NAMESPACES=y
-CONFIG_USER_NS=y
-CONFIG_CHECKPOINT_RESTORE=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_PROFILING=y
-CONFIG_SOC_SIFIVE=y
-CONFIG_SOC_VIRT=y
-CONFIG_NONPORTABLE=y
-CONFIG_ARCH_RV32I=y
-CONFIG_SMP=y
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PM=y
-CONFIG_CPU_IDLE=y
-CONFIG_VIRTUALIZATION=y
-CONFIG_KVM=m
-CONFIG_JUMP_LABEL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_IP_PNP_RARP=y
-CONFIG_NETLINK_DIAG=y
-CONFIG_NET_9P=y
-CONFIG_NET_9P_VIRTIO=y
-CONFIG_PCI=y
-CONFIG_PCIEPORTBUS=y
-CONFIG_PCI_HOST_GENERIC=y
-CONFIG_PCIE_XILINX=y
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_SCSI_VIRTIO=y
-CONFIG_ATA=y
-CONFIG_SATA_AHCI=y
-CONFIG_SATA_AHCI_PLATFORM=y
-CONFIG_NETDEVICES=y
-CONFIG_VIRTIO_NET=y
-CONFIG_MACB=y
-CONFIG_E1000E=y
-CONFIG_R8169=y
-CONFIG_MICROSEMI_PHY=y
-CONFIG_INPUT_MOUSEDEV=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_OF_PLATFORM=y
-CONFIG_VIRTIO_CONSOLE=y
-CONFIG_HW_RANDOM=y
-CONFIG_HW_RANDOM_VIRTIO=y
-CONFIG_SPI=y
-CONFIG_SPI_SIFIVE=y
-# CONFIG_PTP_1588_CLOCK is not set
-CONFIG_DRM=y
-CONFIG_DRM_RADEON=y
-CONFIG_DRM_VIRTIO_GPU=y
-CONFIG_FB=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_USB=y
-CONFIG_USB_XHCI_HCD=y
-CONFIG_USB_XHCI_PLATFORM=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_OHCI_HCD_PLATFORM=y
-CONFIG_USB_STORAGE=y
-CONFIG_USB_UAS=y
-CONFIG_MMC=y
-CONFIG_MMC_SPI=y
-CONFIG_RTC_CLASS=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_INPUT=y
-CONFIG_VIRTIO_MMIO=y
-CONFIG_RPMSG_CHAR=y
-CONFIG_RPMSG_CTRL=y
-CONFIG_RPMSG_VIRTIO=y
-CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_POSIX_ACL=y
-CONFIG_AUTOFS_FS=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_HUGETLBFS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
-CONFIG_NFS_V4_1=y
-CONFIG_NFS_V4_2=y
-CONFIG_ROOT_NFS=y
-CONFIG_9P_FS=y
-CONFIG_CRYPTO_USER_API_HASH=y
-CONFIG_CRYPTO_DEV_VIRTIO=y
-CONFIG_PRINTK_TIME=y
-CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_PAGEALLOC=y
-CONFIG_SCHED_STACK_END_CHECK=y
-CONFIG_DEBUG_VM=y
-CONFIG_DEBUG_VM_PGFLAGS=y
-CONFIG_DEBUG_MEMORY_INIT=y
-CONFIG_DEBUG_PER_CPU_MAPS=y
-CONFIG_SOFTLOCKUP_DETECTOR=y
-CONFIG_WQ_WATCHDOG=y
-CONFIG_DEBUG_TIMEKEEPING=y
-CONFIG_DEBUG_RT_MUTEXES=y
-CONFIG_DEBUG_SPINLOCK=y
-CONFIG_DEBUG_MUTEXES=y
-CONFIG_DEBUG_RWSEMS=y
-CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_STACKTRACE=y
-CONFIG_DEBUG_LIST=y
-CONFIG_DEBUG_PLIST=y
-CONFIG_DEBUG_SG=y
-# CONFIG_RCU_TRACE is not set
-CONFIG_RCU_EQS_DEBUG=y
-# CONFIG_FTRACE is not set
-# CONFIG_RUNTIME_TESTING_MENU is not set
-CONFIG_MEMTEST=y

arch/riscv/include/asm/cpu_ops.h

@@ -13,33 +13,23 @@
 /**
  * struct cpu_operations - Callback operations for hotplugging CPUs.
  *
- * @name:		Name of the boot protocol.
- * @cpu_prepare:	Early one-time preparation step for a cpu. If there
- *			is a mechanism for doing so, tests whether it is
- *			possible to boot the given HART.
  * @cpu_start:		Boots a cpu into the kernel.
- * @cpu_disable:	Prepares a cpu to die. May fail for some
- *			mechanism-specific reason, which will cause the hot
- *			unplug to be aborted. Called from the cpu to be killed.
  * @cpu_stop:		Makes a cpu leave the kernel. Must not fail. Called from
  *			the cpu being stopped.
  * @cpu_is_stopped:	Ensures a cpu has left the kernel. Called from another
  *			cpu.
  */
 struct cpu_operations {
-	const char	*name;
-	int		(*cpu_prepare)(unsigned int cpu);
 	int		(*cpu_start)(unsigned int cpu,
 				     struct task_struct *tidle);
 #ifdef CONFIG_HOTPLUG_CPU
-	int		(*cpu_disable)(unsigned int cpu);
 	void		(*cpu_stop)(void);
 	int		(*cpu_is_stopped)(unsigned int cpu);
 #endif
 };
 
 extern const struct cpu_operations cpu_ops_spinwait;
-extern const struct cpu_operations *cpu_ops[NR_CPUS];
-void __init cpu_set_ops(int cpu);
+extern const struct cpu_operations *cpu_ops;
+void __init cpu_set_ops(void);
 
 #endif /* ifndef __ASM_CPU_OPS_H */

arch/riscv/include/asm/cpufeature.h

@@ -59,6 +59,8 @@ struct riscv_isa_ext_data {
 	const unsigned int id;
 	const char *name;
 	const char *property;
+	const unsigned int *subset_ext_ids;
+	const unsigned int subset_ext_size;
 };
 
 extern const struct riscv_isa_ext_data riscv_isa_ext[];
@@ -67,7 +69,7 @@ extern bool riscv_isa_fallback;
 
 unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
 
-bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit);
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit);
 #define riscv_isa_extension_available(isa_bitmap, ext)	\
 	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
 

arch/riscv/include/asm/hwcap.h

@@ -11,19 +11,13 @@
 #include <uapi/asm/hwcap.h>
 
 #define RISCV_ISA_EXT_a		('a' - 'a')
-#define RISCV_ISA_EXT_b		('b' - 'a')
 #define RISCV_ISA_EXT_c		('c' - 'a')
 #define RISCV_ISA_EXT_d		('d' - 'a')
 #define RISCV_ISA_EXT_f		('f' - 'a')
 #define RISCV_ISA_EXT_h		('h' - 'a')
 #define RISCV_ISA_EXT_i		('i' - 'a')
-#define RISCV_ISA_EXT_j		('j' - 'a')
-#define RISCV_ISA_EXT_k		('k' - 'a')
 #define RISCV_ISA_EXT_m		('m' - 'a')
-#define RISCV_ISA_EXT_p		('p' - 'a')
 #define RISCV_ISA_EXT_q		('q' - 'a')
-#define RISCV_ISA_EXT_s		('s' - 'a')
-#define RISCV_ISA_EXT_u		('u' - 'a')
 #define RISCV_ISA_EXT_v		('v' - 'a')
 
 /*
@@ -57,8 +51,38 @@
 #define RISCV_ISA_EXT_ZIHPM		42
 #define RISCV_ISA_EXT_SMSTATEEN		43
 #define RISCV_ISA_EXT_ZICOND		44
+#define RISCV_ISA_EXT_ZBC		45
+#define RISCV_ISA_EXT_ZBKB		46
+#define RISCV_ISA_EXT_ZBKC		47
+#define RISCV_ISA_EXT_ZBKX		48
+#define RISCV_ISA_EXT_ZKND		49
+#define RISCV_ISA_EXT_ZKNE		50
+#define RISCV_ISA_EXT_ZKNH		51
+#define RISCV_ISA_EXT_ZKR		52
+#define RISCV_ISA_EXT_ZKSED		53
+#define RISCV_ISA_EXT_ZKSH		54
+#define RISCV_ISA_EXT_ZKT		55
+#define RISCV_ISA_EXT_ZVBB		56
+#define RISCV_ISA_EXT_ZVBC		57
+#define RISCV_ISA_EXT_ZVKB		58
+#define RISCV_ISA_EXT_ZVKG		59
+#define RISCV_ISA_EXT_ZVKNED		60
+#define RISCV_ISA_EXT_ZVKNHA		61
+#define RISCV_ISA_EXT_ZVKNHB		62
+#define RISCV_ISA_EXT_ZVKSED		63
+#define RISCV_ISA_EXT_ZVKSH		64
+#define RISCV_ISA_EXT_ZVKT		65
+#define RISCV_ISA_EXT_ZFH		66
+#define RISCV_ISA_EXT_ZFHMIN		67
+#define RISCV_ISA_EXT_ZIHINTNTL		68
+#define RISCV_ISA_EXT_ZVFH		69
+#define RISCV_ISA_EXT_ZVFHMIN		70
+#define RISCV_ISA_EXT_ZFA		71
+#define RISCV_ISA_EXT_ZTSO		72
+#define RISCV_ISA_EXT_ZACAS		73
 
-#define RISCV_ISA_EXT_MAX		64
+#define RISCV_ISA_EXT_MAX		128
+#define RISCV_ISA_EXT_INVALID		U32_MAX
 
 #ifdef CONFIG_RISCV_M_MODE
 #define RISCV_ISA_EXT_SxAIA		RISCV_ISA_EXT_SMAIA

arch/riscv/include/asm/hwprobe.h

@@ -15,4 +15,28 @@ static inline bool riscv_hwprobe_key_is_valid(__s64 key)
 	return key >= 0 && key <= RISCV_HWPROBE_MAX_KEY;
 }
 
+static inline bool hwprobe_key_is_bitmask(__s64 key)
+{
+	switch (key) {
+	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
+	case RISCV_HWPROBE_KEY_IMA_EXT_0:
+	case RISCV_HWPROBE_KEY_CPUPERF_0:
+		return true;
+	}
+
+	return false;
+}
+
+static inline bool riscv_hwprobe_pair_cmp(struct riscv_hwprobe *pair,
+					  struct riscv_hwprobe *other_pair)
+{
+	if (pair->key != other_pair->key)
+		return false;
+
+	if (hwprobe_key_is_bitmask(pair->key))
+		return (pair->value & other_pair->value) == other_pair->value;
+
+	return pair->value == other_pair->value;
+}
+
 #endif

arch/riscv/include/asm/kfence.h

@@ -18,9 +18,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
 	pte_t *pte = virt_to_kpte(addr);
 
 	if (protect)
-		set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~_PAGE_PRESENT));
 	else
-		set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT));
 
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 

arch/riscv/include/asm/pgtable-64.h

@@ -202,7 +202,7 @@ static inline int pud_user(pud_t pud)
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
-	*pudp = pud;
+	WRITE_ONCE(*pudp, pud);
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -278,7 +278,7 @@ static inline unsigned long _pmd_pfn(pmd_t pmd)
 static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
 	if (pgtable_l4_enabled)
-		*p4dp = p4d;
+		WRITE_ONCE(*p4dp, p4d);
 	else
 		set_pud((pud_t *)p4dp, (pud_t){ p4d_val(p4d) });
 }
@@ -340,18 +340,12 @@ static inline struct page *p4d_page(p4d_t p4d)
 #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
 
 #define pud_offset pud_offset
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
-{
-	if (pgtable_l4_enabled)
-		return p4d_pgtable(*p4d) + pud_index(address);
-
-	return (pud_t *)p4d;
-}
+pud_t *pud_offset(p4d_t *p4d, unsigned long address);
 
 static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
 	if (pgtable_l5_enabled)
-		*pgdp = pgd;
+		WRITE_ONCE(*pgdp, pgd);
 	else
 		set_p4d((p4d_t *)pgdp, (p4d_t){ pgd_val(pgd) });
 }
@@ -404,12 +398,6 @@ static inline struct page *pgd_page(pgd_t pgd)
 #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1))
 
 #define p4d_offset p4d_offset
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
-{
-	if (pgtable_l5_enabled)
-		return pgd_pgtable(*pgd) + p4d_index(address);
-
-	return (p4d_t *)pgd;
-}
+p4d_t *p4d_offset(pgd_t *pgd, unsigned long address);
 
 #endif /* _ASM_RISCV_PGTABLE_64_H */

arch/riscv/include/asm/pgtable.h

@@ -248,7 +248,7 @@ static inline int pmd_leaf(pmd_t pmd)
 
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
-	*pmdp = pmd;
+	WRITE_ONCE(*pmdp, pmd);
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
@@ -510,7 +510,7 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
  */
 static inline void set_pte(pte_t *ptep, pte_t pteval)
 {
-	*ptep = pteval;
+	WRITE_ONCE(*ptep, pteval);
 }
 
 void flush_icache_pte(pte_t pte);
@@ -544,19 +544,12 @@ static inline void pte_clear(struct mm_struct *mm,
 	__set_pte_at(ptep, __pte(0));
 }
 
-#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-static inline int ptep_set_access_flags(struct vm_area_struct *vma,
-					unsigned long address, pte_t *ptep,
-					pte_t entry, int dirty)
-{
-	if (!pte_same(*ptep, entry))
-		__set_pte_at(ptep, entry);
-	/*
-	 * update_mmu_cache will unconditionally execute, handling both
-	 * the case that the PTE changed and the spurious fault case.
-	 */
-	return true;
-}
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS	/* defined in mm/pgtable.c */
+extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+				 pte_t *ptep, pte_t entry, int dirty);
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG	/* defined in mm/pgtable.c */
+extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address,
+				     pte_t *ptep);
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
@@ -569,16 +562,6 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 	return pte;
 }
 
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long address,
-					    pte_t *ptep)
-{
-	if (!pte_young(*ptep))
-		return 0;
-	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
-}
-
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm,
 				      unsigned long address, pte_t *ptep)

arch/riscv/include/asm/sections.h

@@ -13,6 +13,7 @@ extern char _start_kernel[];
 extern char __init_data_begin[], __init_data_end[];
 extern char __init_text_begin[], __init_text_end[];
 extern char __alt_start[], __alt_end[];
+extern char __exittext_begin[], __exittext_end[];
 
 static inline bool is_va_kernel_text(uintptr_t va)
 {

arch/riscv/include/asm/thread_info.h

@@ -28,7 +28,6 @@
 
 #define THREAD_SHIFT            (PAGE_SHIFT + THREAD_SIZE_ORDER)
 #define OVERFLOW_STACK_SIZE     SZ_4K
-#define SHADOW_OVERFLOW_STACK_SIZE (1024)
 
 #define IRQ_STACK_SIZE		THREAD_SIZE
 

arch/riscv/include/asm/xip_fixup.h

@@ -13,7 +13,7 @@
         add \reg, \reg, t0
 .endm
 .macro XIP_FIXUP_FLASH_OFFSET reg
-	la t1, __data_loc
+	la t0, __data_loc
 	REG_L t1, _xip_phys_offset
 	sub \reg, \reg, t1
 	add \reg, \reg, t0

arch/riscv/include/uapi/asm/hwprobe.h

@@ -30,6 +30,35 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZBB		(1 << 4)
 #define		RISCV_HWPROBE_EXT_ZBS		(1 << 5)
 #define		RISCV_HWPROBE_EXT_ZICBOZ	(1 << 6)
+#define		RISCV_HWPROBE_EXT_ZBC		(1 << 7)
+#define		RISCV_HWPROBE_EXT_ZBKB		(1 << 8)
+#define		RISCV_HWPROBE_EXT_ZBKC		(1 << 9)
+#define		RISCV_HWPROBE_EXT_ZBKX		(1 << 10)
+#define		RISCV_HWPROBE_EXT_ZKND		(1 << 11)
+#define		RISCV_HWPROBE_EXT_ZKNE		(1 << 12)
+#define		RISCV_HWPROBE_EXT_ZKNH		(1 << 13)
+#define		RISCV_HWPROBE_EXT_ZKSED		(1 << 14)
+#define		RISCV_HWPROBE_EXT_ZKSH		(1 << 15)
+#define		RISCV_HWPROBE_EXT_ZKT		(1 << 16)
+#define		RISCV_HWPROBE_EXT_ZVBB		(1 << 17)
+#define		RISCV_HWPROBE_EXT_ZVBC		(1 << 18)
+#define		RISCV_HWPROBE_EXT_ZVKB		(1 << 19)
+#define		RISCV_HWPROBE_EXT_ZVKG		(1 << 20)
+#define		RISCV_HWPROBE_EXT_ZVKNED	(1 << 21)
+#define		RISCV_HWPROBE_EXT_ZVKNHA	(1 << 22)
+#define		RISCV_HWPROBE_EXT_ZVKNHB	(1 << 23)
+#define		RISCV_HWPROBE_EXT_ZVKSED	(1 << 24)
+#define		RISCV_HWPROBE_EXT_ZVKSH		(1 << 25)
+#define		RISCV_HWPROBE_EXT_ZVKT		(1 << 26)
+#define		RISCV_HWPROBE_EXT_ZFH		(1 << 27)
+#define		RISCV_HWPROBE_EXT_ZFHMIN	(1 << 28)
+#define		RISCV_HWPROBE_EXT_ZIHINTNTL	(1 << 29)
+#define		RISCV_HWPROBE_EXT_ZVFH		(1 << 30)
+#define		RISCV_HWPROBE_EXT_ZVFHMIN	(1 << 31)
+#define		RISCV_HWPROBE_EXT_ZFA		(1ULL << 32)
+#define		RISCV_HWPROBE_EXT_ZTSO		(1ULL << 33)
+#define		RISCV_HWPROBE_EXT_ZACAS		(1ULL << 34)
+#define		RISCV_HWPROBE_EXT_ZICOND	(1ULL << 35)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
@@ -40,4 +69,7 @@ struct riscv_hwprobe {
 #define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE	6
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
+/* Flags */
+#define RISCV_HWPROBE_WHICH_CPUS	(1 << 0)
+
 #endif

arch/riscv/kernel/Makefile

@@ -50,6 +50,7 @@ obj-y	+= setup.o
 obj-y	+= signal.o
 obj-y	+= syscall_table.o
 obj-y	+= sys_riscv.o
+obj-y	+= sys_hwprobe.o
 obj-y	+= time.o
 obj-y	+= traps.o
 obj-y	+= riscv_ksyms.o

arch/riscv/kernel/cpu-hotplug.c

@@ -18,7 +18,7 @@
 
 bool cpu_has_hotplug(unsigned int cpu)
 {
-	if (cpu_ops[cpu]->cpu_stop)
+	if (cpu_ops->cpu_stop)
 		return true;
 
 	return false;
@@ -29,25 +29,18 @@ bool cpu_has_hotplug(unsigned int cpu)
  */
 int __cpu_disable(void)
 {
-	int ret = 0;
 	unsigned int cpu = smp_processor_id();
 
-	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_stop)
+	if (!cpu_ops->cpu_stop)
 		return -EOPNOTSUPP;
 
-	if (cpu_ops[cpu]->cpu_disable)
-		ret = cpu_ops[cpu]->cpu_disable(cpu);
-
-	if (ret)
-		return ret;
-
 	remove_cpu_topology(cpu);
 	numa_remove_cpu(cpu);
 	set_cpu_online(cpu, false);
 	riscv_ipi_disable();
 	irq_migrate_all_off_this_cpu();
 
-	return ret;
+	return 0;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -62,8 +55,8 @@ void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
 	pr_notice("CPU%u: off\n", cpu);
 
 	/* Verify from the firmware if the cpu is really stopped*/
-	if (cpu_ops[cpu]->cpu_is_stopped)
-		ret = cpu_ops[cpu]->cpu_is_stopped(cpu);
+	if (cpu_ops->cpu_is_stopped)
+		ret = cpu_ops->cpu_is_stopped(cpu);
 	if (ret)
 		pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
 }
@@ -77,7 +70,7 @@ void __noreturn arch_cpu_idle_dead(void)
 
 	cpuhp_ap_report_dead();
 
-	cpu_ops[smp_processor_id()]->cpu_stop();
+	cpu_ops->cpu_stop();
 	/* It should never reach here */
 	BUG();
 }

arch/riscv/kernel/cpu_ops.c

@@ -13,25 +13,21 @@
 #include <asm/sbi.h>
 #include <asm/smp.h>
 
-const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
+const struct cpu_operations *cpu_ops __ro_after_init = &cpu_ops_spinwait;
 
 extern const struct cpu_operations cpu_ops_sbi;
 #ifndef CONFIG_RISCV_BOOT_SPINWAIT
 const struct cpu_operations cpu_ops_spinwait = {
-	.name		= "",
-	.cpu_prepare	= NULL,
 	.cpu_start	= NULL,
 };
 #endif
 
-void __init cpu_set_ops(int cpuid)
+void __init cpu_set_ops(void)
 {
 #if IS_ENABLED(CONFIG_RISCV_SBI)
 	if (sbi_probe_extension(SBI_EXT_HSM)) {
-		if (!cpuid)
-			pr_info("SBI HSM extension detected\n");
-		cpu_ops[cpuid] = &cpu_ops_sbi;
-	} else
+		pr_info("SBI HSM extension detected\n");
+		cpu_ops = &cpu_ops_sbi;
+	}
 #endif
-		cpu_ops[cpuid] = &cpu_ops_spinwait;
 }

arch/riscv/kernel/cpu_ops_sbi.c

@@ -79,23 +79,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 	return sbi_hsm_hart_start(hartid, boot_addr, hsm_data);
 }
 
-static int sbi_cpu_prepare(unsigned int cpuid)
-{
-	if (!cpu_ops_sbi.cpu_start) {
-		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
-		return -ENODEV;
-	}
-	return 0;
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
-static int sbi_cpu_disable(unsigned int cpuid)
-{
-	if (!cpu_ops_sbi.cpu_stop)
-		return -EOPNOTSUPP;
-	return 0;
-}
-
 static void sbi_cpu_stop(void)
 {
 	int ret;
@@ -118,11 +102,8 @@ static int sbi_cpu_is_stopped(unsigned int cpuid)
 #endif
 
 const struct cpu_operations cpu_ops_sbi = {
-	.name		= "sbi",
-	.cpu_prepare	= sbi_cpu_prepare,
 	.cpu_start	= sbi_cpu_start,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable	= sbi_cpu_disable,
 	.cpu_stop	= sbi_cpu_stop,
 	.cpu_is_stopped	= sbi_cpu_is_stopped,
 #endif

arch/riscv/kernel/cpu_ops_spinwait.c

@@ -39,15 +39,6 @@ static void cpu_update_secondary_bootdata(unsigned int cpuid,
 	WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle);
 }
 
-static int spinwait_cpu_prepare(unsigned int cpuid)
-{
-	if (!cpu_ops_spinwait.cpu_start) {
-		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
-		return -ENODEV;
-	}
-	return 0;
-}
-
 static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 {
 	/*
@@ -64,7 +55,5 @@ static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 }
 
 const struct cpu_operations cpu_ops_spinwait = {
-	.name		= "spinwait",
-	.cpu_prepare	= spinwait_cpu_prepare,
 	.cpu_start	= spinwait_cpu_start,
 };

arch/riscv/kernel/cpufeature.c

@@ -70,7 +70,7 @@ EXPORT_SYMBOL_GPL(riscv_isa_extension_base);
  *
  * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
  */
-bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit)
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit)
 {
 	const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa;
 
@@ -102,17 +102,101 @@ static bool riscv_isa_extension_check(int id)
 			return false;
 		}
 		return true;
+	case RISCV_ISA_EXT_INVALID:
+		return false;
 	}
 
 	return true;
 }
 
-#define __RISCV_ISA_EXT_DATA(_name, _id) {	\
-	.name = #_name,				\
-	.property = #_name,			\
-	.id = _id,				\
+#define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size) {	\
+	.name = #_name,								\
+	.property = #_name,							\
+	.id = _id,								\
+	.subset_ext_ids = _subset_exts,						\
+	.subset_ext_size = _subset_exts_size					\
 }
 
+#define __RISCV_ISA_EXT_DATA(_name, _id) _RISCV_ISA_EXT_DATA(_name, _id, NULL, 0)
+
+/* Used to declare pure "lasso" extension (Zk for instance) */
+#define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \
+	_RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, ARRAY_SIZE(_bundled_exts))
+
+/* Used to declare extensions that are a superset of other extensions (Zvbb for instance) */
+#define __RISCV_ISA_EXT_SUPERSET(_name, _id, _sub_exts) \
+	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts))
+
+static const unsigned int riscv_zk_bundled_exts[] = {
+	RISCV_ISA_EXT_ZBKB,
+	RISCV_ISA_EXT_ZBKC,
+	RISCV_ISA_EXT_ZBKX,
+	RISCV_ISA_EXT_ZKND,
+	RISCV_ISA_EXT_ZKNE,
+	RISCV_ISA_EXT_ZKR,
+	RISCV_ISA_EXT_ZKT,
+};
+
+static const unsigned int riscv_zkn_bundled_exts[] = {
+	RISCV_ISA_EXT_ZBKB,
+	RISCV_ISA_EXT_ZBKC,
+	RISCV_ISA_EXT_ZBKX,
+	RISCV_ISA_EXT_ZKND,
+	RISCV_ISA_EXT_ZKNE,
+	RISCV_ISA_EXT_ZKNH,
+};
+
+static const unsigned int riscv_zks_bundled_exts[] = {
+	RISCV_ISA_EXT_ZBKB,
+	RISCV_ISA_EXT_ZBKC,
+	RISCV_ISA_EXT_ZKSED,
+	RISCV_ISA_EXT_ZKSH
+};
+
+#define RISCV_ISA_EXT_ZVKN	\
+	RISCV_ISA_EXT_ZVKNED,	\
+	RISCV_ISA_EXT_ZVKNHB,	\
+	RISCV_ISA_EXT_ZVKB,	\
+	RISCV_ISA_EXT_ZVKT
+
+static const unsigned int riscv_zvkn_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKN
+};
+
+static const unsigned int riscv_zvknc_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKN,
+	RISCV_ISA_EXT_ZVBC
+};
+
+static const unsigned int riscv_zvkng_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKN,
+	RISCV_ISA_EXT_ZVKG
+};
+
+#define RISCV_ISA_EXT_ZVKS	\
+	RISCV_ISA_EXT_ZVKSED,	\
+	RISCV_ISA_EXT_ZVKSH,	\
+	RISCV_ISA_EXT_ZVKB,	\
+	RISCV_ISA_EXT_ZVKT
+
+static const unsigned int riscv_zvks_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKS
+};
+
+static const unsigned int riscv_zvksc_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKS,
+	RISCV_ISA_EXT_ZVBC
+};
+
+static const unsigned int riscv_zvksg_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKS,
+	RISCV_ISA_EXT_ZVKG
+};
+
+static const unsigned int riscv_zvbb_exts[] = {
+	RISCV_ISA_EXT_ZVKB
+};
+
 /*
  * The canonical order of ISA extension names in the ISA string is defined in
  * chapter 27 of the unprivileged specification.
@@ -160,10 +244,6 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(d, RISCV_ISA_EXT_d),
 	__RISCV_ISA_EXT_DATA(q, RISCV_ISA_EXT_q),
 	__RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c),
-	__RISCV_ISA_EXT_DATA(b, RISCV_ISA_EXT_b),
-	__RISCV_ISA_EXT_DATA(k, RISCV_ISA_EXT_k),
-	__RISCV_ISA_EXT_DATA(j, RISCV_ISA_EXT_j),
-	__RISCV_ISA_EXT_DATA(p, RISCV_ISA_EXT_p),
 	__RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v),
 	__RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h),
 	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
@@ -172,11 +252,49 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND),
 	__RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),
 	__RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI),
+	__RISCV_ISA_EXT_DATA(zihintntl, RISCV_ISA_EXT_ZIHINTNTL),
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
 	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
+	__RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS),
+	__RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA),
+	__RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH),
+	__RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN),
 	__RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA),
 	__RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB),
+	__RISCV_ISA_EXT_DATA(zbc, RISCV_ISA_EXT_ZBC),
+	__RISCV_ISA_EXT_DATA(zbkb, RISCV_ISA_EXT_ZBKB),
+	__RISCV_ISA_EXT_DATA(zbkc, RISCV_ISA_EXT_ZBKC),
+	__RISCV_ISA_EXT_DATA(zbkx, RISCV_ISA_EXT_ZBKX),
 	__RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS),
+	__RISCV_ISA_EXT_BUNDLE(zk, riscv_zk_bundled_exts),
+	__RISCV_ISA_EXT_BUNDLE(zkn, riscv_zkn_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zknd, RISCV_ISA_EXT_ZKND),
+	__RISCV_ISA_EXT_DATA(zkne, RISCV_ISA_EXT_ZKNE),
+	__RISCV_ISA_EXT_DATA(zknh, RISCV_ISA_EXT_ZKNH),
+	__RISCV_ISA_EXT_DATA(zkr, RISCV_ISA_EXT_ZKR),
+	__RISCV_ISA_EXT_BUNDLE(zks, riscv_zks_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zkt, RISCV_ISA_EXT_ZKT),
+	__RISCV_ISA_EXT_DATA(zksed, RISCV_ISA_EXT_ZKSED),
+	__RISCV_ISA_EXT_DATA(zksh, RISCV_ISA_EXT_ZKSH),
+	__RISCV_ISA_EXT_DATA(ztso, RISCV_ISA_EXT_ZTSO),
+	__RISCV_ISA_EXT_SUPERSET(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts),
+	__RISCV_ISA_EXT_DATA(zvbc, RISCV_ISA_EXT_ZVBC),
+	__RISCV_ISA_EXT_DATA(zvfh, RISCV_ISA_EXT_ZVFH),
+	__RISCV_ISA_EXT_DATA(zvfhmin, RISCV_ISA_EXT_ZVFHMIN),
+	__RISCV_ISA_EXT_DATA(zvkb, RISCV_ISA_EXT_ZVKB),
+	__RISCV_ISA_EXT_DATA(zvkg, RISCV_ISA_EXT_ZVKG),
+	__RISCV_ISA_EXT_BUNDLE(zvkn, riscv_zvkn_bundled_exts),
+	__RISCV_ISA_EXT_BUNDLE(zvknc, riscv_zvknc_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvkned, RISCV_ISA_EXT_ZVKNED),
+	__RISCV_ISA_EXT_BUNDLE(zvkng, riscv_zvkng_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvknha, RISCV_ISA_EXT_ZVKNHA),
+	__RISCV_ISA_EXT_DATA(zvknhb, RISCV_ISA_EXT_ZVKNHB),
+	__RISCV_ISA_EXT_BUNDLE(zvks, riscv_zvks_bundled_exts),
+	__RISCV_ISA_EXT_BUNDLE(zvksc, riscv_zvksc_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvksed, RISCV_ISA_EXT_ZVKSED),
+	__RISCV_ISA_EXT_DATA(zvksh, RISCV_ISA_EXT_ZVKSH),
+	__RISCV_ISA_EXT_BUNDLE(zvksg, riscv_zvksg_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvkt, RISCV_ISA_EXT_ZVKT),
 	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
 	__RISCV_ISA_EXT_DATA(smstateen, RISCV_ISA_EXT_SMSTATEEN),
 	__RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
@@ -189,6 +307,31 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 
 const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext);
 
+static void __init match_isa_ext(const struct riscv_isa_ext_data *ext, const char *name,
+				 const char *name_end, struct riscv_isainfo *isainfo)
+{
+	if ((name_end - name == strlen(ext->name)) &&
+	     !strncasecmp(name, ext->name, name_end - name)) {
+		/*
+		 * If this is a bundle, enable all the ISA extensions that
+		 * comprise the bundle.
+		 */
+		if (ext->subset_ext_size) {
+			for (int i = 0; i < ext->subset_ext_size; i++) {
+				if (riscv_isa_extension_check(ext->subset_ext_ids[i]))
+					set_bit(ext->subset_ext_ids[i], isainfo->isa);
+			}
+		}
+
+		/*
+		 * This is valid even for bundle extensions which uses the RISCV_ISA_EXT_INVALID id
+		 * (rejected by riscv_isa_extension_check()).
+		 */
+		if (riscv_isa_extension_check(ext->id))
+			set_bit(ext->id, isainfo->isa);
+	}
+}
+
 static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct riscv_isainfo *isainfo,
 					  unsigned long *isa2hwcap, const char *isa)
 {
@@ -321,14 +464,6 @@ static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct risc
 		if (*isa == '_')
 			++isa;
 
-#define SET_ISA_EXT_MAP(name, bit)						\
-		do {								\
-			if ((ext_end - ext == strlen(name)) &&			\
-			     !strncasecmp(ext, name, strlen(name)) &&		\
-			     riscv_isa_extension_check(bit))			\
-				set_bit(bit, isainfo->isa);			\
-		} while (false)							\
-
 		if (unlikely(ext_err))
 			continue;
 		if (!ext_long) {
@@ -340,10 +475,8 @@ static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct risc
 			}
 		} else {
 			for (int i = 0; i < riscv_isa_ext_count; i++)
-				SET_ISA_EXT_MAP(riscv_isa_ext[i].name,
-						riscv_isa_ext[i].id);
+				match_isa_ext(&riscv_isa_ext[i], ext, ext_end, isainfo);
 		}
-#undef SET_ISA_EXT_MAP
 	}
 }
 
@@ -442,18 +575,26 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
 		}
 
 		for (int i = 0; i < riscv_isa_ext_count; i++) {
+			const struct riscv_isa_ext_data *ext = &riscv_isa_ext[i];
+
 			if (of_property_match_string(cpu_node, "riscv,isa-extensions",
-						     riscv_isa_ext[i].property) < 0)
+						     ext->property) < 0)
 				continue;
 
-			if (!riscv_isa_extension_check(riscv_isa_ext[i].id))
-				continue;
+			if (ext->subset_ext_size) {
+				for (int j = 0; j < ext->subset_ext_size; j++) {
+					if (riscv_isa_extension_check(ext->subset_ext_ids[i]))
+						set_bit(ext->subset_ext_ids[j], isainfo->isa);
+				}
+			}
 
-			/* Only single letter extensions get set in hwcap */
-			if (strnlen(riscv_isa_ext[i].name, 2) == 1)
-				this_hwcap |= isa2hwcap[riscv_isa_ext[i].id];
+			if (riscv_isa_extension_check(ext->id)) {
+				set_bit(ext->id, isainfo->isa);
 
-			set_bit(riscv_isa_ext[i].id, isainfo->isa);
+				/* Only single letter extensions get set in hwcap */
+				if (strnlen(riscv_isa_ext[i].name, 2) == 1)
+					this_hwcap |= isa2hwcap[riscv_isa_ext[i].id];
+			}
 		}
 
 		of_node_put(cpu_node);

arch/riscv/kernel/efi.c

@@ -60,7 +60,7 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
 {
 	efi_memory_desc_t *md = data;
-	pte_t pte = READ_ONCE(*ptep);
+	pte_t pte = ptep_get(ptep);
 	unsigned long val;
 
 	if (md->attribute & EFI_MEMORY_RO) {

arch/riscv/kernel/head.S

@@ -11,7 +11,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/csr.h>
-#include <asm/cpu_ops_sbi.h>
 #include <asm/hwcap.h>
 #include <asm/image.h>
 #include <asm/scs.h>
@@ -89,6 +88,7 @@ relocate_enable_mmu:
 	/* Compute satp for kernel page tables, but don't load it yet */
 	srl a2, a0, PAGE_SHIFT
 	la a1, satp_mode
+	XIP_FIXUP_OFFSET a1
 	REG_L a1, 0(a1)
 	or a2, a2, a1
 
@@ -265,10 +265,12 @@ SYM_CODE_START(_start_kernel)
 	la sp, _end + THREAD_SIZE
 	XIP_FIXUP_OFFSET sp
 	mv s0, a0
+	mv s1, a1
 	call __copy_data
 
-	/* Restore a0 copy */
+	/* Restore a0 & a1 copy */
 	mv a0, s0
+	mv a1, s1
 #endif
 
 #ifndef CONFIG_XIP_KERNEL

arch/riscv/kernel/mcount-dyn.S

@@ -3,12 +3,12 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/csr.h>
 #include <asm/unistd.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
-#include <asm-generic/export.h>
 #include <asm/ftrace.h>
 
 	.text

arch/riscv/kernel/mcount.S

@@ -4,12 +4,12 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/cfi_types.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/csr.h>
 #include <asm/unistd.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
-#include <asm-generic/export.h>
 #include <asm/ftrace.h>
 
 	.text

arch/riscv/kernel/module.c

@@ -894,7 +894,8 @@ void *module_alloc(unsigned long size)
 {
 	return __vmalloc_node_range(size, 1, MODULES_VADDR,
 				    MODULES_END, GFP_KERNEL,
-				    PAGE_KERNEL, 0, NUMA_NO_NODE,
+				    PAGE_KERNEL, VM_FLUSH_RESET_PERMS,
+				    NUMA_NO_NODE,
 				    __builtin_return_address(0));
 }
 #endif

arch/riscv/kernel/patch.c

@@ -14,6 +14,7 @@
 #include <asm/fixmap.h>
 #include <asm/ftrace.h>
 #include <asm/patch.h>
+#include <asm/sections.h>
 
 struct patch_insn {
 	void *addr;
@@ -25,6 +26,14 @@ struct patch_insn {
 int riscv_patch_in_stop_machine = false;
 
 #ifdef CONFIG_MMU
+
+static inline bool is_kernel_exittext(uintptr_t addr)
+{
+	return system_state < SYSTEM_RUNNING &&
+		addr >= (uintptr_t)__exittext_begin &&
+		addr < (uintptr_t)__exittext_end;
+}
+
 /*
  * The fix_to_virt(, idx) needs a const value (not a dynamic variable of
  * reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses".
@@ -35,7 +44,7 @@ static __always_inline void *patch_map(void *addr, const unsigned int fixmap)
 	uintptr_t uintaddr = (uintptr_t) addr;
 	struct page *page;
 
-	if (core_kernel_text(uintaddr))
+	if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr))
 		page = phys_to_page(__pa_symbol(addr));
 	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
 		page = vmalloc_to_page(addr);

arch/riscv/kernel/setup.c

@@ -26,7 +26,6 @@
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
-#include <asm/cpu_ops.h>
 #include <asm/early_ioremap.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>

arch/riscv/kernel/signal.c

@@ -91,7 +91,7 @@ static long save_v_state(struct pt_regs *regs, void __user **sc_vec)
 	err = __copy_to_user(&state->v_state, &current->thread.vstate,
 			     offsetof(struct __riscv_v_ext_state, datap));
 	/* Copy the pointer datap itself. */
-	err |= __put_user(datap, &state->v_state.datap);
+	err |= __put_user((__force void *)datap, &state->v_state.datap);
 	/* Copy the whole vector content to user space datap. */
 	err |= __copy_to_user(datap, current->thread.vstate.datap, riscv_v_vsize);
 	/* Copy magic to the user space after saving  all vector conetext */

arch/riscv/kernel/smp.c

@@ -81,7 +81,7 @@ static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
 
 #ifdef CONFIG_HOTPLUG_CPU
 	if (cpu_has_hotplug(cpu))
-		cpu_ops[cpu]->cpu_stop();
+		cpu_ops->cpu_stop();
 #endif
 
 	for(;;)

arch/riscv/kernel/smpboot.c

@@ -49,7 +49,6 @@ void __init smp_prepare_boot_cpu(void)
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	int cpuid;
-	int ret;
 	unsigned int curr_cpuid;
 
 	init_cpu_topology();
@@ -66,11 +65,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	for_each_possible_cpu(cpuid) {
 		if (cpuid == curr_cpuid)
 			continue;
-		if (cpu_ops[cpuid]->cpu_prepare) {
-			ret = cpu_ops[cpuid]->cpu_prepare(cpuid);
-			if (ret)
-				continue;
-		}
 		set_cpu_present(cpuid, true);
 		numa_store_cpu_info(cpuid);
 	}
@@ -125,18 +119,7 @@ static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const un
 
 static void __init acpi_parse_and_init_cpus(void)
 {
-	int cpuid;
-
-	cpu_set_ops(0);
-
 	acpi_table_parse_madt(ACPI_MADT_TYPE_RINTC, acpi_parse_rintc, 0);
-
-	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
-		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
-			cpu_set_ops(cpuid);
-			set_cpu_possible(cpuid, true);
-		}
-	}
 }
 #else
 #define acpi_parse_and_init_cpus(...)	do { } while (0)
@@ -150,8 +133,6 @@ static void __init of_parse_and_init_cpus(void)
 	int cpuid = 1;
 	int rc;
 
-	cpu_set_ops(0);
-
 	for_each_of_cpu_node(dn) {
 		rc = riscv_early_of_processor_hartid(dn, &hart);
 		if (rc < 0)
@@ -179,27 +160,28 @@ static void __init of_parse_and_init_cpus(void)
 	if (cpuid > nr_cpu_ids)
 		pr_warn("Total number of cpus [%d] is greater than nr_cpus option value [%d]\n",
 			cpuid, nr_cpu_ids);
-
-	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
-		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
-			cpu_set_ops(cpuid);
-			set_cpu_possible(cpuid, true);
-		}
-	}
 }
 
 void __init setup_smp(void)
 {
+	int cpuid;
+
+	cpu_set_ops();
+
 	if (acpi_disabled)
 		of_parse_and_init_cpus();
 	else
 		acpi_parse_and_init_cpus();
+
+	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++)
+		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID)
+			set_cpu_possible(cpuid, true);
 }
 
 static int start_secondary_cpu(int cpu, struct task_struct *tidle)
 {
-	if (cpu_ops[cpu]->cpu_start)
-		return cpu_ops[cpu]->cpu_start(cpu, tidle);
+	if (cpu_ops->cpu_start)
+		return cpu_ops->cpu_start(cpu, tidle);
 
 	return -EOPNOTSUPP;
 }

arch/riscv/kernel/sys_hwprobe.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * The hwprobe interface, for allowing userspace to probe to see which features
+ * are supported by the hardware.  See Documentation/arch/riscv/hwprobe.rst for
+ * more details.
+ */
+#include <linux/syscalls.h>
+#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
+#include <asm/hwprobe.h>
+#include <asm/sbi.h>
+#include <asm/switch_to.h>
+#include <asm/uaccess.h>
+#include <asm/unistd.h>
+#include <asm/vector.h>
+#include <vdso/vsyscall.h>
+
+
+static void hwprobe_arch_id(struct riscv_hwprobe *pair,
+			    const struct cpumask *cpus)
+{
+	u64 id = -1ULL;
+	bool first = true;
+	int cpu;
+
+	for_each_cpu(cpu, cpus) {
+		u64 cpu_id;
+
+		switch (pair->key) {
+		case RISCV_HWPROBE_KEY_MVENDORID:
+			cpu_id = riscv_cached_mvendorid(cpu);
+			break;
+		case RISCV_HWPROBE_KEY_MIMPID:
+			cpu_id = riscv_cached_mimpid(cpu);
+			break;
+		case RISCV_HWPROBE_KEY_MARCHID:
+			cpu_id = riscv_cached_marchid(cpu);
+			break;
+		}
+
+		if (first) {
+			id = cpu_id;
+			first = false;
+		}
+
+		/*
+		 * If there's a mismatch for the given set, return -1 in the
+		 * value.
+		 */
+		if (id != cpu_id) {
+			id = -1ULL;
+			break;
+		}
+	}
+
+	pair->value = id;
+}
+
+static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
+			     const struct cpumask *cpus)
+{
+	int cpu;
+	u64 missing = 0;
+
+	pair->value = 0;
+	if (has_fpu())
+		pair->value |= RISCV_HWPROBE_IMA_FD;
+
+	if (riscv_isa_extension_available(NULL, c))
+		pair->value |= RISCV_HWPROBE_IMA_C;
+
+	if (has_vector())
+		pair->value |= RISCV_HWPROBE_IMA_V;
+
+	/*
+	 * Loop through and record extensions that 1) anyone has, and 2) anyone
+	 * doesn't have.
+	 */
+	for_each_cpu(cpu, cpus) {
+		struct riscv_isainfo *isainfo = &hart_isa[cpu];
+
+#define EXT_KEY(ext)									\
+	do {										\
+		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext))	\
+			pair->value |= RISCV_HWPROBE_EXT_##ext;				\
+		else									\
+			missing |= RISCV_HWPROBE_EXT_##ext;				\
+	} while (false)
+
+		/*
+		 * Only use EXT_KEY() for extensions which can be exposed to userspace,
+		 * regardless of the kernel's configuration, as no other checks, besides
+		 * presence in the hart_isa bitmap, are made.
+		 */
+		EXT_KEY(ZBA);
+		EXT_KEY(ZBB);
+		EXT_KEY(ZBS);
+		EXT_KEY(ZICBOZ);
+		EXT_KEY(ZBC);
+
+		EXT_KEY(ZBKB);
+		EXT_KEY(ZBKC);
+		EXT_KEY(ZBKX);
+		EXT_KEY(ZKND);
+		EXT_KEY(ZKNE);
+		EXT_KEY(ZKNH);
+		EXT_KEY(ZKSED);
+		EXT_KEY(ZKSH);
+		EXT_KEY(ZKT);
+		EXT_KEY(ZIHINTNTL);
+		EXT_KEY(ZTSO);
+		EXT_KEY(ZACAS);
+		EXT_KEY(ZICOND);
+
+		if (has_vector()) {
+			EXT_KEY(ZVBB);
+			EXT_KEY(ZVBC);
+			EXT_KEY(ZVKB);
+			EXT_KEY(ZVKG);
+			EXT_KEY(ZVKNED);
+			EXT_KEY(ZVKNHA);
+			EXT_KEY(ZVKNHB);
+			EXT_KEY(ZVKSED);
+			EXT_KEY(ZVKSH);
+			EXT_KEY(ZVKT);
+			EXT_KEY(ZVFH);
+			EXT_KEY(ZVFHMIN);
+		}
+
+		if (has_fpu()) {
+			EXT_KEY(ZFH);
+			EXT_KEY(ZFHMIN);
+			EXT_KEY(ZFA);
+		}
+#undef EXT_KEY
+	}
+
+	/* Now turn off reporting features if any CPU is missing it. */
+	pair->value &= ~missing;
+}
+
+static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
+{
+	struct riscv_hwprobe pair;
+
+	hwprobe_isa_ext0(&pair, cpus);
+	return (pair.value & ext);
+}
+
+static u64 hwprobe_misaligned(const struct cpumask *cpus)
+{
+	int cpu;
+	u64 perf = -1ULL;
+
+	for_each_cpu(cpu, cpus) {
+		int this_perf = per_cpu(misaligned_access_speed, cpu);
+
+		if (perf == -1ULL)
+			perf = this_perf;
+
+		if (perf != this_perf) {
+			perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+			break;
+		}
+	}
+
+	if (perf == -1ULL)
+		return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+
+	return perf;
+}
+
+static void hwprobe_one_pair(struct riscv_hwprobe *pair,
+			     const struct cpumask *cpus)
+{
+	switch (pair->key) {
+	case RISCV_HWPROBE_KEY_MVENDORID:
+	case RISCV_HWPROBE_KEY_MARCHID:
+	case RISCV_HWPROBE_KEY_MIMPID:
+		hwprobe_arch_id(pair, cpus);
+		break;
+	/*
+	 * The kernel already assumes that the base single-letter ISA
+	 * extensions are supported on all harts, and only supports the
+	 * IMA base, so just cheat a bit here and tell that to
+	 * userspace.
+	 */
+	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
+		pair->value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA;
+		break;
+
+	case RISCV_HWPROBE_KEY_IMA_EXT_0:
+		hwprobe_isa_ext0(pair, cpus);
+		break;
+
+	case RISCV_HWPROBE_KEY_CPUPERF_0:
+		pair->value = hwprobe_misaligned(cpus);
+		break;
+
+	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
+		pair->value = 0;
+		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
+			pair->value = riscv_cboz_block_size;
+		break;
+
+	/*
+	 * For forward compatibility, unknown keys don't fail the whole
+	 * call, but get their element key set to -1 and value set to 0
+	 * indicating they're unrecognized.
+	 */
+	default:
+		pair->key = -1;
+		pair->value = 0;
+		break;
+	}
+}
+
+static int hwprobe_get_values(struct riscv_hwprobe __user *pairs,
+			      size_t pair_count, size_t cpusetsize,
+			      unsigned long __user *cpus_user,
+			      unsigned int flags)
+{
+	size_t out;
+	int ret;
+	cpumask_t cpus;
+
+	/* Check the reserved flags. */
+	if (flags != 0)
+		return -EINVAL;
+
+	/*
+	 * The interface supports taking in a CPU mask, and returns values that
+	 * are consistent across that mask. Allow userspace to specify NULL and
+	 * 0 as a shortcut to all online CPUs.
+	 */
+	cpumask_clear(&cpus);
+	if (!cpusetsize && !cpus_user) {
+		cpumask_copy(&cpus, cpu_online_mask);
+	} else {
+		if (cpusetsize > cpumask_size())
+			cpusetsize = cpumask_size();
+
+		ret = copy_from_user(&cpus, cpus_user, cpusetsize);
+		if (ret)
+			return -EFAULT;
+
+		/*
+		 * Userspace must provide at least one online CPU, without that
+		 * there's no way to define what is supported.
+		 */
+		cpumask_and(&cpus, &cpus, cpu_online_mask);
+		if (cpumask_empty(&cpus))
+			return -EINVAL;
+	}
+
+	for (out = 0; out < pair_count; out++, pairs++) {
+		struct riscv_hwprobe pair;
+
+		if (get_user(pair.key, &pairs->key))
+			return -EFAULT;
+
+		pair.value = 0;
+		hwprobe_one_pair(&pair, &cpus);
+		ret = put_user(pair.key, &pairs->key);
+		if (ret == 0)
+			ret = put_user(pair.value, &pairs->value);
+
+		if (ret)
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int hwprobe_get_cpus(struct riscv_hwprobe __user *pairs,
+			    size_t pair_count, size_t cpusetsize,
+			    unsigned long __user *cpus_user,
+			    unsigned int flags)
+{
+	cpumask_t cpus, one_cpu;
+	bool clear_all = false;
+	size_t i;
+	int ret;
+
+	if (flags != RISCV_HWPROBE_WHICH_CPUS)
+		return -EINVAL;
+
+	if (!cpusetsize || !cpus_user)
+		return -EINVAL;
+
+	if (cpusetsize > cpumask_size())
+		cpusetsize = cpumask_size();
+
+	ret = copy_from_user(&cpus, cpus_user, cpusetsize);
+	if (ret)
+		return -EFAULT;
+
+	if (cpumask_empty(&cpus))
+		cpumask_copy(&cpus, cpu_online_mask);
+
+	cpumask_and(&cpus, &cpus, cpu_online_mask);
+
+	cpumask_clear(&one_cpu);
+
+	for (i = 0; i < pair_count; i++) {
+		struct riscv_hwprobe pair, tmp;
+		int cpu;
+
+		ret = copy_from_user(&pair, &pairs[i], sizeof(pair));
+		if (ret)
+			return -EFAULT;
+
+		if (!riscv_hwprobe_key_is_valid(pair.key)) {
+			clear_all = true;
+			pair = (struct riscv_hwprobe){ .key = -1, };
+			ret = copy_to_user(&pairs[i], &pair, sizeof(pair));
+			if (ret)
+				return -EFAULT;
+		}
+
+		if (clear_all)
+			continue;
+
+		tmp = (struct riscv_hwprobe){ .key = pair.key, };
+
+		for_each_cpu(cpu, &cpus) {
+			cpumask_set_cpu(cpu, &one_cpu);
+
+			hwprobe_one_pair(&tmp, &one_cpu);
+
+			if (!riscv_hwprobe_pair_cmp(&tmp, &pair))
+				cpumask_clear_cpu(cpu, &cpus);
+
+			cpumask_clear_cpu(cpu, &one_cpu);
+		}
+	}
+
+	if (clear_all)
+		cpumask_clear(&cpus);
+
+	ret = copy_to_user(cpus_user, &cpus, cpusetsize);
+	if (ret)
+		return -EFAULT;
+
+	return 0;
+}
+
+static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
+			    size_t pair_count, size_t cpusetsize,
+			    unsigned long __user *cpus_user,
+			    unsigned int flags)
+{
+	if (flags & RISCV_HWPROBE_WHICH_CPUS)
+		return hwprobe_get_cpus(pairs, pair_count, cpusetsize,
+					cpus_user, flags);
+
+	return hwprobe_get_values(pairs, pair_count, cpusetsize,
+				  cpus_user, flags);
+}
+
+#ifdef CONFIG_MMU
+
+static int __init init_hwprobe_vdso_data(void)
+{
+	struct vdso_data *vd = __arch_get_k_vdso_data();
+	struct arch_vdso_data *avd = &vd->arch_data;
+	u64 id_bitsmash = 0;
+	struct riscv_hwprobe pair;
+	int key;
+
+	/*
+	 * Initialize vDSO data with the answers for the "all CPUs" case, to
+	 * save a syscall in the common case.
+	 */
+	for (key = 0; key <= RISCV_HWPROBE_MAX_KEY; key++) {
+		pair.key = key;
+		hwprobe_one_pair(&pair, cpu_online_mask);
+
+		WARN_ON_ONCE(pair.key < 0);
+
+		avd->all_cpu_hwprobe_values[key] = pair.value;
+		/*
+		 * Smash together the vendor, arch, and impl IDs to see if
+		 * they're all 0 or any negative.
+		 */
+		if (key <= RISCV_HWPROBE_KEY_MIMPID)
+			id_bitsmash |= pair.value;
+	}
+
+	/*
+	 * If the arch, vendor, and implementation ID are all the same across
+	 * all harts, then assume all CPUs are the same, and allow the vDSO to
+	 * answer queries for arbitrary masks. However if all values are 0 (not
+	 * populated) or any value returns -1 (varies across CPUs), then the
+	 * vDSO should defer to the kernel for exotic cpu masks.
+	 */
+	avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1;
+	return 0;
+}
+
+arch_initcall_sync(init_hwprobe_vdso_data);
+
+#endif /* CONFIG_MMU */
+
+SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
+		size_t, pair_count, size_t, cpusetsize, unsigned long __user *,
+		cpus, unsigned int, flags)
+{
+	return do_riscv_hwprobe(pairs, pair_count, cpusetsize,
+				cpus, flags);
+}

arch/riscv/kernel/sys_riscv.c

@@ -7,15 +7,7 @@
 
 #include <linux/syscalls.h>
 #include <asm/cacheflush.h>
-#include <asm/cpufeature.h>
-#include <asm/hwprobe.h>
-#include <asm/sbi.h>
-#include <asm/vector.h>
-#include <asm/switch_to.h>
-#include <asm/uaccess.h>
-#include <asm/unistd.h>
 #include <asm-generic/mman-common.h>
-#include <vdso/vsyscall.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 			   unsigned long prot, unsigned long flags,
@@ -77,283 +69,6 @@ SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
 	return 0;
 }
 
-/*
- * The hwprobe interface, for allowing userspace to probe to see which features
- * are supported by the hardware.  See Documentation/arch/riscv/hwprobe.rst for more
- * details.
- */
-static void hwprobe_arch_id(struct riscv_hwprobe *pair,
-			    const struct cpumask *cpus)
-{
-	u64 id = -1ULL;
-	bool first = true;
-	int cpu;
-
-	for_each_cpu(cpu, cpus) {
-		u64 cpu_id;
-
-		switch (pair->key) {
-		case RISCV_HWPROBE_KEY_MVENDORID:
-			cpu_id = riscv_cached_mvendorid(cpu);
-			break;
-		case RISCV_HWPROBE_KEY_MIMPID:
-			cpu_id = riscv_cached_mimpid(cpu);
-			break;
-		case RISCV_HWPROBE_KEY_MARCHID:
-			cpu_id = riscv_cached_marchid(cpu);
-			break;
-		}
-
-		if (first) {
-			id = cpu_id;
-			first = false;
-		}
-
-		/*
-		 * If there's a mismatch for the given set, return -1 in the
-		 * value.
-		 */
-		if (id != cpu_id) {
-			id = -1ULL;
-			break;
-		}
-	}
-
-	pair->value = id;
-}
-
-static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
-			     const struct cpumask *cpus)
-{
-	int cpu;
-	u64 missing = 0;
-
-	pair->value = 0;
-	if (has_fpu())
-		pair->value |= RISCV_HWPROBE_IMA_FD;
-
-	if (riscv_isa_extension_available(NULL, c))
-		pair->value |= RISCV_HWPROBE_IMA_C;
-
-	if (has_vector())
-		pair->value |= RISCV_HWPROBE_IMA_V;
-
-	/*
-	 * Loop through and record extensions that 1) anyone has, and 2) anyone
-	 * doesn't have.
-	 */
-	for_each_cpu(cpu, cpus) {
-		struct riscv_isainfo *isainfo = &hart_isa[cpu];
-
-#define EXT_KEY(ext)									\
-	do {										\
-		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext))	\
-			pair->value |= RISCV_HWPROBE_EXT_##ext;				\
-		else									\
-			missing |= RISCV_HWPROBE_EXT_##ext;				\
-	} while (false)
-
-		/*
-		 * Only use EXT_KEY() for extensions which can be exposed to userspace,
-		 * regardless of the kernel's configuration, as no other checks, besides
-		 * presence in the hart_isa bitmap, are made.
-		 */
-		EXT_KEY(ZBA);
-		EXT_KEY(ZBB);
-		EXT_KEY(ZBS);
-		EXT_KEY(ZICBOZ);
-#undef EXT_KEY
-	}
-
-	/* Now turn off reporting features if any CPU is missing it. */
-	pair->value &= ~missing;
-}
-
-static bool hwprobe_ext0_has(const struct cpumask *cpus, u64 ext)
-{
-	struct riscv_hwprobe pair;
-
-	hwprobe_isa_ext0(&pair, cpus);
-	return (pair.value & ext);
-}
-
-static u64 hwprobe_misaligned(const struct cpumask *cpus)
-{
-	int cpu;
-	u64 perf = -1ULL;
-
-	for_each_cpu(cpu, cpus) {
-		int this_perf = per_cpu(misaligned_access_speed, cpu);
-
-		if (perf == -1ULL)
-			perf = this_perf;
-
-		if (perf != this_perf) {
-			perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
-			break;
-		}
-	}
-
-	if (perf == -1ULL)
-		return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
-
-	return perf;
-}
-
-static void hwprobe_one_pair(struct riscv_hwprobe *pair,
-			     const struct cpumask *cpus)
-{
-	switch (pair->key) {
-	case RISCV_HWPROBE_KEY_MVENDORID:
-	case RISCV_HWPROBE_KEY_MARCHID:
-	case RISCV_HWPROBE_KEY_MIMPID:
-		hwprobe_arch_id(pair, cpus);
-		break;
-	/*
-	 * The kernel already assumes that the base single-letter ISA
-	 * extensions are supported on all harts, and only supports the
-	 * IMA base, so just cheat a bit here and tell that to
-	 * userspace.
-	 */
-	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
-		pair->value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA;
-		break;
-
-	case RISCV_HWPROBE_KEY_IMA_EXT_0:
-		hwprobe_isa_ext0(pair, cpus);
-		break;
-
-	case RISCV_HWPROBE_KEY_CPUPERF_0:
-		pair->value = hwprobe_misaligned(cpus);
-		break;
-
-	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
-		pair->value = 0;
-		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
-			pair->value = riscv_cboz_block_size;
-		break;
-
-	/*
-	 * For forward compatibility, unknown keys don't fail the whole
-	 * call, but get their element key set to -1 and value set to 0
-	 * indicating they're unrecognized.
-	 */
-	default:
-		pair->key = -1;
-		pair->value = 0;
-		break;
-	}
-}
-
-static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
-			    size_t pair_count, size_t cpu_count,
-			    unsigned long __user *cpus_user,
-			    unsigned int flags)
-{
-	size_t out;
-	int ret;
-	cpumask_t cpus;
-
-	/* Check the reserved flags. */
-	if (flags != 0)
-		return -EINVAL;
-
-	/*
-	 * The interface supports taking in a CPU mask, and returns values that
-	 * are consistent across that mask. Allow userspace to specify NULL and
-	 * 0 as a shortcut to all online CPUs.
-	 */
-	cpumask_clear(&cpus);
-	if (!cpu_count && !cpus_user) {
-		cpumask_copy(&cpus, cpu_online_mask);
-	} else {
-		if (cpu_count > cpumask_size())
-			cpu_count = cpumask_size();
-
-		ret = copy_from_user(&cpus, cpus_user, cpu_count);
-		if (ret)
-			return -EFAULT;
-
-		/*
-		 * Userspace must provide at least one online CPU, without that
-		 * there's no way to define what is supported.
-		 */
-		cpumask_and(&cpus, &cpus, cpu_online_mask);
-		if (cpumask_empty(&cpus))
-			return -EINVAL;
-	}
-
-	for (out = 0; out < pair_count; out++, pairs++) {
-		struct riscv_hwprobe pair;
-
-		if (get_user(pair.key, &pairs->key))
-			return -EFAULT;
-
-		pair.value = 0;
-		hwprobe_one_pair(&pair, &cpus);
-		ret = put_user(pair.key, &pairs->key);
-		if (ret == 0)
-			ret = put_user(pair.value, &pairs->value);
-
-		if (ret)
-			return -EFAULT;
-	}
-
-	return 0;
-}
-
-#ifdef CONFIG_MMU
-
-static int __init init_hwprobe_vdso_data(void)
-{
-	struct vdso_data *vd = __arch_get_k_vdso_data();
-	struct arch_vdso_data *avd = &vd->arch_data;
-	u64 id_bitsmash = 0;
-	struct riscv_hwprobe pair;
-	int key;
-
-	/*
-	 * Initialize vDSO data with the answers for the "all CPUs" case, to
-	 * save a syscall in the common case.
-	 */
-	for (key = 0; key <= RISCV_HWPROBE_MAX_KEY; key++) {
-		pair.key = key;
-		hwprobe_one_pair(&pair, cpu_online_mask);
-
-		WARN_ON_ONCE(pair.key < 0);
-
-		avd->all_cpu_hwprobe_values[key] = pair.value;
-		/*
-		 * Smash together the vendor, arch, and impl IDs to see if
-		 * they're all 0 or any negative.
-		 */
-		if (key <= RISCV_HWPROBE_KEY_MIMPID)
-			id_bitsmash |= pair.value;
-	}
-
-	/*
-	 * If the arch, vendor, and implementation ID are all the same across
-	 * all harts, then assume all CPUs are the same, and allow the vDSO to
-	 * answer queries for arbitrary masks. However if all values are 0 (not
-	 * populated) or any value returns -1 (varies across CPUs), then the
-	 * vDSO should defer to the kernel for exotic cpu masks.
-	 */
-	avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1;
-	return 0;
-}
-
-arch_initcall_sync(init_hwprobe_vdso_data);
-
-#endif /* CONFIG_MMU */
-
-SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
-		size_t, pair_count, size_t, cpu_count, unsigned long __user *,
-		cpus, unsigned int, flags)
-{
-	return do_riscv_hwprobe(pairs, pair_count, cpu_count,
-				cpus, flags);
-}
-
 /* Not defined using SYSCALL_DEFINE0 to avoid error injection */
 asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *__unused)
 {

arch/riscv/kernel/traps_misaligned.c

@@ -319,7 +319,7 @@ static inline int get_insn(struct pt_regs *regs, ulong mepc, ulong *r_insn)
 static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val)
 {
 	if (user_mode(regs)) {
-		return __get_user(*r_val, addr);
+		return __get_user(*r_val, (u8 __user *)addr);
 	} else {
 		*r_val = *addr;
 		return 0;
@@ -329,7 +329,7 @@ static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val)
 static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val)
 {
 	if (user_mode(regs)) {
-		return __put_user(val, addr);
+		return __put_user(val, (u8 __user *)addr);
 	} else {
 		*addr = val;
 		return 0;
@@ -343,7 +343,7 @@ static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val)
 	if (user_mode(regs)) {				\
 		__ret = __get_user(insn, insn_addr);	\
 	} else {					\
-		insn = *insn_addr;			\
+		insn = *(__force u16 *)insn_addr;	\
 		__ret = 0;				\
 	}						\
 							\

arch/riscv/kernel/vdso/hwprobe.c

@@ -3,26 +3,22 @@
  * Copyright 2023 Rivos, Inc
  */
 
+#include <linux/string.h>
 #include <linux/types.h>
 #include <vdso/datapage.h>
 #include <vdso/helpers.h>
 
 extern int riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpu_count, unsigned long *cpus,
+			 size_t cpusetsize, unsigned long *cpus,
 			 unsigned int flags);
 
-/* Add a prototype to avoid -Wmissing-prototypes warning. */
-int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpu_count, unsigned long *cpus,
-			 unsigned int flags);
-
-int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpu_count, unsigned long *cpus,
-			 unsigned int flags)
+static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count,
+				 size_t cpusetsize, unsigned long *cpus,
+				 unsigned int flags)
 {
 	const struct vdso_data *vd = __arch_get_vdso_data();
 	const struct arch_vdso_data *avd = &vd->arch_data;
-	bool all_cpus = !cpu_count && !cpus;
+	bool all_cpus = !cpusetsize && !cpus;
 	struct riscv_hwprobe *p = pairs;
 	struct riscv_hwprobe *end = pairs + pair_count;
 
@@ -33,7 +29,7 @@ int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
 	 * masks.
 	 */
 	if ((flags != 0) || (!all_cpus && !avd->homogeneous_cpus))
-		return riscv_hwprobe(pairs, pair_count, cpu_count, cpus, flags);
+		return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags);
 
 	/* This is something we can handle, fill out the pairs. */
 	while (p < end) {
@@ -50,3 +46,71 @@ int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
 
 	return 0;
 }
+
+static int riscv_vdso_get_cpus(struct riscv_hwprobe *pairs, size_t pair_count,
+			       size_t cpusetsize, unsigned long *cpus,
+			       unsigned int flags)
+{
+	const struct vdso_data *vd = __arch_get_vdso_data();
+	const struct arch_vdso_data *avd = &vd->arch_data;
+	struct riscv_hwprobe *p = pairs;
+	struct riscv_hwprobe *end = pairs + pair_count;
+	unsigned char *c = (unsigned char *)cpus;
+	bool empty_cpus = true;
+	bool clear_all = false;
+	int i;
+
+	if (!cpusetsize || !cpus)
+		return -EINVAL;
+
+	for (i = 0; i < cpusetsize; i++) {
+		if (c[i]) {
+			empty_cpus = false;
+			break;
+		}
+	}
+
+	if (empty_cpus || flags != RISCV_HWPROBE_WHICH_CPUS || !avd->homogeneous_cpus)
+		return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags);
+
+	while (p < end) {
+		if (riscv_hwprobe_key_is_valid(p->key)) {
+			struct riscv_hwprobe t = {
+				.key = p->key,
+				.value = avd->all_cpu_hwprobe_values[p->key],
+			};
+
+			if (!riscv_hwprobe_pair_cmp(&t, p))
+				clear_all = true;
+		} else {
+			clear_all = true;
+			p->key = -1;
+			p->value = 0;
+		}
+		p++;
+	}
+
+	if (clear_all) {
+		for (i = 0; i < cpusetsize; i++)
+			c[i] = 0;
+	}
+
+	return 0;
+}
+
+/* Add a prototype to avoid -Wmissing-prototypes warning. */
+int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
+			 size_t cpusetsize, unsigned long *cpus,
+			 unsigned int flags);
+
+int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
+			 size_t cpusetsize, unsigned long *cpus,
+			 unsigned int flags)
+{
+	if (flags & RISCV_HWPROBE_WHICH_CPUS)
+		return riscv_vdso_get_cpus(pairs, pair_count, cpusetsize,
+					   cpus, flags);
+
+	return riscv_vdso_get_values(pairs, pair_count, cpusetsize,
+				     cpus, flags);
+}

arch/riscv/kernel/vmlinux-xip.lds.S

@@ -29,10 +29,12 @@ SECTIONS
 	HEAD_TEXT_SECTION
 	INIT_TEXT_SECTION(PAGE_SIZE)
 	/* we have to discard exit text and such at runtime, not link time */
+	__exittext_begin = .;
 	.exit.text :
 	{
 		EXIT_TEXT
 	}
+	__exittext_end = .;
 
 	.text : {
 		_text = .;

arch/riscv/kernel/vmlinux.lds.S

@@ -69,10 +69,12 @@ SECTIONS
 		__soc_builtin_dtb_table_end = .;
 	}
 	/* we have to discard exit text and such at runtime, not link time */
+	__exittext_begin = .;
 	.exit.text :
 	{
 		EXIT_TEXT
 	}
+	__exittext_end = .;
 
 	__init_text_end = .;
 	. = ALIGN(SECTION_ALIGN);

arch/riscv/kvm/mmu.c

@@ -103,7 +103,7 @@ static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr,
 	*ptep_level = current_level;
 	ptep = (pte_t *)kvm->arch.pgd;
 	ptep = &ptep[gstage_pte_index(addr, current_level)];
-	while (ptep && pte_val(*ptep)) {
+	while (ptep && pte_val(ptep_get(ptep))) {
 		if (gstage_pte_leaf(ptep)) {
 			*ptep_level = current_level;
 			*ptepp = ptep;
@@ -113,7 +113,7 @@ static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr,
 		if (current_level) {
 			current_level--;
 			*ptep_level = current_level;
-			ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+			ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 			ptep = &ptep[gstage_pte_index(addr, current_level)];
 		} else {
 			ptep = NULL;
@@ -149,25 +149,25 @@ static int gstage_set_pte(struct kvm *kvm, u32 level,
 		if (gstage_pte_leaf(ptep))
 			return -EEXIST;
 
-		if (!pte_val(*ptep)) {
+		if (!pte_val(ptep_get(ptep))) {
 			if (!pcache)
 				return -ENOMEM;
 			next_ptep = kvm_mmu_memory_cache_alloc(pcache);
 			if (!next_ptep)
 				return -ENOMEM;
-			*ptep = pfn_pte(PFN_DOWN(__pa(next_ptep)),
-					__pgprot(_PAGE_TABLE));
+			set_pte(ptep, pfn_pte(PFN_DOWN(__pa(next_ptep)),
+					      __pgprot(_PAGE_TABLE)));
 		} else {
 			if (gstage_pte_leaf(ptep))
 				return -EEXIST;
-			next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+			next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 		}
 
 		current_level--;
 		ptep = &next_ptep[gstage_pte_index(addr, current_level)];
 	}
 
-	*ptep = *new_pte;
+	set_pte(ptep, *new_pte);
 	if (gstage_pte_leaf(ptep))
 		gstage_remote_tlb_flush(kvm, current_level, addr);
 
@@ -239,11 +239,11 @@ static void gstage_op_pte(struct kvm *kvm, gpa_t addr,
 
 	BUG_ON(addr & (page_size - 1));
 
-	if (!pte_val(*ptep))
+	if (!pte_val(ptep_get(ptep)))
 		return;
 
 	if (ptep_level && !gstage_pte_leaf(ptep)) {
-		next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+		next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 		next_ptep_level = ptep_level - 1;
 		ret = gstage_level_to_page_size(next_ptep_level,
 						&next_page_size);
@@ -261,7 +261,7 @@ static void gstage_op_pte(struct kvm *kvm, gpa_t addr,
 		if (op == GSTAGE_OP_CLEAR)
 			set_pte(ptep, __pte(0));
 		else if (op == GSTAGE_OP_WP)
-			set_pte(ptep, __pte(pte_val(*ptep) & ~_PAGE_WRITE));
+			set_pte(ptep, __pte(pte_val(ptep_get(ptep)) & ~_PAGE_WRITE));
 		gstage_remote_tlb_flush(kvm, ptep_level, addr);
 	}
 }
@@ -603,7 +603,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 				   &ptep, &ptep_level))
 		return false;
 
-	return pte_young(*ptep);
+	return pte_young(ptep_get(ptep));
 }
 
 int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,

arch/riscv/lib/clear_page.S

@@ -4,9 +4,9 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/alternative-macros.h>
-#include <asm-generic/export.h>
 #include <asm/hwcap.h>
 #include <asm/insn-def.h>
 #include <asm/page.h>

arch/riscv/lib/tishift.S

@@ -4,7 +4,7 @@
  */
 
 #include <linux/linkage.h>
-#include <asm-generic/export.h>
+#include <linux/export.h>
 
 SYM_FUNC_START(__lshrti3)
 	beqz	a2, .L1

arch/riscv/lib/uaccess.S

 #include <linux/linkage.h>
-#include <asm-generic/export.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/asm-extable.h>
 #include <asm/csr.h>

arch/riscv/mm/Makefile

@@ -13,10 +13,9 @@ endif
 KCOV_INSTRUMENT_init.o := n
 
 obj-y += init.o
-obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o
+obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o pgtable.o
 obj-y += cacheflush.o
 obj-y += context.o
-obj-y += pgtable.o
 obj-y += pmem.o
 
 ifeq ($(CONFIG_MMU),y)

arch/riscv/mm/fault.c

@@ -136,24 +136,24 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	pgd = (pgd_t *)pfn_to_virt(pfn) + index;
 	pgd_k = init_mm.pgd + index;
 
-	if (!pgd_present(*pgd_k)) {
+	if (!pgd_present(pgdp_get(pgd_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	set_pgd(pgd, *pgd_k);
+	set_pgd(pgd, pgdp_get(pgd_k));
 
 	p4d_k = p4d_offset(pgd_k, addr);
-	if (!p4d_present(*p4d_k)) {
+	if (!p4d_present(p4dp_get(p4d_k))) {
 		no_context(regs, addr);
 		return;
 	}
 
 	pud_k = pud_offset(p4d_k, addr);
-	if (!pud_present(*pud_k)) {
+	if (!pud_present(pudp_get(pud_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	if (pud_leaf(*pud_k))
+	if (pud_leaf(pudp_get(pud_k)))
 		goto flush_tlb;
 
 	/*
@@ -161,11 +161,11 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	 * to copy individual PTEs
 	 */
 	pmd_k = pmd_offset(pud_k, addr);
-	if (!pmd_present(*pmd_k)) {
+	if (!pmd_present(pmdp_get(pmd_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	if (pmd_leaf(*pmd_k))
+	if (pmd_leaf(pmdp_get(pmd_k)))
 		goto flush_tlb;
 
 	/*
@@ -175,7 +175,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	 * silently loop forever.
 	 */
 	pte_k = pte_offset_kernel(pmd_k, addr);
-	if (!pte_present(*pte_k)) {
+	if (!pte_present(ptep_get(pte_k))) {
 		no_context(regs, addr);
 		return;
 	}

arch/riscv/mm/hugetlbpage.c

@@ -54,7 +54,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	}
 
 	if (sz == PMD_SIZE) {
-		if (want_pmd_share(vma, addr) && pud_none(*pud))
+		if (want_pmd_share(vma, addr) && pud_none(pudp_get(pud)))
 			pte = huge_pmd_share(mm, vma, addr, pud);
 		else
 			pte = (pte_t *)pmd_alloc(mm, pud, addr);
@@ -93,11 +93,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
-	if (!pgd_present(*pgd))
+	if (!pgd_present(pgdp_get(pgd)))
 		return NULL;
 
 	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
+	if (!p4d_present(p4dp_get(p4d)))
 		return NULL;
 
 	pud = pud_offset(p4d, addr);
@@ -105,7 +105,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		/* must be pud huge, non-present or none */
 		return (pte_t *)pud;
 
-	if (!pud_present(*pud))
+	if (!pud_present(pudp_get(pud)))
 		return NULL;
 
 	pmd = pmd_offset(pud, addr);
@@ -113,7 +113,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		/* must be pmd huge, non-present or none */
 		return (pte_t *)pmd;
 
-	if (!pmd_present(*pmd))
+	if (!pmd_present(pmdp_get(pmd)))
 		return NULL;
 
 	for_each_napot_order(order) {
@@ -293,7 +293,7 @@ void huge_pte_clear(struct mm_struct *mm,
 		    pte_t *ptep,
 		    unsigned long sz)
 {
-	pte_t pte = READ_ONCE(*ptep);
+	pte_t pte = ptep_get(ptep);
 	int i, pte_num;
 
 	if (!pte_napot(pte)) {

arch/riscv/mm/init.c

@@ -174,6 +174,9 @@ void __init mem_init(void)
 
 /* Limit the memory size via mem. */
 static phys_addr_t memory_limit;
+#ifdef CONFIG_XIP_KERNEL
+#define memory_limit	(*(phys_addr_t *)XIP_FIXUP(&memory_limit))
+#endif /* CONFIG_XIP_KERNEL */
 
 static int __init early_mem(char *p)
 {
@@ -952,7 +955,7 @@ static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va,
 	 * setup_vm_final installs the linear mapping. For 32-bit kernel, as the
 	 * kernel is mapped in the linear mapping, that makes no difference.
 	 */
-	dtb_early_va = kernel_mapping_pa_to_va(XIP_FIXUP(dtb_pa));
+	dtb_early_va = kernel_mapping_pa_to_va(dtb_pa);
 #endif
 
 	dtb_early_pa = dtb_pa;
@@ -1055,9 +1058,9 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 #endif
 
 	kernel_map.virt_addr = KERNEL_LINK_ADDR + kernel_map.virt_offset;
-	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
 
 #ifdef CONFIG_XIP_KERNEL
+	kernel_map.page_offset = PAGE_OFFSET_L3;
 	kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
 	kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);
 
@@ -1067,6 +1070,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 
 	kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom;
 #else
+	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
 	kernel_map.phys_addr = (uintptr_t)(&_start);
 	kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr;
 #endif

arch/riscv/mm/kasan_init.c

@@ -31,7 +31,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned
 	phys_addr_t phys_addr;
 	pte_t *ptep, *p;
 
-	if (pmd_none(*pmd)) {
+	if (pmd_none(pmdp_get(pmd))) {
 		p = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
 		set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -39,7 +39,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned
 	ptep = pte_offset_kernel(pmd, vaddr);
 
 	do {
-		if (pte_none(*ptep)) {
+		if (pte_none(ptep_get(ptep))) {
 			phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL));
 			memset(__va(phys_addr), KASAN_SHADOW_INIT, PAGE_SIZE);
@@ -53,7 +53,7 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned
 	pmd_t *pmdp, *p;
 	unsigned long next;
 
-	if (pud_none(*pud)) {
+	if (pud_none(pudp_get(pud))) {
 		p = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
 		set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -63,7 +63,8 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned
 	do {
 		next = pmd_addr_end(vaddr, end);
 
-		if (pmd_none(*pmdp) && IS_ALIGNED(vaddr, PMD_SIZE) && (next - vaddr) >= PMD_SIZE) {
+		if (pmd_none(pmdp_get(pmdp)) && IS_ALIGNED(vaddr, PMD_SIZE) &&
+		    (next - vaddr) >= PMD_SIZE) {
 			phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE);
 			if (phys_addr) {
 				set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL));
@@ -83,7 +84,7 @@ static void __init kasan_populate_pud(p4d_t *p4d,
 	pud_t *pudp, *p;
 	unsigned long next;
 
-	if (p4d_none(*p4d)) {
+	if (p4d_none(p4dp_get(p4d))) {
 		p = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
 		set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -93,7 +94,8 @@ static void __init kasan_populate_pud(p4d_t *p4d,
 	do {
 		next = pud_addr_end(vaddr, end);
 
-		if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) {
+		if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) &&
+		    (next - vaddr) >= PUD_SIZE) {
 			phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE);
 			if (phys_addr) {
 				set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL));
@@ -113,7 +115,7 @@ static void __init kasan_populate_p4d(pgd_t *pgd,
 	p4d_t *p4dp, *p;
 	unsigned long next;
 
-	if (pgd_none(*pgd)) {
+	if (pgd_none(pgdp_get(pgd))) {
 		p = memblock_alloc(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE);
 		set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -123,7 +125,8 @@ static void __init kasan_populate_p4d(pgd_t *pgd,
 	do {
 		next = p4d_addr_end(vaddr, end);
 
-		if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) {
+		if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) &&
+		    (next - vaddr) >= P4D_SIZE) {
 			phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE);
 			if (phys_addr) {
 				set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL));
@@ -145,7 +148,7 @@ static void __init kasan_populate_pgd(pgd_t *pgdp,
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+		if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
 		    (next - vaddr) >= PGDIR_SIZE) {
 			phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
 			if (phys_addr) {
@@ -168,7 +171,7 @@ static void __init kasan_early_clear_pud(p4d_t *p4dp,
 	if (!pgtable_l4_enabled) {
 		pudp = (pud_t *)p4dp;
 	} else {
-		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp)));
+		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp))));
 		pudp = base_pud + pud_index(vaddr);
 	}
 
@@ -193,7 +196,7 @@ static void __init kasan_early_clear_p4d(pgd_t *pgdp,
 	if (!pgtable_l5_enabled) {
 		p4dp = (p4d_t *)pgdp;
 	} else {
-		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp)));
+		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp))));
 		p4dp = base_p4d + p4d_index(vaddr);
 	}
 
@@ -239,14 +242,14 @@ static void __init kasan_early_populate_pud(p4d_t *p4dp,
 	if (!pgtable_l4_enabled) {
 		pudp = (pud_t *)p4dp;
 	} else {
-		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp)));
+		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp))));
 		pudp = base_pud + pud_index(vaddr);
 	}
 
 	do {
 		next = pud_addr_end(vaddr, end);
 
-		if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) &&
+		if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) &&
 		    (next - vaddr) >= PUD_SIZE) {
 			phys_addr = __pa((uintptr_t)kasan_early_shadow_pmd);
 			set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE));
@@ -277,14 +280,14 @@ static void __init kasan_early_populate_p4d(pgd_t *pgdp,
 	if (!pgtable_l5_enabled) {
 		p4dp = (p4d_t *)pgdp;
 	} else {
-		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp)));
+		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp))));
 		p4dp = base_p4d + p4d_index(vaddr);
 	}
 
 	do {
 		next = p4d_addr_end(vaddr, end);
 
-		if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) &&
+		if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) &&
 		    (next - vaddr) >= P4D_SIZE) {
 			phys_addr = __pa((uintptr_t)kasan_early_shadow_pud);
 			set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE));
@@ -305,7 +308,7 @@ static void __init kasan_early_populate_pgd(pgd_t *pgdp,
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+		if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
 		    (next - vaddr) >= PGDIR_SIZE) {
 			phys_addr = __pa((uintptr_t)kasan_early_shadow_p4d);
 			set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE));
@@ -381,7 +384,7 @@ static void __init kasan_shallow_populate_pud(p4d_t *p4d,
 	do {
 		next = pud_addr_end(vaddr, end);
 
-		if (pud_none(*pud_k)) {
+		if (pud_none(pudp_get(pud_k))) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
@@ -401,7 +404,7 @@ static void __init kasan_shallow_populate_p4d(pgd_t *pgd,
 	do {
 		next = p4d_addr_end(vaddr, end);
 
-		if (p4d_none(*p4d_k)) {
+		if (p4d_none(p4dp_get(p4d_k))) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
@@ -420,7 +423,7 @@ static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		if (pgd_none(*pgd_k)) {
+		if (pgd_none(pgdp_get(pgd_k))) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
@@ -451,7 +454,7 @@ static void __init create_tmp_mapping(void)
 
 	/* Copy the last p4d since it is shared with the kernel mapping. */
 	if (pgtable_l5_enabled) {
-		ptr = (p4d_t *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
+		ptr = (p4d_t *)pgd_page_vaddr(pgdp_get(pgd_offset_k(KASAN_SHADOW_END)));
 		memcpy(tmp_p4d, ptr, sizeof(p4d_t) * PTRS_PER_P4D);
 		set_pgd(&tmp_pg_dir[pgd_index(KASAN_SHADOW_END)],
 			pfn_pgd(PFN_DOWN(__pa(tmp_p4d)), PAGE_TABLE));
@@ -462,7 +465,7 @@ static void __init create_tmp_mapping(void)
 
 	/* Copy the last pud since it is shared with the kernel mapping. */
 	if (pgtable_l4_enabled) {
-		ptr = (pud_t *)p4d_page_vaddr(*(base_p4d + p4d_index(KASAN_SHADOW_END)));
+		ptr = (pud_t *)p4d_page_vaddr(p4dp_get(base_p4d + p4d_index(KASAN_SHADOW_END)));
 		memcpy(tmp_pud, ptr, sizeof(pud_t) * PTRS_PER_PUD);
 		set_p4d(&base_p4d[p4d_index(KASAN_SHADOW_END)],
 			pfn_p4d(PFN_DOWN(__pa(tmp_pud)), PAGE_TABLE));

arch/riscv/mm/pageattr.c

@@ -29,7 +29,7 @@ static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk)
 static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	p4d_t val = READ_ONCE(*p4d);
+	p4d_t val = p4dp_get(p4d);
 
 	if (p4d_leaf(val)) {
 		val = __p4d(set_pageattr_masks(p4d_val(val), walk));
@@ -42,7 +42,7 @@ static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pud_t val = READ_ONCE(*pud);
+	pud_t val = pudp_get(pud);
 
 	if (pud_leaf(val)) {
 		val = __pud(set_pageattr_masks(pud_val(val), walk));
@@ -55,7 +55,7 @@ static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
 static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pmd_t val = READ_ONCE(*pmd);
+	pmd_t val = pmdp_get(pmd);
 
 	if (pmd_leaf(val)) {
 		val = __pmd(set_pageattr_masks(pmd_val(val), walk));
@@ -68,7 +68,7 @@ static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
 static int pageattr_pte_entry(pte_t *pte, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pte_t val = READ_ONCE(*pte);
+	pte_t val = ptep_get(pte);
 
 	val = __pte(set_pageattr_masks(pte_val(val), walk));
 	set_pte(pte, val);
@@ -108,10 +108,10 @@ static int __split_linear_mapping_pmd(pud_t *pudp,
 		    vaddr <= (vaddr & PMD_MASK) && end >= next)
 			continue;
 
-		if (pmd_leaf(*pmdp)) {
+		if (pmd_leaf(pmdp_get(pmdp))) {
 			struct page *pte_page;
-			unsigned long pfn = _pmd_pfn(*pmdp);
-			pgprot_t prot = __pgprot(pmd_val(*pmdp) & ~_PAGE_PFN_MASK);
+			unsigned long pfn = _pmd_pfn(pmdp_get(pmdp));
+			pgprot_t prot = __pgprot(pmd_val(pmdp_get(pmdp)) & ~_PAGE_PFN_MASK);
 			pte_t *ptep_new;
 			int i;
 
@@ -148,10 +148,10 @@ static int __split_linear_mapping_pud(p4d_t *p4dp,
 		    vaddr <= (vaddr & PUD_MASK) && end >= next)
 			continue;
 
-		if (pud_leaf(*pudp)) {
+		if (pud_leaf(pudp_get(pudp))) {
 			struct page *pmd_page;
-			unsigned long pfn = _pud_pfn(*pudp);
-			pgprot_t prot = __pgprot(pud_val(*pudp) & ~_PAGE_PFN_MASK);
+			unsigned long pfn = _pud_pfn(pudp_get(pudp));
+			pgprot_t prot = __pgprot(pud_val(pudp_get(pudp)) & ~_PAGE_PFN_MASK);
 			pmd_t *pmdp_new;
 			int i;
 
@@ -197,10 +197,10 @@ static int __split_linear_mapping_p4d(pgd_t *pgdp,
 		    vaddr <= (vaddr & P4D_MASK) && end >= next)
 			continue;
 
-		if (p4d_leaf(*p4dp)) {
+		if (p4d_leaf(p4dp_get(p4dp))) {
 			struct page *pud_page;
-			unsigned long pfn = _p4d_pfn(*p4dp);
-			pgprot_t prot = __pgprot(p4d_val(*p4dp) & ~_PAGE_PFN_MASK);
+			unsigned long pfn = _p4d_pfn(p4dp_get(p4dp));
+			pgprot_t prot = __pgprot(p4d_val(p4dp_get(p4dp)) & ~_PAGE_PFN_MASK);
 			pud_t *pudp_new;
 			int i;
 
@@ -305,8 +305,13 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 				goto unlock;
 		}
 	} else if (is_kernel_mapping(start) || is_linear_mapping(start)) {
-		lm_start = (unsigned long)lm_alias(start);
-		lm_end = (unsigned long)lm_alias(end);
+		if (is_kernel_mapping(start)) {
+			lm_start = (unsigned long)lm_alias(start);
+			lm_end = (unsigned long)lm_alias(end);
+		} else {
+			lm_start = start;
+			lm_end = end;
+		}
 
 		ret = split_linear_mapping(lm_start, lm_end);
 		if (ret)
@@ -378,7 +383,7 @@ int set_direct_map_invalid_noflush(struct page *page)
 int set_direct_map_default_noflush(struct page *page)
 {
 	return __set_memory((unsigned long)page_address(page), 1,
-			    PAGE_KERNEL, __pgprot(0));
+			    PAGE_KERNEL, __pgprot(_PAGE_EXEC));
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
@@ -406,29 +411,29 @@ bool kernel_page_present(struct page *page)
 	pte_t *pte;
 
 	pgd = pgd_offset_k(addr);
-	if (!pgd_present(*pgd))
+	if (!pgd_present(pgdp_get(pgd)))
 		return false;
-	if (pgd_leaf(*pgd))
+	if (pgd_leaf(pgdp_get(pgd)))
 		return true;
 
 	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
+	if (!p4d_present(p4dp_get(p4d)))
 		return false;
-	if (p4d_leaf(*p4d))
+	if (p4d_leaf(p4dp_get(p4d)))
 		return true;
 
 	pud = pud_offset(p4d, addr);
-	if (!pud_present(*pud))
+	if (!pud_present(pudp_get(pud)))
 		return false;
-	if (pud_leaf(*pud))
+	if (pud_leaf(pudp_get(pud)))
 		return true;
 
 	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd))
+	if (!pmd_present(pmdp_get(pmd)))
 		return false;
-	if (pmd_leaf(*pmd))
+	if (pmd_leaf(pmdp_get(pmd)))
 		return true;
 
 	pte = pte_offset_kernel(pmd, addr);
-	return pte_present(*pte);
+	return pte_present(ptep_get(pte));
 }

arch/riscv/mm/pgtable.c

@@ -5,6 +5,47 @@
 #include <linux/kernel.h>
 #include <linux/pgtable.h>
 
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	if (!pte_same(ptep_get(ptep), entry))
+		__set_pte_at(ptep, entry);
+	/*
+	 * update_mmu_cache will unconditionally execute, handling both
+	 * the case that the PTE changed and the spurious fault case.
+	 */
+	return true;
+}
+
+int ptep_test_and_clear_young(struct vm_area_struct *vma,
+			      unsigned long address,
+			      pte_t *ptep)
+{
+	if (!pte_young(ptep_get(ptep)))
+		return 0;
+	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
+}
+EXPORT_SYMBOL_GPL(ptep_test_and_clear_young);
+
+#ifdef CONFIG_64BIT
+pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	if (pgtable_l4_enabled)
+		return p4d_pgtable(p4dp_get(p4d)) + pud_index(address);
+
+	return (pud_t *)p4d;
+}
+
+p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+{
+	if (pgtable_l5_enabled)
+		return pgd_pgtable(pgdp_get(pgd)) + p4d_index(address);
+
+	return (p4d_t *)pgd;
+}
+#endif
+
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
 int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
 {
@@ -25,7 +66,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)
 
 int pud_clear_huge(pud_t *pud)
 {
-	if (!pud_leaf(READ_ONCE(*pud)))
+	if (!pud_leaf(pudp_get(pud)))
 		return 0;
 	pud_clear(pud);
 	return 1;
@@ -33,7 +74,7 @@ int pud_clear_huge(pud_t *pud)
 
 int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
-	pmd_t *pmd = pud_pgtable(*pud);
+	pmd_t *pmd = pud_pgtable(pudp_get(pud));
 	int i;
 
 	pud_clear(pud);
@@ -63,7 +104,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot)
 
 int pmd_clear_huge(pmd_t *pmd)
 {
-	if (!pmd_leaf(READ_ONCE(*pmd)))
+	if (!pmd_leaf(pmdp_get(pmd)))
 		return 0;
 	pmd_clear(pmd);
 	return 1;
@@ -71,7 +112,7 @@ int pmd_clear_huge(pmd_t *pmd)
 
 int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
-	pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
+	pte_t *pte = (pte_t *)pmd_page_vaddr(pmdp_get(pmd));
 
 	pmd_clear(pmd);
 
@@ -88,7 +129,7 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
 	pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	VM_BUG_ON(pmd_trans_huge(*pmdp));
+	VM_BUG_ON(pmd_trans_huge(pmdp_get(pmdp)));
 	/*
 	 * When leaf PTE entries (regular pages) are collapsed into a leaf
 	 * PMD entry (huge page), a valid non-leaf PTE is converted into a

include/linux/pgtable.h

@@ -299,6 +299,27 @@ static inline pmd_t pmdp_get(pmd_t *pmdp)
 }
 #endif
 
+#ifndef pudp_get
+static inline pud_t pudp_get(pud_t *pudp)
+{
+	return READ_ONCE(*pudp);
+}
+#endif
+
+#ifndef p4dp_get
+static inline p4d_t p4dp_get(p4d_t *p4dp)
+{
+	return READ_ONCE(*p4dp);
+}
+#endif
+
+#ifndef pgdp_get
+static inline pgd_t pgdp_get(pgd_t *pgdp)
+{
+	return READ_ONCE(*pgdp);
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address,

tools/testing/selftests/riscv/hwprobe/Makefile

@@ -4,7 +4,7 @@
 
 CFLAGS += -I$(top_srcdir)/tools/include
 
-TEST_GEN_PROGS := hwprobe cbo
+TEST_GEN_PROGS := hwprobe cbo which-cpus
 
 include ../../lib.mk
 
@@ -13,3 +13,6 @@ $(OUTPUT)/hwprobe: hwprobe.c sys_hwprobe.S
 
 $(OUTPUT)/cbo: cbo.c sys_hwprobe.S
 	$(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^
+
+$(OUTPUT)/which-cpus: which-cpus.c sys_hwprobe.S
+	$(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^

tools/testing/selftests/riscv/hwprobe/hwprobe.c

@@ -47,7 +47,7 @@ int main(int argc, char **argv)
 	ksft_test_result(out != 0, "Bad CPU set\n");
 
 	out = riscv_hwprobe(pairs, 8, 1, 0, 0);
-	ksft_test_result(out != 0, "NULL CPU set with non-zero count\n");
+	ksft_test_result(out != 0, "NULL CPU set with non-zero size\n");
 
 	pairs[0].key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR;
 	out = riscv_hwprobe(pairs, 1, 1, &cpus, 0);

tools/testing/selftests/riscv/hwprobe/hwprobe.h

@@ -10,6 +10,6 @@
  * contain the call.
  */
 long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-		   size_t cpu_count, unsigned long *cpus, unsigned int flags);
+		   size_t cpusetsize, unsigned long *cpus, unsigned int flags);
 
 #endif

tools/testing/selftests/riscv/hwprobe/which-cpus.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Ventana Micro Systems Inc.
+ *
+ * Test the RISCV_HWPROBE_WHICH_CPUS flag of hwprobe. Also provides a command
+ * line interface to get the cpu list for arbitrary hwprobe pairs.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sched.h>
+#include <unistd.h>
+#include <assert.h>
+
+#include "hwprobe.h"
+#include "../../kselftest.h"
+
+static void help(void)
+{
+	printf("\n"
+	       "which-cpus: [-h] [<key=value> [<key=value> ...]]\n\n"
+	       "   Without parameters, tests the RISCV_HWPROBE_WHICH_CPUS flag of hwprobe.\n"
+	       "   With parameters, where each parameter is a hwprobe pair written as\n"
+	       "   <key=value>, outputs the cpulist for cpus which all match the given set\n"
+	       "   of pairs.  'key' and 'value' should be in numeric form, e.g. 4=0x3b\n");
+}
+
+static void print_cpulist(cpu_set_t *cpus)
+{
+	int start = 0, end = 0;
+
+	if (!CPU_COUNT(cpus)) {
+		printf("cpus: None\n");
+		return;
+	}
+
+	printf("cpus:");
+	for (int i = 0, c = 0; i < CPU_COUNT(cpus); i++, c++) {
+		if (start != end && !CPU_ISSET(c, cpus))
+			printf("-%d", end);
+
+		while (!CPU_ISSET(c, cpus))
+			++c;
+
+		if (i != 0 && c == end + 1) {
+			end = c;
+			continue;
+		}
+
+		printf("%c%d", i == 0 ? ' ' : ',', c);
+		start = end = c;
+	}
+	if (start != end)
+		printf("-%d", end);
+	printf("\n");
+}
+
+static void do_which_cpus(int argc, char **argv, cpu_set_t *cpus)
+{
+	struct riscv_hwprobe *pairs;
+	int nr_pairs = argc - 1;
+	char *start, *end;
+	int rc;
+
+	pairs = malloc(nr_pairs * sizeof(struct riscv_hwprobe));
+	assert(pairs);
+
+	for (int i = 0; i < nr_pairs; i++) {
+		start = argv[i + 1];
+		pairs[i].key = strtol(start, &end, 0);
+		assert(end != start && *end == '=');
+		start = end + 1;
+		pairs[i].value = strtoul(start, &end, 0);
+		assert(end != start && *end == '\0');
+	}
+
+	rc = riscv_hwprobe(pairs, nr_pairs, sizeof(cpu_set_t), (unsigned long *)cpus, RISCV_HWPROBE_WHICH_CPUS);
+	assert(rc == 0);
+	print_cpulist(cpus);
+	free(pairs);
+}
+
+int main(int argc, char **argv)
+{
+	struct riscv_hwprobe pairs[2];
+	cpu_set_t cpus_aff, cpus;
+	__u64 ext0_all;
+	long rc;
+
+	rc = sched_getaffinity(0, sizeof(cpu_set_t), &cpus_aff);
+	assert(rc == 0);
+
+	if (argc > 1) {
+		if (!strcmp(argv[1], "-h"))
+			help();
+		else
+			do_which_cpus(argc, argv, &cpus_aff);
+		return 0;
+	}
+
+	ksft_print_header();
+	ksft_set_plan(7);
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, };
+	rc = riscv_hwprobe(pairs, 1, 0, NULL, 0);
+	assert(rc == 0 && pairs[0].key == RISCV_HWPROBE_KEY_BASE_BEHAVIOR &&
+	       pairs[0].value == RISCV_HWPROBE_BASE_BEHAVIOR_IMA);
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, };
+	rc = riscv_hwprobe(pairs, 1, 0, NULL, 0);
+	assert(rc == 0 && pairs[0].key == RISCV_HWPROBE_KEY_IMA_EXT_0);
+	ext0_all = pairs[0].value;
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	CPU_ZERO(&cpus);
+	rc = riscv_hwprobe(pairs, 1, 0, (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == -EINVAL, "no cpusetsize\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	rc = riscv_hwprobe(pairs, 1, sizeof(cpu_set_t), NULL, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == -EINVAL, "NULL cpus\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = 0xbadc0de, };
+	CPU_ZERO(&cpus);
+	rc = riscv_hwprobe(pairs, 1, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0 && CPU_COUNT(&cpus) == 0, "unknown key\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	CPU_ZERO(&cpus);
+	rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0, "duplicate keys\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, .value = ext0_all, };
+	CPU_ZERO(&cpus);
+	rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0 && CPU_COUNT(&cpus) == sysconf(_SC_NPROCESSORS_ONLN), "set all cpus\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, .value = ext0_all, };
+	memcpy(&cpus, &cpus_aff, sizeof(cpu_set_t));
+	rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0 && CPU_EQUAL(&cpus, &cpus_aff), "set all affinity cpus\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, .value = ~ext0_all, };
+	memcpy(&cpus, &cpus_aff, sizeof(cpu_set_t));
+	rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0 && CPU_COUNT(&cpus) == 0, "clear all cpus\n");
+
+	ksft_finished();
+}

tools/testing/selftests/riscv/vector/vstate_prctl.c

 // SPDX-License-Identifier: GPL-2.0-only
 #include <sys/prctl.h>
 #include <unistd.h>
-#include <asm/hwprobe.h>
 #include <errno.h>
 #include <sys/wait.h>
 
+#include "../hwprobe/hwprobe.h"
 #include "../../kselftest.h"
 
-/*
- * Rather than relying on having a new enough libc to define this, just do it
- * ourselves.  This way we don't need to be coupled to a new-enough libc to
- * contain the call.
- */
-long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-		   size_t cpu_count, unsigned long *cpus, unsigned int flags);
-
 #define NEXT_PROGRAM "./vstate_exec_nolibc"
 static int launch_test(int test_inherit)
 {