Merge tag 'riscv-for-linus-6.6-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

- Support for the new "riscv,isa-extensions" and "riscv,isa-base"
device tree interfaces for probing extensions

- Support for userspace access to the performance counters

- Support for more instructions in kprobes

- Crash kernels can be allocated above 4GiB

- Support for KCFI

- Support for ELFs in !MMU configurations

- ARCH_KMALLOC_MINALIGN has been reduced to 8

- mmap() defaults to sv48-sized addresses, with longer addresses hidden
behind a hint (similar to Arm and Intel)

- Also various fixes and cleanups

* tag 'riscv-for-linus-6.6-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (51 commits)
lib/Kconfig.debug: Restrict DEBUG_INFO_SPLIT for RISC-V
riscv: support PREEMPT_DYNAMIC with static keys
riscv: Move create_tmp_mapping() to init sections
riscv: Mark KASAN tmp* page tables variables as static
riscv: mm: use bitmap_zero() API
riscv: enable DEBUG_FORCE_FUNCTION_ALIGN_64B
riscv: remove redundant mv instructions
RISC-V: mm: Document mmap changes
RISC-V: mm: Update pgtable comment documentation
RISC-V: mm: Add tests for RISC-V mm
RISC-V: mm: Restrict address space for sv39,sv48,sv57
riscv: enable DMA_BOUNCE_UNALIGNED_KMALLOC for !dma_coherent
riscv: allow kmalloc() caches aligned to the smallest value
riscv: support the elf-fdpic binfmt loader
binfmt_elf_fdpic: support 64-bit systems
riscv: Allow CONFIG_CFI_CLANG to be selected
riscv/purgatory: Disable CFI
riscv: Add CFI error handling
riscv: Add ftrace_stub_graph
riscv: Add types to indirectly called assembly functions
...

Documentation/admin-guide/kernel-parameters.txt

···
 			memory region [offset, offset + size] for that kernel
 			image. If '@offset' is omitted, then a suitable offset
 			is selected automatically.
-			[KNL, X86-64, ARM64] Select a region under 4G first, and
+			[KNL, X86-64, ARM64, RISCV] Select a region under 4G first, and
 			fall back to reserve region above 4G when '@offset'
 			hasn't been specified.
 			See Documentation/admin-guide/kdump/kdump.rst for further details.
···
 			Documentation/admin-guide/kdump/kdump.rst for an example.
 
 	crashkernel=size[KMG],high
-			[KNL, X86-64, ARM64] range could be above 4G. Allow kernel
-			to allocate physical memory region from top, so could
-			be above 4G if system have more than 4G ram installed.
-			Otherwise memory region will be allocated below 4G, if
-			available.
+			[KNL, X86-64, ARM64, RISCV] range could be above 4G.
+			Allow kernel to allocate physical memory region from top,
+			so could be above 4G if system have more than 4G ram
+			installed. Otherwise memory region will be allocated
+			below 4G, if available.
 			It will be ignored if crashkernel=X is specified.
 	crashkernel=size[KMG],low
-			[KNL, X86-64, ARM64] range under 4G. When crashkernel=X,high
+			[KNL, X86-64, ARM64, RISCV] range under 4G. When crashkernel=X,high
 			is passed, kernel could allocate physical memory region
 			above 4G, that cause second kernel crash on system
 			that require some amount of low memory, e.g. swiotlb
···
 			size is	platform dependent.
 			  --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB)
 			  --> arm64: 128MiB
+			  --> riscv: 128MiB
 			This one lets the user specify own low range under 4G
 			for second kernel instead.
 			0: to disable low allocation.
···
 	ring3mwait=disable
 			[KNL] Disable ring 3 MONITOR/MWAIT feature on supported
 			CPUs.
+
+	riscv_isa_fallback [RISCV]
+			When CONFIG_RISCV_ISA_FALLBACK is not enabled, permit
+			falling back to detecting extension support by parsing
+			"riscv,isa" property on devicetree systems when the
+			replacement properties are not found. See the Kconfig
+			entry for RISCV_ISA_FALLBACK.
 
 	ro		[KNL] Mount root device read-only on boot
 

Documentation/admin-guide/sysctl/kernel.rst

···
 The default value is 8.
 
 
-perf_user_access (arm64 only)
-=================================
+perf_user_access (arm64 and riscv only)
+=======================================
 
-Controls user space access for reading perf event counters. When set to 1,
-user space can read performance monitor counter registers directly.
+Controls user space access for reading perf event counters.
+
+arm64
+=====
 
 The default value is 0 (access disabled).
 
+When set to 1, user space can read performance monitor counter registers
+directly.
+
 See Documentation/arch/arm64/perf.rst for more information.
 
+riscv
+=====
+
+When set to 0, user space access is disabled.
+
+The default value is 1, user space can read performance monitor counter
+registers through perf, any direct access without perf intervention will trigger
+an illegal instruction.
+
+When set to 2, which enables legacy mode (user space has direct access to cycle
+and insret CSRs only). Note that this legacy value is deprecated and will be
+removed once all user space applications are fixed.
+
+Note that the time CSR is always directly accessible to all modes.
 
 pid_max
 =======

Documentation/riscv/vm-layout.rst

···
    ffffffff00000000 |  -4     GB | ffffffff7fffffff |    2 GB | modules, BPF
    ffffffff80000000 |  -2     GB | ffffffffffffffff |    2 GB | kernel
   __________________|____________|__________________|_________|____________________________________________________________
+
+
+Userspace VAs
+--------------------
+To maintain compatibility with software that relies on the VA space with a
+maximum of 48 bits the kernel will, by default, return virtual addresses to
+userspace from a 48-bit range (sv48). This default behavior is achieved by
+passing 0 into the hint address parameter of mmap. On CPUs with an address space
+smaller than sv48, the CPU maximum supported address space will be the default.
+
+Software can "opt-in" to receiving VAs from another VA space by providing
+a hint address to mmap. A hint address passed to mmap will cause the largest
+address space that fits entirely into the hint to be used, unless there is no
+space left in the address space. If there is no space available in the requested
+address space, an address in the next smallest available address space will be
+returned.
+
+For example, in order to obtain 48-bit VA space, a hint address greater than
+:code:`1 << 47` must be provided. Note that this is 47 due to sv48 userspace
+ending at :code:`1 << 47` and the addresses beyond this are reserved for the
+kernel. Similarly, to obtain 57-bit VA space addresses, a hint address greater
+than or equal to :code:`1 << 56` must be provided.

arch/riscv/Kconfig

···
 	select ARCH_HAS_SET_MEMORY if MMU
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
 	select ARCH_HAS_STRICT_MODULE_RWX if MMU && !XIP_KERNEL
+	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAS_VDSO_DATA
···
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
 	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_CFI_CLANG
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
 	select ARCH_SUPPORTS_HUGETLBFS if MMU
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU
 	select ARCH_SUPPORTS_PER_VMA_LOCK if MMU
 	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
+	select ARCH_USES_CFI_TRAPS if CFI_CLANG
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT
···
 	select COMMON_CLK
 	select CPU_PM if CPU_IDLE || HIBERNATION
 	select EDAC_SUPPORT
+	select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE)
 	select GENERIC_ARCH_TOPOLOGY
 	select GENERIC_ATOMIC64 if !64BIT
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
···
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
+	select HAVE_PREEMPT_DYNAMIC_KEY if !XIP_KERNEL
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RETHOOK if !XIP_KERNEL
 	select HAVE_RSEQ
···
 	select ARCH_HAS_SETUP_DMA_OPS
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select DMA_BOUNCE_UNALIGNED_KMALLOC if SWIOTLB
 	select DMA_DIRECT_REMAP
 
 config AS_HAS_INSN
···
 	  This is the physical address in your flash memory the kernel will
 	  be linked for and stored to.  This address is dependent on your
 	  own flash usage.
+
+config RISCV_ISA_FALLBACK
+	bool "Permit falling back to parsing riscv,isa for extension support by default"
+	default y
+	help
+	  Parsing the "riscv,isa" devicetree property has been deprecated and
+	  replaced by a list of explicitly defined strings. For compatibility
+	  with existing platforms, the kernel will fall back to parsing the
+	  "riscv,isa" property if the replacements are not found.
+
+	  Selecting N here will result in a kernel that does not use the
+	  fallback, unless the commandline "riscv_isa_fallback" parameter is
+	  present.
+
+	  Please see the dt-binding, located at
+	  Documentation/devicetree/bindings/riscv/extensions.yaml for details
+	  on the replacement properties, "riscv,isa-base" and
+	  "riscv,isa-extensions".
 
 endmenu # "Boot options"
 

arch/riscv/Makefile

···
 ifeq ($(CONFIG_CMODEL_MEDANY),y)
 	KBUILD_CFLAGS += -mcmodel=medany
 endif
-ifeq ($(CONFIG_PERF_EVENTS),y)
-        KBUILD_CFLAGS += -fno-omit-frame-pointer
-endif
 
 # Avoid generating .eh_frame sections.
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables

arch/riscv/include/asm/alternative-macros.h

···
  * vendor_id: The CPU vendor ID.
  * patch_id: The patch ID (erratum ID or cpufeature ID).
  * CONFIG_k: The Kconfig of this patch ID. When Kconfig is disabled, the old
- *	     content will alwyas be executed.
+ *	     content will always be executed.
  */
 #define ALTERNATIVE(old_content, new_content, vendor_id, patch_id, CONFIG_k) \
 	_ALTERNATIVE_CFG(old_content, new_content, vendor_id, patch_id, CONFIG_k)

arch/riscv/include/asm/cache.h

···
 
 #ifdef CONFIG_RISCV_DMA_NONCOHERENT
 #define ARCH_DMA_MINALIGN L1_CACHE_BYTES
+#define ARCH_KMALLOC_MINALIGN	(8)
 #endif
 
 /*
···
 #ifndef CONFIG_MMU
 #define ARCH_SLAB_MINALIGN	16
 #endif
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_RISCV_DMA_NONCOHERENT
+extern int dma_cache_alignment;
+#define dma_get_cache_alignment dma_get_cache_alignment
+static inline int dma_get_cache_alignment(void)
+{
+	return dma_cache_alignment;
+}
+#endif
+
+#endif	/* __ASSEMBLY__ */
 
 #endif /* _ASM_RISCV_CACHE_H */

arch/riscv/include/asm/cacheflush.h

···
 
 #ifdef CONFIG_RISCV_DMA_NONCOHERENT
 void riscv_noncoherent_supported(void);
+void __init riscv_set_dma_cache_alignment(void);
 #else
 static inline void riscv_noncoherent_supported(void) {}
+static inline void riscv_set_dma_cache_alignment(void) {}
 #endif
 
 /*

arch/riscv/include/asm/cfi.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_CFI_H
+#define _ASM_RISCV_CFI_H
+
+/*
+ * Clang Control Flow Integrity (CFI) support.
+ *
+ * Copyright (C) 2023 Google LLC
+ */
+
+#include <linux/cfi.h>
+
+#ifdef CONFIG_CFI_CLANG
+enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
+#else
+static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
+{
+	return BUG_TRAP_TYPE_NONE;
+}
+#endif /* CONFIG_CFI_CLANG */
+
+#endif /* _ASM_RISCV_CFI_H */

arch/riscv/include/asm/elf.h

···
 #define compat_elf_check_arch	compat_elf_check_arch
 
 #define CORE_DUMP_USE_REGSET
+#define ELF_FDPIC_CORE_EFLAGS	0
 #define ELF_EXEC_PAGESIZE	(PAGE_SIZE)
 
 /*
···
  * the loader.  We need to make sure that it is out of the way of the program
  * that it will "exec", and that there is sufficient room for the brk.
  */
-#define ELF_ET_DYN_BASE		((TASK_SIZE / 3) * 2)
+#define ELF_ET_DYN_BASE		((DEFAULT_MAP_WINDOW / 3) * 2)
 
 #ifdef CONFIG_64BIT
 #ifdef CONFIG_COMPAT
···
 #define ELF_HWCAP	riscv_get_elf_hwcap()
 extern unsigned long elf_hwcap;
 
+#define ELF_FDPIC_PLAT_INIT(_r, _exec_map_addr, _interp_map_addr, dynamic_addr) \
+	do { \
+		(_r)->a1 = _exec_map_addr; \
+		(_r)->a2 = _interp_map_addr; \
+		(_r)->a3 = dynamic_addr; \
+	} while (0)
+
 /*
  * This yields a string that ld.so will use to load implementation
  * specific libraries for optimization.  This is more specific in
···
 
 #define COMPAT_ELF_PLATFORM	(NULL)
 
-#ifdef CONFIG_MMU
 #define ARCH_DLINFO						\
 do {								\
 	/*							\
···
 	else							 \
 		NEW_AUX_ENT(AT_IGNORE, 0);			 \
 } while (0)
+
+#ifdef CONFIG_MMU
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES
 struct linux_binprm;
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,

arch/riscv/include/asm/hwcap.h

···
 #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')
···
 #define RISCV_ISA_EXT_ZIHPM		42
 
 #define RISCV_ISA_EXT_MAX		64
-#define RISCV_ISA_EXT_NAME_LEN_MAX	32
 
 #ifdef CONFIG_RISCV_M_MODE
 #define RISCV_ISA_EXT_SxAIA		RISCV_ISA_EXT_SMAIA
···
 unsigned long riscv_get_elf_hwcap(void);
 
 struct riscv_isa_ext_data {
-	/* Name of the extension displayed to userspace via /proc/cpuinfo */
-	char uprop[RISCV_ISA_EXT_NAME_LEN_MAX];
-	/* The logical ISA extension ID */
-	unsigned int isa_ext_id;
+	const unsigned int id;
+	const char *name;
+	const char *property;
 };
+
+extern const struct riscv_isa_ext_data riscv_isa_ext[];
+extern const size_t riscv_isa_ext_count;
+extern bool riscv_isa_fallback;
 
 unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
 

arch/riscv/include/asm/insn.h

···
 #define RVG_RS1_OPOFF		15
 #define RVG_RS2_OPOFF		20
 #define RVG_RD_OPOFF		7
+#define RVG_RS1_MASK		GENMASK(4, 0)
 #define RVG_RD_MASK		GENMASK(4, 0)
 
 /* The bit field of immediate value in RVC J instruction */
···
 #define RVC_C2_RS1_OPOFF	7
 #define RVC_C2_RS2_OPOFF	2
 #define RVC_C2_RD_OPOFF		7
+#define RVC_C2_RS1_MASK		GENMASK(4, 0)
 
 /* parts of opcode for RVG*/
 #define RVG_OPCODE_FENCE	0x0f
···
 #define RV_X(X, s, mask)  (((X) >> (s)) & (mask))
 #define RVC_X(X, s, mask) RV_X(X, s, mask)
 
+#define RV_EXTRACT_RS1_REG(x) \
+	({typeof(x) x_ = (x); \
+	(RV_X(x_, RVG_RS1_OPOFF, RVG_RS1_MASK)); })
+
 #define RV_EXTRACT_RD_REG(x) \
 	({typeof(x) x_ = (x); \
 	(RV_X(x_, RVG_RD_OPOFF, RVG_RD_MASK)); })
···
 	(RV_X(x_, RV_B_IMM_10_5_OPOFF, RV_B_IMM_10_5_MASK) << RV_B_IMM_10_5_OFF) | \
 	(RV_X(x_, RV_B_IMM_11_OPOFF, RV_B_IMM_11_MASK) << RV_B_IMM_11_OFF) | \
 	(RV_IMM_SIGN(x_) << RV_B_IMM_SIGN_OFF); })
+
+#define RVC_EXTRACT_C2_RS1_REG(x) \
+	({typeof(x) x_ = (x); \
+	(RV_X(x_, RVC_C2_RS1_OPOFF, RVC_C2_RS1_MASK)); })
 
 #define RVC_EXTRACT_JTYPE_IMM(x) \
 	({typeof(x) x_ = (x); \

arch/riscv/include/asm/mmu.h

···
 	/* A local icache flush is needed before user execution can resume. */
 	cpumask_t icache_stale_mask;
 #endif
+#ifdef CONFIG_BINFMT_ELF_FDPIC
+	unsigned long exec_fdpic_loadmap;
+	unsigned long interp_fdpic_loadmap;
+#endif
 } mm_context_t;
 
 void __init create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa,

arch/riscv/include/asm/pgtable.h

···
  * struct pages to map half the virtual address space. Then
  * position vmemmap directly below the VMALLOC region.
  */
+#define VA_BITS_SV32 32
 #ifdef CONFIG_64BIT
+#define VA_BITS_SV39 39
+#define VA_BITS_SV48 48
+#define VA_BITS_SV57 57
+
 #define VA_BITS		(pgtable_l5_enabled ? \
-				57 : (pgtable_l4_enabled ? 48 : 39))
+				VA_BITS_SV57 : (pgtable_l4_enabled ? VA_BITS_SV48 : VA_BITS_SV39))
 #else
-#define VA_BITS		32
+#define VA_BITS		VA_BITS_SV32
 #endif
 
 #define VMEMMAP_SHIFT \
···
 #include <asm/page.h>
 #include <asm/tlbflush.h>
 #include <linux/mm_types.h>
+#include <asm/compat.h>
 
 #define __page_val_to_pfn(_val)  (((_val) & _PAGE_PFN_MASK) >> _PAGE_PFN_SHIFT)
 
 #ifdef CONFIG_64BIT
 #include <asm/pgtable-64.h>
+
+#define VA_USER_SV39 (UL(1) << (VA_BITS_SV39 - 1))
+#define VA_USER_SV48 (UL(1) << (VA_BITS_SV48 - 1))
+#define VA_USER_SV57 (UL(1) << (VA_BITS_SV57 - 1))
+
+#ifdef CONFIG_COMPAT
+#define MMAP_VA_BITS_64 ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS)
+#define MMAP_MIN_VA_BITS_64 (VA_BITS_SV39)
+#define MMAP_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_VA_BITS_64)
+#define MMAP_MIN_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_MIN_VA_BITS_64)
+#else
+#define MMAP_VA_BITS ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS)
+#define MMAP_MIN_VA_BITS (VA_BITS_SV39)
+#endif /* CONFIG_COMPAT */
+
 #else
 #include <asm/pgtable-32.h>
 #endif /* CONFIG_64BIT */
···
  * Task size is 0x4000000000 for RV64 or 0x9fc00000 for RV32.
  * Note that PGDIR_SIZE must evenly divide TASK_SIZE.
  * Task size is:
- * -     0x9fc00000 (~2.5GB) for RV32.
- * -   0x4000000000 ( 256GB) for RV64 using SV39 mmu
- * - 0x800000000000 ( 128TB) for RV64 using SV48 mmu
+ * -        0x9fc00000	(~2.5GB) for RV32.
+ * -      0x4000000000	( 256GB) for RV64 using SV39 mmu
+ * -    0x800000000000	( 128TB) for RV64 using SV48 mmu
+ * - 0x100000000000000	(  64PB) for RV64 using SV57 mmu
  *
  * Note that PGDIR_SIZE must evenly divide TASK_SIZE since "RISC-V
  * Instruction Set Manual Volume II: Privileged Architecture" states that
  * "load and store effective addresses, which are 64bits, must have bits
  * 63–48 all equal to bit 47, or else a page-fault exception will occur."
+ * Similarly for SV57, bits 63–57 must be equal to bit 56.
  */
 #ifdef CONFIG_64BIT
 #define TASK_SIZE_64	(PGDIR_SIZE * PTRS_PER_PGD / 2)

arch/riscv/include/asm/processor.h

···
 
 #include <asm/ptrace.h>
 
+#ifdef CONFIG_64BIT
+#define DEFAULT_MAP_WINDOW	(UL(1) << (MMAP_VA_BITS - 1))
+#define STACK_TOP_MAX		TASK_SIZE_64
+
+#define arch_get_mmap_end(addr, len, flags)			\
+({								\
+	unsigned long mmap_end;					\
+	typeof(addr) _addr = (addr);				\
+	if ((_addr) == 0 || (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())) \
+		mmap_end = STACK_TOP_MAX;			\
+	else if ((_addr) >= VA_USER_SV57)			\
+		mmap_end = STACK_TOP_MAX;			\
+	else if ((((_addr) >= VA_USER_SV48)) && (VA_BITS >= VA_BITS_SV48)) \
+		mmap_end = VA_USER_SV48;			\
+	else							\
+		mmap_end = VA_USER_SV39;			\
+	mmap_end;						\
+})
+
+#define arch_get_mmap_base(addr, base)				\
+({								\
+	unsigned long mmap_base;				\
+	typeof(addr) _addr = (addr);				\
+	typeof(base) _base = (base);				\
+	unsigned long rnd_gap = DEFAULT_MAP_WINDOW - (_base);	\
+	if ((_addr) == 0 || (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())) \
+		mmap_base = (_base);				\
+	else if (((_addr) >= VA_USER_SV57) && (VA_BITS >= VA_BITS_SV57)) \
+		mmap_base = VA_USER_SV57 - rnd_gap;		\
+	else if ((((_addr) >= VA_USER_SV48)) && (VA_BITS >= VA_BITS_SV48)) \
+		mmap_base = VA_USER_SV48 - rnd_gap;		\
+	else							\
+		mmap_base = VA_USER_SV39 - rnd_gap;		\
+	mmap_base;						\
+})
+
+#else
+#define DEFAULT_MAP_WINDOW	TASK_SIZE
+#define STACK_TOP_MAX		TASK_SIZE
+#endif
+#define STACK_ALIGN		16
+
+#define STACK_TOP		DEFAULT_MAP_WINDOW
+
 /*
  * This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
  */
-#define TASK_UNMAPPED_BASE	PAGE_ALIGN(TASK_SIZE / 3)
-
-#define STACK_TOP		TASK_SIZE
 #ifdef CONFIG_64BIT
-#define STACK_TOP_MAX		TASK_SIZE_64
+#define TASK_UNMAPPED_BASE	PAGE_ALIGN((UL(1) << MMAP_MIN_VA_BITS) / 3)
 #else
-#define STACK_TOP_MAX		TASK_SIZE
+#define TASK_UNMAPPED_BASE	PAGE_ALIGN(TASK_SIZE / 3)
 #endif
-#define STACK_ALIGN		16
 
 #ifndef __ASSEMBLY__
 

arch/riscv/include/asm/syscall.h

···
 #endif
 }
 
-typedef long (*syscall_t)(ulong, ulong, ulong, ulong, ulong, ulong, ulong);
+typedef long (*syscall_t)(const struct pt_regs *);
 static inline void syscall_handler(struct pt_regs *regs, ulong syscall)
 {
 	syscall_t fn;
···
 #endif
 		fn = sys_call_table[syscall];
 
-	regs->a0 = fn(regs->orig_a0, regs->a1, regs->a2,
-		      regs->a3, regs->a4, regs->a5, regs->a6);
+	regs->a0 = fn(regs);
 }
 
 static inline bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)

arch/riscv/include/asm/syscall_wrapper.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * syscall_wrapper.h - riscv specific wrappers to syscall definitions
+ *
+ * Based on arch/arm64/include/syscall_wrapper.h
+ */
+
+#ifndef __ASM_SYSCALL_WRAPPER_H
+#define __ASM_SYSCALL_WRAPPER_H
+
+#include <asm/ptrace.h>
+
+asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *);
+
+#define SC_RISCV_REGS_TO_ARGS(x, ...)				\
+	__MAP(x,__SC_ARGS					\
+	      ,,regs->orig_a0,,regs->a1,,regs->a2		\
+	      ,,regs->a3,,regs->a4,,regs->a5,,regs->a6)
+
+#ifdef CONFIG_COMPAT
+
+#define COMPAT_SYSCALL_DEFINEx(x, name, ...)						\
+	asmlinkage long __riscv_compat_sys##name(const struct pt_regs *regs);		\
+	ALLOW_ERROR_INJECTION(__riscv_compat_sys##name, ERRNO);				\
+	static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));		\
+	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
+	asmlinkage long __riscv_compat_sys##name(const struct pt_regs *regs)		\
+	{										\
+		return __se_compat_sys##name(SC_RISCV_REGS_TO_ARGS(x,__VA_ARGS__));	\
+	}										\
+	static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))		\
+	{										\
+		return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));	\
+	}										\
+	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+#define COMPAT_SYSCALL_DEFINE0(sname)							\
+	asmlinkage long __riscv_compat_sys_##sname(const struct pt_regs *__unused);	\
+	ALLOW_ERROR_INJECTION(__riscv_compat_sys_##sname, ERRNO);			\
+	asmlinkage long __riscv_compat_sys_##sname(const struct pt_regs *__unused)
+
+#define COND_SYSCALL_COMPAT(name) 							\
+	asmlinkage long __weak __riscv_compat_sys_##name(const struct pt_regs *regs);	\
+	asmlinkage long __weak __riscv_compat_sys_##name(const struct pt_regs *regs)	\
+	{										\
+		return sys_ni_syscall();						\
+	}
+
+#define COMPAT_SYS_NI(name) \
+	SYSCALL_ALIAS(__riscv_compat_sys_##name, sys_ni_posix_timers);
+
+#endif /* CONFIG_COMPAT */
+
+#define __SYSCALL_DEFINEx(x, name, ...)						\
+	asmlinkage long __riscv_sys##name(const struct pt_regs *regs);		\
+	ALLOW_ERROR_INJECTION(__riscv_sys##name, ERRNO);			\
+	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));		\
+	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
+	asmlinkage long __riscv_sys##name(const struct pt_regs *regs)		\
+	{									\
+		return __se_sys##name(SC_RISCV_REGS_TO_ARGS(x,__VA_ARGS__));	\
+	}									\
+	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))		\
+	{									\
+		long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
+		__MAP(x,__SC_TEST,__VA_ARGS__);					\
+		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));		\
+		return ret;							\
+	}									\
+	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+#define SYSCALL_DEFINE0(sname)							\
+	SYSCALL_METADATA(_##sname, 0);						\
+	asmlinkage long __riscv_sys_##sname(const struct pt_regs *__unused);	\
+	ALLOW_ERROR_INJECTION(__riscv_sys_##sname, ERRNO);			\
+	asmlinkage long __riscv_sys_##sname(const struct pt_regs *__unused)
+
+#define COND_SYSCALL(name)							\
+	asmlinkage long __weak __riscv_sys_##name(const struct pt_regs *regs);	\
+	asmlinkage long __weak __riscv_sys_##name(const struct pt_regs *regs)	\
+	{									\
+		return sys_ni_syscall();					\
+	}
+
+#define SYS_NI(name) SYSCALL_ALIAS(__riscv_sys_##name, sys_ni_posix_timers);
+
+#endif /* __ASM_SYSCALL_WRAPPER_H */

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

···
 
 #include <linux/types.h>
 
+#define PTRACE_GETFDPIC		33
+
+#define PTRACE_GETFDPIC_EXEC	0
+#define PTRACE_GETFDPIC_INTERP	1
+
 /*
  * User-mode register state for core dumps, ptrace, sigcontext
  *

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

···
  * Signal context structure
  *
  * This contains the context saved before a signal handler is invoked;
- * it is restored by sys_sigreturn / sys_rt_sigreturn.
+ * it is restored by sys_rt_sigreturn.
  */
 struct sigcontext {
 	struct user_regs_struct sc_regs;

arch/riscv/kernel/Makefile

···
 
 obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
 
+obj-$(CONFIG_CFI_CLANG)		+= cfi.o
+
 obj-$(CONFIG_EFI)		+= efi.o
 obj-$(CONFIG_COMPAT)		+= compat_syscall_table.o
 obj-$(CONFIG_COMPAT)		+= compat_signal.o

arch/riscv/kernel/cfi.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Clang Control Flow Integrity (CFI) support.
+ *
+ * Copyright (C) 2023 Google LLC
+ */
+#include <asm/cfi.h>
+#include <asm/insn.h>
+
+/*
+ * Returns the target address and the expected type when regs->epc points
+ * to a compiler-generated CFI trap.
+ */
+static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target,
+			    u32 *type)
+{
+	unsigned long *regs_ptr = (unsigned long *)regs;
+	int rs1_num;
+	u32 insn;
+
+	*target = *type = 0;
+
+	/*
+	 * The compiler generates the following instruction sequence
+	 * for indirect call checks:
+	 *
+	 *   lw      t1, -4(<reg>)
+	 *   lui     t2, <hi20>
+	 *   addiw   t2, t2, <lo12>
+	 *   beq     t1, t2, .Ltmp1
+	 *   ebreak  ; <- regs->epc
+	 *   .Ltmp1:
+	 *   jalr    <reg>
+	 *
+	 * We can read the expected type and the target address from the
+	 * registers passed to the beq/jalr instructions.
+	 */
+	if (get_kernel_nofault(insn, (void *)regs->epc - 4))
+		return false;
+	if (!riscv_insn_is_beq(insn))
+		return false;
+
+	*type = (u32)regs_ptr[RV_EXTRACT_RS1_REG(insn)];
+
+	if (get_kernel_nofault(insn, (void *)regs->epc) ||
+	    get_kernel_nofault(insn, (void *)regs->epc + GET_INSN_LENGTH(insn)))
+		return false;
+
+	if (riscv_insn_is_jalr(insn))
+		rs1_num = RV_EXTRACT_RS1_REG(insn);
+	else if (riscv_insn_is_c_jalr(insn))
+		rs1_num = RVC_EXTRACT_C2_RS1_REG(insn);
+	else
+		return false;
+
+	*target = regs_ptr[rs1_num];
+
+	return true;
+}
+
+/*
+ * Checks if the ebreak trap is because of a CFI failure, and handles the trap
+ * if needed. Returns a bug_trap_type value similarly to report_bug.
+ */
+enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
+{
+	unsigned long target;
+	u32 type;
+
+	if (!is_cfi_trap(regs->epc))
+		return BUG_TRAP_TYPE_NONE;
+
+	if (!decode_cfi_insn(regs, &target, &type))
+		return report_cfi_failure_noaddr(regs, regs->epc);
+
+	return report_cfi_failure(regs, regs->epc, &target, type);
+}

arch/riscv/kernel/compat_syscall_table.c

···
 #include <asm/syscall.h>
 
 #undef __SYSCALL
-#define __SYSCALL(nr, call)      [nr] = (call),
+#define __SYSCALL(nr, call)	asmlinkage long __riscv_##call(const struct pt_regs *);
+#include <asm/unistd.h>
+
+#undef __SYSCALL
+#define __SYSCALL(nr, call)      [nr] = __riscv_##call,
 
 asmlinkage long compat_sys_rt_sigreturn(void);
 
 void * const compat_sys_call_table[__NR_syscalls] = {
-	[0 ... __NR_syscalls - 1] = sys_ni_syscall,
+	[0 ... __NR_syscalls - 1] = __riscv_sys_ni_syscall,
 #include <asm/unistd.h>
 };

arch/riscv/kernel/cpu.c

···
 	return 0;
 }
 
-int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart)
+int __init riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart)
 {
 	const char *isa;
 
···
 		return -ENODEV;
 	}
 
-	if (of_property_read_string(node, "riscv,isa", &isa)) {
-		pr_warn("CPU with hartid=%lu has no \"riscv,isa\" property\n", *hart);
+	if (of_property_read_string(node, "riscv,isa-base", &isa))
+		goto old_interface;
+
+	if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32i", 5)) {
+		pr_warn("CPU with hartid=%lu does not support rv32i", *hart);
 		return -ENODEV;
 	}
 
-	if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32ima", 7))
+	if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64i", 5)) {
+		pr_warn("CPU with hartid=%lu does not support rv64i", *hart);
+		return -ENODEV;
+	}
+
+	if (!of_property_present(node, "riscv,isa-extensions"))
 		return -ENODEV;
 
-	if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7))
+	if (of_property_match_string(node, "riscv,isa-extensions", "i") < 0 ||
+	    of_property_match_string(node, "riscv,isa-extensions", "m") < 0 ||
+	    of_property_match_string(node, "riscv,isa-extensions", "a") < 0) {
+		pr_warn("CPU with hartid=%lu does not support ima", *hart);
 		return -ENODEV;
+	}
+
+	return 0;
+
+old_interface:
+	if (!riscv_isa_fallback) {
+		pr_warn("CPU with hartid=%lu is invalid: this kernel does not parse \"riscv,isa\"",
+			*hart);
+		return -ENODEV;
+	}
+
+	if (of_property_read_string(node, "riscv,isa", &isa)) {
+		pr_warn("CPU with hartid=%lu has no \"riscv,isa-base\" or \"riscv,isa\" property\n",
+			*hart);
+		return -ENODEV;
+	}
+
+	if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32ima", 7)) {
+		pr_warn("CPU with hartid=%lu does not support rv32ima", *hart);
+		return -ENODEV;
+	}
+
+	if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7)) {
+		pr_warn("CPU with hartid=%lu does not support rv64ima", *hart);
+		return -ENODEV;
+	}
 
 	return 0;
 }
···
 
 #ifdef CONFIG_PROC_FS
 
-#define __RISCV_ISA_EXT_DATA(UPROP, EXTID) \
-	{							\
-		.uprop = #UPROP,				\
-		.isa_ext_id = EXTID,				\
-	}
-
-/*
- * The canonical order of ISA extension names in the ISA string is defined in
- * chapter 27 of the unprivileged specification.
- *
- * Ordinarily, for in-kernel data structures, this order is unimportant but
- * isa_ext_arr defines the order of the ISA string in /proc/cpuinfo.
- *
- * The specification uses vague wording, such as should, when it comes to
- * ordering, so for our purposes the following rules apply:
- *
- * 1. All multi-letter extensions must be separated from other extensions by an
- *    underscore.
- *
- * 2. Additional standard extensions (starting with 'Z') must be sorted after
- *    single-letter extensions and before any higher-privileged extensions.
-
- * 3. The first letter following the 'Z' conventionally indicates the most
- *    closely related alphabetical extension category, IMAFDQLCBKJTPVH.
- *    If multiple 'Z' extensions are named, they must be ordered first by
- *    category, then alphabetically within a category.
- *
- * 3. Standard supervisor-level extensions (starting with 'S') must be listed
- *    after standard unprivileged extensions.  If multiple supervisor-level
- *    extensions are listed, they must be ordered alphabetically.
- *
- * 4. Standard machine-level extensions (starting with 'Zxm') must be listed
- *    after any lower-privileged, standard extensions.  If multiple
- *    machine-level extensions are listed, they must be ordered
- *    alphabetically.
- *
- * 5. Non-standard extensions (starting with 'X') must be listed after all
- *    standard extensions. If multiple non-standard extensions are listed, they
- *    must be ordered alphabetically.
- *
- * An example string following the order is:
- *    rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux
- *
- * New entries to this struct should follow the ordering rules described above.
- */
-static struct riscv_isa_ext_data isa_ext_arr[] = {
-	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
-	__RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ),
-	__RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
-	__RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),
-	__RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI),
-	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
-	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
-	__RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA),
-	__RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB),
-	__RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS),
-	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
-	__RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
-	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
-	__RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC),
-	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
-	__RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),
-	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
-	__RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX),
-};
-
-static void print_isa_ext(struct seq_file *f)
+static void print_isa(struct seq_file *f)
 {
-	struct riscv_isa_ext_data *edata;
-	int i = 0, arr_sz;
-
-	arr_sz = ARRAY_SIZE(isa_ext_arr) - 1;
-
-	/* No extension support available */
-	if (arr_sz <= 0)
-		return;
-
-	for (i = 0; i <= arr_sz; i++) {
-		edata = &isa_ext_arr[i];
-		if (!__riscv_isa_extension_available(NULL, edata->isa_ext_id))
-			continue;
-		seq_printf(f, "_%s", edata->uprop);
-	}
-}
-
-/*
- * These are the only valid base (single letter) ISA extensions as per the spec.
- * It also specifies the canonical order in which it appears in the spec.
- * Some of the extension may just be a place holder for now (B, K, P, J).
- * This should be updated once corresponding extensions are ratified.
- */
-static const char base_riscv_exts[13] = "imafdqcbkjpvh";
-
-static void print_isa(struct seq_file *f, const char *isa)
-{
-	int i;
-
 	seq_puts(f, "isa\t\t: ");
-	/* Print the rv[64/32] part */
-	seq_write(f, isa, 4);
-	for (i = 0; i < sizeof(base_riscv_exts); i++) {
-		if (__riscv_isa_extension_available(NULL, base_riscv_exts[i] - 'a'))
-			/* Print only enabled the base ISA extensions */
-			seq_write(f, &base_riscv_exts[i], 1);
+
+	if (IS_ENABLED(CONFIG_32BIT))
+		seq_write(f, "rv32", 4);
+	else
+		seq_write(f, "rv64", 4);
+
+	for (int i = 0; i < riscv_isa_ext_count; i++) {
+		if (!__riscv_isa_extension_available(NULL, riscv_isa_ext[i].id))
+			continue;
+
+		/* Only multi-letter extensions are split by underscores */
+		if (strnlen(riscv_isa_ext[i].name, 2) != 1)
+			seq_puts(f, "_");
+
+		seq_printf(f, "%s", riscv_isa_ext[i].name);
 	}
-	print_isa_ext(f);
+
 	seq_puts(f, "\n");
 }
 
 static void print_mmu(struct seq_file *f)
 {
-	char sv_type[16];
+	const char *sv_type;
 
 #ifdef CONFIG_MMU
 #if defined(CONFIG_32BIT)
-	strncpy(sv_type, "sv32", 5);
+	sv_type = "sv32";
 #elif defined(CONFIG_64BIT)
 	if (pgtable_l5_enabled)
-		strncpy(sv_type, "sv57", 5);
+		sv_type = "sv57";
 	else if (pgtable_l4_enabled)
-		strncpy(sv_type, "sv48", 5);
+		sv_type = "sv48";
 	else
-		strncpy(sv_type, "sv39", 5);
+		sv_type = "sv39";
 #endif
 #else
-	strncpy(sv_type, "none", 5);
+	sv_type = "none";
 #endif /* CONFIG_MMU */
 	seq_printf(f, "mmu\t\t: %s\n", sv_type);
 }
···
 	unsigned long cpu_id = (unsigned long)v - 1;
 	struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id);
 	struct device_node *node;
-	const char *compat, *isa;
+	const char *compat;
 
 	seq_printf(m, "processor\t: %lu\n", cpu_id);
 	seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id));
+	print_isa(m);
+	print_mmu(m);
 
 	if (acpi_disabled) {
 		node = of_get_cpu_node(cpu_id, NULL);
-		if (!of_property_read_string(node, "riscv,isa", &isa))
-			print_isa(m, isa);
 
-		print_mmu(m);
 		if (!of_property_read_string(node, "compatible", &compat) &&
 		    strcmp(compat, "riscv"))
 			seq_printf(m, "uarch\t\t: %s\n", compat);
 
 		of_node_put(node);
-	} else {
-		if (!acpi_get_riscv_isa(NULL, cpu_id, &isa))
-			print_isa(m, isa);
-
-		print_mmu(m);
 	}
 
 	seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid);

arch/riscv/kernel/cpufeature.c

···
 	return true;
 }
 
-void __init riscv_fill_hwcap(void)
+#define __RISCV_ISA_EXT_DATA(_name, _id) {	\
+	.name = #_name,				\
+	.property = #_name,			\
+	.id = _id,				\
+}
+
+/*
+ * The canonical order of ISA extension names in the ISA string is defined in
+ * chapter 27 of the unprivileged specification.
+ *
+ * Ordinarily, for in-kernel data structures, this order is unimportant but
+ * isa_ext_arr defines the order of the ISA string in /proc/cpuinfo.
+ *
+ * The specification uses vague wording, such as should, when it comes to
+ * ordering, so for our purposes the following rules apply:
+ *
+ * 1. All multi-letter extensions must be separated from other extensions by an
+ *    underscore.
+ *
+ * 2. Additional standard extensions (starting with 'Z') must be sorted after
+ *    single-letter extensions and before any higher-privileged extensions.
+ *
+ * 3. The first letter following the 'Z' conventionally indicates the most
+ *    closely related alphabetical extension category, IMAFDQLCBKJTPVH.
+ *    If multiple 'Z' extensions are named, they must be ordered first by
+ *    category, then alphabetically within a category.
+ *
+ * 3. Standard supervisor-level extensions (starting with 'S') must be listed
+ *    after standard unprivileged extensions.  If multiple supervisor-level
+ *    extensions are listed, they must be ordered alphabetically.
+ *
+ * 4. Standard machine-level extensions (starting with 'Zxm') must be listed
+ *    after any lower-privileged, standard extensions.  If multiple
+ *    machine-level extensions are listed, they must be ordered
+ *    alphabetically.
+ *
+ * 5. Non-standard extensions (starting with 'X') must be listed after all
+ *    standard extensions. If multiple non-standard extensions are listed, they
+ *    must be ordered alphabetically.
+ *
+ * An example string following the order is:
+ *    rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux
+ *
+ * New entries to this struct should follow the ordering rules described above.
+ */
+const struct riscv_isa_ext_data riscv_isa_ext[] = {
+	__RISCV_ISA_EXT_DATA(i, RISCV_ISA_EXT_i),
+	__RISCV_ISA_EXT_DATA(m, RISCV_ISA_EXT_m),
+	__RISCV_ISA_EXT_DATA(a, RISCV_ISA_EXT_a),
+	__RISCV_ISA_EXT_DATA(f, RISCV_ISA_EXT_f),
+	__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),
+	__RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ),
+	__RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
+	__RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),
+	__RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI),
+	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
+	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
+	__RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA),
+	__RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB),
+	__RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS),
+	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
+	__RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
+	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
+	__RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC),
+	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
+	__RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),
+	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
+};
+
+const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext);
+
+static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct riscv_isainfo *isainfo,
+					  unsigned long *isa2hwcap, const char *isa)
+{
+	/*
+	 * For all possible cpus, we have already validated in
+	 * the boot process that they at least contain "rv" and
+	 * whichever of "32"/"64" this kernel supports, and so this
+	 * section can be skipped.
+	 */
+	isa += 4;
+
+	while (*isa) {
+		const char *ext = isa++;
+		const char *ext_end = isa;
+		bool ext_long = false, ext_err = false;
+
+		switch (*ext) {
+		case 's':
+			/*
+			 * Workaround for invalid single-letter 's' & 'u'(QEMU).
+			 * No need to set the bit in riscv_isa as 's' & 'u' are
+			 * not valid ISA extensions. It works until multi-letter
+			 * extension starting with "Su" appears.
+			 */
+			if (ext[-1] != '_' && ext[1] == 'u') {
+				++isa;
+				ext_err = true;
+				break;
+			}
+			fallthrough;
+		case 'S':
+		case 'x':
+		case 'X':
+		case 'z':
+		case 'Z':
+			/*
+			 * Before attempting to parse the extension itself, we find its end.
+			 * As multi-letter extensions must be split from other multi-letter
+			 * extensions with an "_", the end of a multi-letter extension will
+			 * either be the null character or the "_" at the start of the next
+			 * multi-letter extension.
+			 *
+			 * Next, as the extensions version is currently ignored, we
+			 * eliminate that portion. This is done by parsing backwards from
+			 * the end of the extension, removing any numbers. This may be a
+			 * major or minor number however, so the process is repeated if a
+			 * minor number was found.
+			 *
+			 * ext_end is intended to represent the first character *after* the
+			 * name portion of an extension, but will be decremented to the last
+			 * character itself while eliminating the extensions version number.
+			 * A simple re-increment solves this problem.
+			 */
+			ext_long = true;
+			for (; *isa && *isa != '_'; ++isa)
+				if (unlikely(!isalnum(*isa)))
+					ext_err = true;
+
+			ext_end = isa;
+			if (unlikely(ext_err))
+				break;
+
+			if (!isdigit(ext_end[-1]))
+				break;
+
+			while (isdigit(*--ext_end))
+				;
+
+			if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) {
+				++ext_end;
+				break;
+			}
+
+			while (isdigit(*--ext_end))
+				;
+
+			++ext_end;
+			break;
+		default:
+			/*
+			 * Things are a little easier for single-letter extensions, as they
+			 * are parsed forwards.
+			 *
+			 * After checking that our starting position is valid, we need to
+			 * ensure that, when isa was incremented at the start of the loop,
+			 * that it arrived at the start of the next extension.
+			 *
+			 * If we are already on a non-digit, there is nothing to do. Either
+			 * we have a multi-letter extension's _, or the start of an
+			 * extension.
+			 *
+			 * Otherwise we have found the current extension's major version
+			 * number. Parse past it, and a subsequent p/minor version number
+			 * if present. The `p` extension must not appear immediately after
+			 * a number, so there is no fear of missing it.
+			 *
+			 */
+			if (unlikely(!isalpha(*ext))) {
+				ext_err = true;
+				break;
+			}
+
+			if (!isdigit(*isa))
+				break;
+
+			while (isdigit(*++isa))
+				;
+
+			if (tolower(*isa) != 'p')
+				break;
+
+			if (!isdigit(*++isa)) {
+				--isa;
+				break;
+			}
+
+			while (isdigit(*++isa))
+				;
+
+			break;
+		}
+
+		/*
+		 * The parser expects that at the start of an iteration isa points to the
+		 * first character of the next extension. As we stop parsing an extension
+		 * on meeting a non-alphanumeric character, an extra increment is needed
+		 * where the succeeding extension is a multi-letter prefixed with an "_".
+		 */
+		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) {
+			int nr = tolower(*ext) - 'a';
+
+			if (riscv_isa_extension_check(nr)) {
+				*this_hwcap |= isa2hwcap[nr];
+				set_bit(nr, isainfo->isa);
+			}
+		} 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);
+		}
+#undef SET_ISA_EXT_MAP
+	}
+}
+
+static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap)
 {
 	struct device_node *node;
 	const char *isa;
-	char print_str[NUM_ALPHA_EXTS + 1];
-	int i, j, rc;
-	unsigned long isa2hwcap[26] = {0};
+	int rc;
 	struct acpi_table_header *rhct;
 	acpi_status status;
 	unsigned int cpu;
-
-	isa2hwcap['i' - 'a'] = COMPAT_HWCAP_ISA_I;
-	isa2hwcap['m' - 'a'] = COMPAT_HWCAP_ISA_M;
-	isa2hwcap['a' - 'a'] = COMPAT_HWCAP_ISA_A;
-	isa2hwcap['f' - 'a'] = COMPAT_HWCAP_ISA_F;
-	isa2hwcap['d' - 'a'] = COMPAT_HWCAP_ISA_D;
-	isa2hwcap['c' - 'a'] = COMPAT_HWCAP_ISA_C;
-	isa2hwcap['v' - 'a'] = COMPAT_HWCAP_ISA_V;
-
-	elf_hwcap = 0;
-
-	bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX);
 
 	if (!acpi_disabled) {
 		status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct);
···
 			}
 		}
 
-		/*
-		 * For all possible cpus, we have already validated in
-		 * the boot process that they at least contain "rv" and
-		 * whichever of "32"/"64" this kernel supports, and so this
-		 * section can be skipped.
-		 */
-		isa += 4;
-
-		while (*isa) {
-			const char *ext = isa++;
-			const char *ext_end = isa;
-			bool ext_long = false, ext_err = false;
-
-			switch (*ext) {
-			case 's':
-				/*
-				 * Workaround for invalid single-letter 's' & 'u'(QEMU).
-				 * No need to set the bit in riscv_isa as 's' & 'u' are
-				 * not valid ISA extensions. It works until multi-letter
-				 * extension starting with "Su" appears.
-				 */
-				if (ext[-1] != '_' && ext[1] == 'u') {
-					++isa;
-					ext_err = true;
-					break;
-				}
-				fallthrough;
-			case 'S':
-			case 'x':
-			case 'X':
-			case 'z':
-			case 'Z':
-				/*
-				 * Before attempting to parse the extension itself, we find its end.
-				 * As multi-letter extensions must be split from other multi-letter
-				 * extensions with an "_", the end of a multi-letter extension will
-				 * either be the null character or the "_" at the start of the next
-				 * multi-letter extension.
-				 *
-				 * Next, as the extensions version is currently ignored, we
-				 * eliminate that portion. This is done by parsing backwards from
-				 * the end of the extension, removing any numbers. This may be a
-				 * major or minor number however, so the process is repeated if a
-				 * minor number was found.
-				 *
-				 * ext_end is intended to represent the first character *after* the
-				 * name portion of an extension, but will be decremented to the last
-				 * character itself while eliminating the extensions version number.
-				 * A simple re-increment solves this problem.
-				 */
-				ext_long = true;
-				for (; *isa && *isa != '_'; ++isa)
-					if (unlikely(!isalnum(*isa)))
-						ext_err = true;
-
-				ext_end = isa;
-				if (unlikely(ext_err))
-					break;
-
-				if (!isdigit(ext_end[-1]))
-					break;
-
-				while (isdigit(*--ext_end))
-					;
-
-				if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) {
-					++ext_end;
-					break;
-				}
-
-				while (isdigit(*--ext_end))
-					;
-
-				++ext_end;
-				break;
-			default:
-				/*
-				 * Things are a little easier for single-letter extensions, as they
-				 * are parsed forwards.
-				 *
-				 * After checking that our starting position is valid, we need to
-				 * ensure that, when isa was incremented at the start of the loop,
-				 * that it arrived at the start of the next extension.
-				 *
-				 * If we are already on a non-digit, there is nothing to do. Either
-				 * we have a multi-letter extension's _, or the start of an
-				 * extension.
-				 *
-				 * Otherwise we have found the current extension's major version
-				 * number. Parse past it, and a subsequent p/minor version number
-				 * if present. The `p` extension must not appear immediately after
-				 * a number, so there is no fear of missing it.
-				 *
-				 */
-				if (unlikely(!isalpha(*ext))) {
-					ext_err = true;
-					break;
-				}
-
-				if (!isdigit(*isa))
-					break;
-
-				while (isdigit(*++isa))
-					;
-
-				if (tolower(*isa) != 'p')
-					break;
-
-				if (!isdigit(*++isa)) {
-					--isa;
-					break;
-				}
-
-				while (isdigit(*++isa))
-					;
-
-				break;
-			}
-
-			/*
-			 * The parser expects that at the start of an iteration isa points to the
-			 * first character of the next extension. As we stop parsing an extension
-			 * on meeting a non-alphanumeric character, an extra increment is needed
-			 * where the succeeding extension is a multi-letter prefixed with an "_".
-			 */
-			if (*isa == '_')
-				++isa;
-
-#define SET_ISA_EXT_MAP(name, bit)							\
-			do {								\
-				if ((ext_end - ext == sizeof(name) - 1) &&		\
-				     !strncasecmp(ext, name, sizeof(name) - 1) &&	\
-				     riscv_isa_extension_check(bit))			\
-					set_bit(bit, isainfo->isa);			\
-			} while (false)							\
-
-			if (unlikely(ext_err))
-				continue;
-			if (!ext_long) {
-				int nr = tolower(*ext) - 'a';
-
-				if (riscv_isa_extension_check(nr)) {
-					this_hwcap |= isa2hwcap[nr];
-					set_bit(nr, isainfo->isa);
-				}
-			} else {
-				/* sorted alphabetically */
-				SET_ISA_EXT_MAP("smaia", RISCV_ISA_EXT_SMAIA);
-				SET_ISA_EXT_MAP("ssaia", RISCV_ISA_EXT_SSAIA);
-				SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF);
-				SET_ISA_EXT_MAP("sstc", RISCV_ISA_EXT_SSTC);
-				SET_ISA_EXT_MAP("svinval", RISCV_ISA_EXT_SVINVAL);
-				SET_ISA_EXT_MAP("svnapot", RISCV_ISA_EXT_SVNAPOT);
-				SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT);
-				SET_ISA_EXT_MAP("zba", RISCV_ISA_EXT_ZBA);
-				SET_ISA_EXT_MAP("zbb", RISCV_ISA_EXT_ZBB);
-				SET_ISA_EXT_MAP("zbs", RISCV_ISA_EXT_ZBS);
-				SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM);
-				SET_ISA_EXT_MAP("zicboz", RISCV_ISA_EXT_ZICBOZ);
-				SET_ISA_EXT_MAP("zihintpause", RISCV_ISA_EXT_ZIHINTPAUSE);
-			}
-#undef SET_ISA_EXT_MAP
-		}
+		riscv_parse_isa_string(&this_hwcap, isainfo, isa2hwcap, isa);
 
 		/*
 		 * These ones were as they were part of the base ISA when the
···
 
 	if (!acpi_disabled && rhct)
 		acpi_put_table((struct acpi_table_header *)rhct);
+}
 
-	/* We don't support systems with F but without D, so mask those out
-	 * here. */
+static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		unsigned long this_hwcap = 0;
+		struct device_node *cpu_node;
+		struct riscv_isainfo *isainfo = &hart_isa[cpu];
+
+		cpu_node = of_cpu_device_node_get(cpu);
+		if (!cpu_node) {
+			pr_warn("Unable to find cpu node\n");
+			continue;
+		}
+
+		if (!of_property_present(cpu_node, "riscv,isa-extensions")) {
+			of_node_put(cpu_node);
+			continue;
+		}
+
+		for (int i = 0; i < riscv_isa_ext_count; i++) {
+			if (of_property_match_string(cpu_node, "riscv,isa-extensions",
+						     riscv_isa_ext[i].property) < 0)
+				continue;
+
+			if (!riscv_isa_extension_check(riscv_isa_ext[i].id))
+				continue;
+
+			/* 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];
+
+			set_bit(riscv_isa_ext[i].id, isainfo->isa);
+		}
+
+		of_node_put(cpu_node);
+
+		/*
+		 * All "okay" harts should have same isa. Set HWCAP based on
+		 * common capabilities of every "okay" hart, in case they don't.
+		 */
+		if (elf_hwcap)
+			elf_hwcap &= this_hwcap;
+		else
+			elf_hwcap = this_hwcap;
+
+		if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX))
+			bitmap_copy(riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX);
+		else
+			bitmap_and(riscv_isa, riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX);
+	}
+
+	if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX))
+		return -ENOENT;
+
+	return 0;
+}
+
+#ifdef CONFIG_RISCV_ISA_FALLBACK
+bool __initdata riscv_isa_fallback = true;
+#else
+bool __initdata riscv_isa_fallback;
+static int __init riscv_isa_fallback_setup(char *__unused)
+{
+	riscv_isa_fallback = true;
+	return 1;
+}
+early_param("riscv_isa_fallback", riscv_isa_fallback_setup);
+#endif
+
+void __init riscv_fill_hwcap(void)
+{
+	char print_str[NUM_ALPHA_EXTS + 1];
+	unsigned long isa2hwcap[26] = {0};
+	int i, j;
+
+	isa2hwcap['i' - 'a'] = COMPAT_HWCAP_ISA_I;
+	isa2hwcap['m' - 'a'] = COMPAT_HWCAP_ISA_M;
+	isa2hwcap['a' - 'a'] = COMPAT_HWCAP_ISA_A;
+	isa2hwcap['f' - 'a'] = COMPAT_HWCAP_ISA_F;
+	isa2hwcap['d' - 'a'] = COMPAT_HWCAP_ISA_D;
+	isa2hwcap['c' - 'a'] = COMPAT_HWCAP_ISA_C;
+	isa2hwcap['v' - 'a'] = COMPAT_HWCAP_ISA_V;
+
+	if (!acpi_disabled) {
+		riscv_fill_hwcap_from_isa_string(isa2hwcap);
+	} else {
+		int ret = riscv_fill_hwcap_from_ext_list(isa2hwcap);
+
+		if (ret && riscv_isa_fallback) {
+			pr_info("Falling back to deprecated \"riscv,isa\"\n");
+			riscv_fill_hwcap_from_isa_string(isa2hwcap);
+		}
+	}
+
+	/*
+	 * We don't support systems with F but without D, so mask those out
+	 * here.
+	 */
 	if ((elf_hwcap & COMPAT_HWCAP_ISA_F) && !(elf_hwcap & COMPAT_HWCAP_ISA_D)) {
 		pr_info("This kernel does not support systems with F but not D\n");
 		elf_hwcap &= ~COMPAT_HWCAP_ISA_F;

arch/riscv/kernel/head.S

···
 	blt a3, a4, clear_bss
 clear_bss_done:
 #endif
-	/* Save hart ID and DTB physical address */
-	mv s0, a0
-	mv s1, a1
-
 	la a2, boot_cpu_hartid
 	XIP_FIXUP_OFFSET a2
 	REG_S a0, (a2)
···
 	la a0, __dtb_start
 	XIP_FIXUP_OFFSET a0
 #else
-	mv a0, s1
+	mv a0, a1
 #endif /* CONFIG_BUILTIN_DTB */
 	call setup_vm
 #ifdef CONFIG_MMU

arch/riscv/kernel/mcount.S

···
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/asm.h>
 #include <asm/csr.h>
 #include <asm/unistd.h>
···
 	addi	sp, sp, 4*SZREG
 	.endm
 
-ENTRY(ftrace_stub)
+SYM_TYPED_FUNC_START(ftrace_stub)
 #ifdef CONFIG_DYNAMIC_FTRACE
        .global MCOUNT_NAME
        .set    MCOUNT_NAME, ftrace_stub
 #endif
 	ret
-ENDPROC(ftrace_stub)
+SYM_FUNC_END(ftrace_stub)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
+SYM_TYPED_FUNC_START(ftrace_stub_graph)
+	ret
+SYM_FUNC_END(ftrace_stub_graph)
+
 ENTRY(return_to_handler)
 /*
  * On implementing the frame point test, the ideal way is to compare the

arch/riscv/kernel/probes/decode-insn.c

···
 	 * TODO: the REJECTED ones below need to be implemented
 	 */
 #ifdef CONFIG_RISCV_ISA_C
-	RISCV_INSN_REJECTED(c_j,		insn);
-	RISCV_INSN_REJECTED(c_jr,		insn);
 	RISCV_INSN_REJECTED(c_jal,		insn);
-	RISCV_INSN_REJECTED(c_jalr,		insn);
-	RISCV_INSN_REJECTED(c_beqz,		insn);
-	RISCV_INSN_REJECTED(c_bnez,		insn);
 	RISCV_INSN_REJECTED(c_ebreak,		insn);
+
+	RISCV_INSN_SET_SIMULATE(c_j,		insn);
+	RISCV_INSN_SET_SIMULATE(c_jr,		insn);
+	RISCV_INSN_SET_SIMULATE(c_jalr,		insn);
+	RISCV_INSN_SET_SIMULATE(c_beqz,		insn);
+	RISCV_INSN_SET_SIMULATE(c_bnez,		insn);
 #endif
 
 	RISCV_INSN_SET_SIMULATE(jal,		insn);

arch/riscv/kernel/probes/simulate-insn.c

···
 
 	return true;
 }
+
+bool __kprobes simulate_c_j(u32 opcode, unsigned long addr, struct pt_regs *regs)
+{
+	/*
+	 *  15    13 12                            2 1      0
+	 * | funct3 | offset[11|4|9:8|10|6|7|3:1|5] | opcode |
+	 *     3                   11                    2
+	 */
+
+	s32 offset;
+
+	offset  = ((opcode >> 3)  & 0x7) << 1;
+	offset |= ((opcode >> 11) & 0x1) << 4;
+	offset |= ((opcode >> 2)  & 0x1) << 5;
+	offset |= ((opcode >> 7)  & 0x1) << 6;
+	offset |= ((opcode >> 6)  & 0x1) << 7;
+	offset |= ((opcode >> 9)  & 0x3) << 8;
+	offset |= ((opcode >> 8)  & 0x1) << 10;
+	offset |= ((opcode >> 12) & 0x1) << 11;
+
+	instruction_pointer_set(regs, addr + sign_extend32(offset, 11));
+
+	return true;
+}
+
+static bool __kprobes simulate_c_jr_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs,
+					 bool is_jalr)
+{
+	/*
+	 *  15    12 11  7 6   2 1  0
+	 * | funct4 | rs1 | rs2 | op |
+	 *     4       5     5    2
+	 */
+
+	unsigned long jump_addr;
+
+	u32 rs1 = (opcode >> 7) & 0x1f;
+
+	if (rs1 == 0) /* C.JR is only valid when rs1 != x0 */
+		return false;
+
+	if (!rv_insn_reg_get_val(regs, rs1, &jump_addr))
+		return false;
+
+	if (is_jalr && !rv_insn_reg_set_val(regs, 1, addr + 2))
+		return false;
+
+	instruction_pointer_set(regs, jump_addr);
+
+	return true;
+}
+
+bool __kprobes simulate_c_jr(u32 opcode, unsigned long addr, struct pt_regs *regs)
+{
+	return simulate_c_jr_jalr(opcode, addr, regs, false);
+}
+
+bool __kprobes simulate_c_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs)
+{
+	return simulate_c_jr_jalr(opcode, addr, regs, true);
+}
+
+static bool __kprobes simulate_c_bnez_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs,
+					   bool is_bnez)
+{
+	/*
+	 *  15    13 12           10 9    7 6                 2 1  0
+	 * | funct3 | offset[8|4:3] | rs1' | offset[7:6|2:1|5] | op |
+	 *     3            3          3             5           2
+	 */
+
+	s32 offset;
+	u32 rs1;
+	unsigned long rs1_val;
+
+	rs1 = 0x8 | ((opcode >> 7) & 0x7);
+
+	if (!rv_insn_reg_get_val(regs, rs1, &rs1_val))
+		return false;
+
+	if ((rs1_val != 0 && is_bnez) || (rs1_val == 0 && !is_bnez)) {
+		offset =  ((opcode >> 3)  & 0x3) << 1;
+		offset |= ((opcode >> 10) & 0x3) << 3;
+		offset |= ((opcode >> 2)  & 0x1) << 5;
+		offset |= ((opcode >> 5)  & 0x3) << 6;
+		offset |= ((opcode >> 12) & 0x1) << 8;
+		offset = sign_extend32(offset, 8);
+	} else {
+		offset = 2;
+	}
+
+	instruction_pointer_set(regs, addr + offset);
+
+	return true;
+}
+
+bool __kprobes simulate_c_bnez(u32 opcode, unsigned long addr, struct pt_regs *regs)
+{
+	return simulate_c_bnez_beqz(opcode, addr, regs, true);
+}
+
+bool __kprobes simulate_c_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs)
+{
+	return simulate_c_bnez_beqz(opcode, addr, regs, false);
+}

arch/riscv/kernel/probes/simulate-insn.h

···
 bool simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *regs);
 bool simulate_jal(u32 opcode, unsigned long addr, struct pt_regs *regs);
 bool simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs);
+bool simulate_c_j(u32 opcode, unsigned long addr, struct pt_regs *regs);
+bool simulate_c_jr(u32 opcode, unsigned long addr, struct pt_regs *regs);
+bool simulate_c_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs);
+bool simulate_c_bnez(u32 opcode, unsigned long addr, struct pt_regs *regs);
+bool simulate_c_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs);
 
 #endif /* _RISCV_KERNEL_PROBES_SIMULATE_INSN_H */

arch/riscv/kernel/setup.c

···
 		if (ret < 0)
 			goto error;
 	}
+	if (crashk_low_res.start != crashk_low_res.end) {
+		ret = add_resource(&iomem_resource, &crashk_low_res);
+		if (ret < 0)
+			goto error;
+	}
 #endif
 
 #ifdef CONFIG_CRASH_DUMP
···
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) &&
 	    riscv_isa_extension_available(NULL, ZICBOM))
 		riscv_noncoherent_supported();
+	riscv_set_dma_cache_alignment();
 }
 
 static int __init topology_init(void)

arch/riscv/kernel/suspend_entry.S

···
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/assembler.h>
···
 	ret
 END(__cpu_suspend_enter)
 
-ENTRY(__cpu_resume_enter)
+SYM_TYPED_FUNC_START(__cpu_resume_enter)
 	/* Load the global pointer */
 	.option push
 	.option norelax
···
 
 	/* Return to C code */
 	ret
-END(__cpu_resume_enter)
+SYM_FUNC_END(__cpu_resume_enter)

arch/riscv/kernel/sys_riscv.c

···
 	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)
+{
+	return -ENOSYS;
+}

arch/riscv/kernel/syscall_table.c

···
 #include <asm/syscall.h>
 
 #undef __SYSCALL
-#define __SYSCALL(nr, call)	[nr] = (call),
+#define __SYSCALL(nr, call)	asmlinkage long __riscv_##call(const struct pt_regs *);
+#include <asm/unistd.h>
+
+#undef __SYSCALL
+#define __SYSCALL(nr, call)	[nr] = __riscv_##call,
 
 void * const sys_call_table[__NR_syscalls] = {
-	[0 ... __NR_syscalls - 1] = sys_ni_syscall,
+	[0 ... __NR_syscalls - 1] = __riscv_sys_ni_syscall,
 #include <asm/unistd.h>
 };

arch/riscv/kernel/traps.c

···
 
 #include <asm/asm-prototypes.h>
 #include <asm/bug.h>
+#include <asm/cfi.h>
 #include <asm/csr.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
···
 								== NOTIFY_STOP)
 		return;
 #endif
-	else if (report_bug(regs->epc, regs) == BUG_TRAP_TYPE_WARN)
+	else if (report_bug(regs->epc, regs) == BUG_TRAP_TYPE_WARN ||
+		 handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN)
 		regs->epc += get_break_insn_length(regs->epc);
 	else
 		die(regs, "Kernel BUG");

arch/riscv/mm/context.c

···
 	lockdep_assert_held(&context_lock);
 
 	/* Update the list of reserved ASIDs and the ASID bitmap. */
-	bitmap_clear(context_asid_map, 0, num_asids);
+	bitmap_zero(context_asid_map, num_asids);
 
 	/* Mark already active ASIDs as used */
 	for_each_possible_cpu(i) {

arch/riscv/mm/dma-noncoherent.c

···
 #include <asm/cacheflush.h>
 
 static bool noncoherent_supported __ro_after_init;
+int dma_cache_alignment __ro_after_init = ARCH_DMA_MINALIGN;
+EXPORT_SYMBOL_GPL(dma_cache_alignment);
 
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 			      enum dma_data_direction dir)
···
 	WARN(!riscv_cbom_block_size,
 	     "Non-coherent DMA support enabled without a block size\n");
 	noncoherent_supported = true;
+}
+
+void __init riscv_set_dma_cache_alignment(void)
+{
+	if (!noncoherent_supported)
+		dma_cache_alignment = 1;
 }

arch/riscv/mm/init.c

···
 }
 #endif /* CONFIG_MMU */
 
+/* Reserve 128M low memory by default for swiotlb buffer */
+#define DEFAULT_CRASH_KERNEL_LOW_SIZE	(128UL << 20)
+
+static int __init reserve_crashkernel_low(unsigned long long low_size)
+{
+	unsigned long long low_base;
+
+	low_base = memblock_phys_alloc_range(low_size, PMD_SIZE, 0, dma32_phys_limit);
+	if (!low_base) {
+		pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size);
+		return -ENOMEM;
+	}
+
+	pr_info("crashkernel low memory reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
+		low_base, low_base + low_size, low_size >> 20);
+
+	crashk_low_res.start = low_base;
+	crashk_low_res.end = low_base + low_size - 1;
+
+	return 0;
+}
+
 /*
  * reserve_crashkernel() - reserves memory for crash kernel
  *
···
 {
 	unsigned long long crash_base = 0;
 	unsigned long long crash_size = 0;
+	unsigned long long crash_low_size = 0;
 	unsigned long search_start = memblock_start_of_DRAM();
-	unsigned long search_end = memblock_end_of_DRAM();
+	unsigned long search_end = (unsigned long)dma32_phys_limit;
+	char *cmdline = boot_command_line;
+	bool fixed_base = false;
+	bool high = false;
 
 	int ret = 0;
 
···
 		return;
 	}
 
-	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
 				&crash_size, &crash_base);
-	if (ret || !crash_size)
+	if (ret == -ENOENT) {
+		/* Fallback to crashkernel=X,[high,low] */
+		ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base);
+		if (ret || !crash_size)
+			return;
+
+		/*
+		 * crashkernel=Y,low is valid only when crashkernel=X,high
+		 * is passed.
+		 */
+		ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base);
+		if (ret == -ENOENT)
+			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
+		else if (ret)
+			return;
+
+		search_start = (unsigned long)dma32_phys_limit;
+		search_end = memblock_end_of_DRAM();
+		high = true;
+	} else if (ret || !crash_size) {
+		/* Invalid argument value specified */
 		return;
+	}
 
 	crash_size = PAGE_ALIGN(crash_size);
 
 	if (crash_base) {
+		fixed_base = true;
 		search_start = crash_base;
 		search_end = crash_base + crash_size;
 	}
···
 	 * swiotlb can work on the crash kernel.
 	 */
 	crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
-					       search_start,
-					       min(search_end, (unsigned long)(SZ_4G - 1)));
+					       search_start, search_end);
 	if (crash_base == 0) {
-		/* Try again without restricting region to 32bit addressible memory */
+		/*
+		 * For crashkernel=size[KMG]@offset[KMG], print out failure
+		 * message if can't reserve the specified region.
+		 */
+		if (fixed_base) {
+			pr_warn("crashkernel: allocating failed with given size@offset\n");
+			return;
+		}
+
+		if (high) {
+			/*
+			 * For crashkernel=size[KMG],high, if the first attempt was
+			 * for high memory, fall back to low memory.
+			 */
+			search_start = memblock_start_of_DRAM();
+			search_end = (unsigned long)dma32_phys_limit;
+		} else {
+			/*
+			 * For crashkernel=size[KMG], if the first attempt was for
+			 * low memory, fall back to high memory, the minimum required
+			 * low memory will be reserved later.
+			 */
+			search_start = (unsigned long)dma32_phys_limit;
+			search_end = memblock_end_of_DRAM();
+			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
+		}
+
 		crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
-						search_start, search_end);
+						       search_start, search_end);
 		if (crash_base == 0) {
 			pr_warn("crashkernel: couldn't allocate %lldKB\n",
 				crash_size >> 10);
 			return;
 		}
+	}
+
+	if ((crash_base >= dma32_phys_limit) && crash_low_size &&
+	     reserve_crashkernel_low(crash_low_size)) {
+		memblock_phys_free(crash_base, crash_size);
+		return;
 	}
 
 	pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n",

arch/riscv/mm/kasan_init.c

···
  * region is not and then we have to go down to the PUD level.
  */
 
-pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
-p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss;
-pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss;
+static pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
+static p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss;
+static pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss;
 
 static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned long end)
 {
···
 	kasan_shallow_populate_pgd(vaddr, vend);
 }
 
-static void create_tmp_mapping(void)
+static void __init create_tmp_mapping(void)
 {
 	void *ptr;
 	p4d_t *base_p4d;

arch/riscv/purgatory/Makefile

···
 PURGATORY_CFLAGS_REMOVE		+= -fstack-protector-strong
 endif
 
+ifdef CONFIG_CFI_CLANG
+PURGATORY_CFLAGS_REMOVE		+= $(CC_FLAGS_CFI)
+endif
+
 CFLAGS_REMOVE_purgatory.o	+= $(PURGATORY_CFLAGS_REMOVE)
 CFLAGS_purgatory.o		+= $(PURGATORY_CFLAGS)
 

drivers/perf/riscv_pmu.c

···
 #include <linux/perf/riscv_pmu.h>
 #include <linux/printk.h>
 #include <linux/smp.h>
+#include <linux/sched_clock.h>
 
 #include <asm/sbi.h>
+
+static bool riscv_perf_user_access(struct perf_event *event)
+{
+	return ((event->attr.type == PERF_TYPE_HARDWARE) ||
+		(event->attr.type == PERF_TYPE_HW_CACHE) ||
+		(event->attr.type == PERF_TYPE_RAW)) &&
+		!!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT);
+}
+
+void arch_perf_update_userpage(struct perf_event *event,
+			       struct perf_event_mmap_page *userpg, u64 now)
+{
+	struct clock_read_data *rd;
+	unsigned int seq;
+	u64 ns;
+
+	userpg->cap_user_time = 0;
+	userpg->cap_user_time_zero = 0;
+	userpg->cap_user_time_short = 0;
+	userpg->cap_user_rdpmc = riscv_perf_user_access(event);
+
+#ifdef CONFIG_RISCV_PMU
+	/*
+	 * The counters are 64-bit but the priv spec doesn't mandate all the
+	 * bits to be implemented: that's why, counter width can vary based on
+	 * the cpu vendor.
+	 */
+	if (userpg->cap_user_rdpmc)
+		userpg->pmc_width = to_riscv_pmu(event->pmu)->ctr_get_width(event->hw.idx) + 1;
+#endif
+
+	do {
+		rd = sched_clock_read_begin(&seq);
+
+		userpg->time_mult = rd->mult;
+		userpg->time_shift = rd->shift;
+		userpg->time_zero = rd->epoch_ns;
+		userpg->time_cycles = rd->epoch_cyc;
+		userpg->time_mask = rd->sched_clock_mask;
+
+		/*
+		 * Subtract the cycle base, such that software that
+		 * doesn't know about cap_user_time_short still 'works'
+		 * assuming no wraps.
+		 */
+		ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift);
+		userpg->time_zero -= ns;
+
+	} while (sched_clock_read_retry(seq));
+
+	userpg->time_offset = userpg->time_zero - now;
+
+	/*
+	 * time_shift is not expected to be greater than 31 due to
+	 * the original published conversion algorithm shifting a
+	 * 32-bit value (now specifies a 64-bit value) - refer
+	 * perf_event_mmap_page documentation in perf_event.h.
+	 */
+	if (userpg->time_shift == 32) {
+		userpg->time_shift = 31;
+		userpg->time_mult >>= 1;
+	}
+
+	/*
+	 * Internal timekeeping for enabled/running/stopped times
+	 * is always computed with the sched_clock.
+	 */
+	userpg->cap_user_time = 1;
+	userpg->cap_user_time_zero = 1;
+	userpg->cap_user_time_short = 1;
+}
 
 static unsigned long csr_read_num(int csr_num)
 {
···
 
 	local64_set(&hwc->prev_count, (u64)-left);
 
+	perf_event_update_userpage(event);
+
 	return overflow;
 }
 
···
 	hwc->idx = -1;
 	hwc->event_base = mapped_event;
 
+	if (rvpmu->event_init)
+		rvpmu->event_init(event);
+
 	if (!is_sampling_event(event)) {
 		/*
 		 * For non-sampling runs, limit the sample_period to half
···
 	}
 
 	return 0;
+}
+
+static int riscv_pmu_event_idx(struct perf_event *event)
+{
+	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
+
+	if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT))
+		return 0;
+
+	if (rvpmu->csr_index)
+		return rvpmu->csr_index(event) + 1;
+
+	return 0;
+}
+
+static void riscv_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
+{
+	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
+
+	if (rvpmu->event_mapped) {
+		rvpmu->event_mapped(event, mm);
+		perf_event_update_userpage(event);
+	}
+}
+
+static void riscv_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm)
+{
+	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
+
+	if (rvpmu->event_unmapped) {
+		rvpmu->event_unmapped(event, mm);
+		perf_event_update_userpage(event);
+	}
 }
 
 struct riscv_pmu *riscv_pmu_alloc(void)
···
 	}
 	pmu->pmu = (struct pmu) {
 		.event_init	= riscv_pmu_event_init,
+		.event_mapped	= riscv_pmu_event_mapped,
+		.event_unmapped	= riscv_pmu_event_unmapped,
+		.event_idx	= riscv_pmu_event_idx,
 		.add		= riscv_pmu_add,
 		.del		= riscv_pmu_del,
 		.start		= riscv_pmu_start,

drivers/perf/riscv_pmu_legacy.c

···
 #include <linux/platform_device.h>
 
 #define RISCV_PMU_LEGACY_CYCLE		0
-#define RISCV_PMU_LEGACY_INSTRET	1
+#define RISCV_PMU_LEGACY_INSTRET	2
 
 static bool pmu_init_done;
 
···
 	local64_set(&hwc->prev_count, initial_val);
 }
 
+static uint8_t pmu_legacy_csr_index(struct perf_event *event)
+{
+	return event->hw.idx;
+}
+
+static void pmu_legacy_event_mapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES &&
+	    event->attr.config != PERF_COUNT_HW_INSTRUCTIONS)
+		return;
+
+	event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT;
+}
+
+static void pmu_legacy_event_unmapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES &&
+	    event->attr.config != PERF_COUNT_HW_INSTRUCTIONS)
+		return;
+
+	event->hw.flags &= ~PERF_EVENT_FLAG_USER_READ_CNT;
+}
+
 /*
  * This is just a simple implementation to allow legacy implementations
  * compatible with new RISC-V PMU driver framework.
···
 	pmu->ctr_get_width = NULL;
 	pmu->ctr_clear_idx = NULL;
 	pmu->ctr_read = pmu_legacy_read_ctr;
+	pmu->event_mapped = pmu_legacy_event_mapped;
+	pmu->event_unmapped = pmu_legacy_event_unmapped;
+	pmu->csr_index = pmu_legacy_csr_index;
 
 	perf_pmu_register(&pmu->pmu, "cpu", PERF_TYPE_RAW);
 }

drivers/perf/riscv_pmu_sbi.c

···
 #include <asm/sbi.h>
 #include <asm/hwcap.h>
 
+#define SYSCTL_NO_USER_ACCESS	0
+#define SYSCTL_USER_ACCESS	1
+#define SYSCTL_LEGACY		2
+
+#define PERF_EVENT_FLAG_NO_USER_ACCESS	BIT(SYSCTL_NO_USER_ACCESS)
+#define PERF_EVENT_FLAG_USER_ACCESS	BIT(SYSCTL_USER_ACCESS)
+#define PERF_EVENT_FLAG_LEGACY		BIT(SYSCTL_LEGACY)
+
 PMU_FORMAT_ATTR(event, "config:0-47");
 PMU_FORMAT_ATTR(firmware, "config:63");
 
···
 	&riscv_pmu_format_group,
 	NULL,
 };
+
+/* Allow user mode access by default */
+static int sysctl_perf_user_access __read_mostly = SYSCTL_USER_ACCESS;
 
 /*
  * RISC-V doesn't have heterogeneous harts yet. This need to be part of
···
 }
 EXPORT_SYMBOL_GPL(riscv_pmu_get_hpm_info);
 
+static uint8_t pmu_sbi_csr_index(struct perf_event *event)
+{
+	return pmu_ctr_list[event->hw.idx].csr - CSR_CYCLE;
+}
+
 static unsigned long pmu_sbi_get_filter_flags(struct perf_event *event)
 {
 	unsigned long cflags = 0;
···
 	struct cpu_hw_events *cpuc = this_cpu_ptr(rvpmu->hw_events);
 	struct sbiret ret;
 	int idx;
-	uint64_t cbase = 0;
+	uint64_t cbase = 0, cmask = rvpmu->cmask;
 	unsigned long cflags = 0;
 
 	cflags = pmu_sbi_get_filter_flags(event);
+
+	/*
+	 * In legacy mode, we have to force the fixed counters for those events
+	 * but not in the user access mode as we want to use the other counters
+	 * that support sampling/filtering.
+	 */
+	if (hwc->flags & PERF_EVENT_FLAG_LEGACY) {
+		if (event->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
+			cflags |= SBI_PMU_CFG_FLAG_SKIP_MATCH;
+			cmask = 1;
+		} else if (event->attr.config == PERF_COUNT_HW_INSTRUCTIONS) {
+			cflags |= SBI_PMU_CFG_FLAG_SKIP_MATCH;
+			cmask = 1UL << (CSR_INSTRET - CSR_CYCLE);
+		}
+	}
+
 	/* retrieve the available counter index */
 #if defined(CONFIG_32BIT)
 	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase,
-			rvpmu->cmask, cflags, hwc->event_base, hwc->config,
+			cmask, cflags, hwc->event_base, hwc->config,
 			hwc->config >> 32);
 #else
 	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase,
-			rvpmu->cmask, cflags, hwc->event_base, hwc->config, 0);
+			cmask, cflags, hwc->event_base, hwc->config, 0);
 #endif
 	if (ret.error) {
 		pr_debug("Not able to find a counter for event %lx config %llx\n",
···
 	return val;
 }
 
+static void pmu_sbi_set_scounteren(void *arg)
+{
+	struct perf_event *event = (struct perf_event *)arg;
+
+	csr_write(CSR_SCOUNTEREN,
+		  csr_read(CSR_SCOUNTEREN) | (1 << pmu_sbi_csr_index(event)));
+}
+
+static void pmu_sbi_reset_scounteren(void *arg)
+{
+	struct perf_event *event = (struct perf_event *)arg;
+
+	csr_write(CSR_SCOUNTEREN,
+		  csr_read(CSR_SCOUNTEREN) & ~(1 << pmu_sbi_csr_index(event)));
+}
+
 static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival)
 {
 	struct sbiret ret;
···
 	if (ret.error && (ret.error != SBI_ERR_ALREADY_STARTED))
 		pr_err("Starting counter idx %d failed with error %d\n",
 			hwc->idx, sbi_err_map_linux_errno(ret.error));
+
+	if ((hwc->flags & PERF_EVENT_FLAG_USER_ACCESS) &&
+	    (hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT))
+		pmu_sbi_set_scounteren((void *)event);
 }
 
 static void pmu_sbi_ctr_stop(struct perf_event *event, unsigned long flag)
 {
 	struct sbiret ret;
 	struct hw_perf_event *hwc = &event->hw;
+
+	if ((hwc->flags & PERF_EVENT_FLAG_USER_ACCESS) &&
+	    (hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT))
+		pmu_sbi_reset_scounteren((void *)event);
 
 	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, hwc->idx, 1, flag, 0, 0, 0);
 	if (ret.error && (ret.error != SBI_ERR_ALREADY_STOPPED) &&
···
 	struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events);
 
 	/*
-	 * Enable the access for CYCLE, TIME, and INSTRET CSRs from userspace,
-	 * as is necessary to maintain uABI compatibility.
+	 * We keep enabling userspace access to CYCLE, TIME and INSTRET via the
+	 * legacy option but that will be removed in the future.
 	 */
-	csr_write(CSR_SCOUNTEREN, 0x7);
+	if (sysctl_perf_user_access == SYSCTL_LEGACY)
+		csr_write(CSR_SCOUNTEREN, 0x7);
+	else
+		csr_write(CSR_SCOUNTEREN, 0x2);
 
 	/* Stop all the counters so that they can be enabled from perf */
 	pmu_sbi_stop_all(pmu);
···
 	cpuhp_state_remove_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node);
 }
 
+static void pmu_sbi_event_init(struct perf_event *event)
+{
+	/*
+	 * The permissions are set at event_init so that we do not depend
+	 * on the sysctl value that can change.
+	 */
+	if (sysctl_perf_user_access == SYSCTL_NO_USER_ACCESS)
+		event->hw.flags |= PERF_EVENT_FLAG_NO_USER_ACCESS;
+	else if (sysctl_perf_user_access == SYSCTL_USER_ACCESS)
+		event->hw.flags |= PERF_EVENT_FLAG_USER_ACCESS;
+	else
+		event->hw.flags |= PERF_EVENT_FLAG_LEGACY;
+}
+
+static void pmu_sbi_event_mapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (event->hw.flags & PERF_EVENT_FLAG_NO_USER_ACCESS)
+		return;
+
+	if (event->hw.flags & PERF_EVENT_FLAG_LEGACY) {
+		if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES &&
+		    event->attr.config != PERF_COUNT_HW_INSTRUCTIONS) {
+			return;
+		}
+	}
+
+	/*
+	 * The user mmapped the event to directly access it: this is where
+	 * we determine based on sysctl_perf_user_access if we grant userspace
+	 * the direct access to this event. That means that within the same
+	 * task, some events may be directly accessible and some other may not,
+	 * if the user changes the value of sysctl_perf_user_accesss in the
+	 * meantime.
+	 */
+
+	event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT;
+
+	/*
+	 * We must enable userspace access *before* advertising in the user page
+	 * that it is possible to do so to avoid any race.
+	 * And we must notify all cpus here because threads that currently run
+	 * on other cpus will try to directly access the counter too without
+	 * calling pmu_sbi_ctr_start.
+	 */
+	if (event->hw.flags & PERF_EVENT_FLAG_USER_ACCESS)
+		on_each_cpu_mask(mm_cpumask(mm),
+				 pmu_sbi_set_scounteren, (void *)event, 1);
+}
+
+static void pmu_sbi_event_unmapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (event->hw.flags & PERF_EVENT_FLAG_NO_USER_ACCESS)
+		return;
+
+	if (event->hw.flags & PERF_EVENT_FLAG_LEGACY) {
+		if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES &&
+		    event->attr.config != PERF_COUNT_HW_INSTRUCTIONS) {
+			return;
+		}
+	}
+
+	/*
+	 * Here we can directly remove user access since the user does not have
+	 * access to the user page anymore so we avoid the racy window where the
+	 * user could have read cap_user_rdpmc to true right before we disable
+	 * it.
+	 */
+	event->hw.flags &= ~PERF_EVENT_FLAG_USER_READ_CNT;
+
+	if (event->hw.flags & PERF_EVENT_FLAG_USER_ACCESS)
+		on_each_cpu_mask(mm_cpumask(mm),
+				 pmu_sbi_reset_scounteren, (void *)event, 1);
+}
+
+static void riscv_pmu_update_counter_access(void *info)
+{
+	if (sysctl_perf_user_access == SYSCTL_LEGACY)
+		csr_write(CSR_SCOUNTEREN, 0x7);
+	else
+		csr_write(CSR_SCOUNTEREN, 0x2);
+}
+
+static int riscv_pmu_proc_user_access_handler(struct ctl_table *table,
+					      int write, void *buffer,
+					      size_t *lenp, loff_t *ppos)
+{
+	int prev = sysctl_perf_user_access;
+	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+	/*
+	 * Test against the previous value since we clear SCOUNTEREN when
+	 * sysctl_perf_user_access is set to SYSCTL_USER_ACCESS, but we should
+	 * not do that if that was already the case.
+	 */
+	if (ret || !write || prev == sysctl_perf_user_access)
+		return ret;
+
+	on_each_cpu(riscv_pmu_update_counter_access, NULL, 1);
+
+	return 0;
+}
+
+static struct ctl_table sbi_pmu_sysctl_table[] = {
+	{
+		.procname       = "perf_user_access",
+		.data		= &sysctl_perf_user_access,
+		.maxlen		= sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler	= riscv_pmu_proc_user_access_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_TWO,
+	},
+	{ }
+};
+
 static int pmu_sbi_device_probe(struct platform_device *pdev)
 {
 	struct riscv_pmu *pmu = NULL;
···
 	pmu->ctr_get_width = pmu_sbi_ctr_get_width;
 	pmu->ctr_clear_idx = pmu_sbi_ctr_clear_idx;
 	pmu->ctr_read = pmu_sbi_ctr_read;
+	pmu->event_init = pmu_sbi_event_init;
+	pmu->event_mapped = pmu_sbi_event_mapped;
+	pmu->event_unmapped = pmu_sbi_event_unmapped;
+	pmu->csr_index = pmu_sbi_csr_index;
 
 	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node);
 	if (ret)
···
 	ret = perf_pmu_register(&pmu->pmu, "cpu", PERF_TYPE_RAW);
 	if (ret)
 		goto out_unregister;
+
+	register_sysctl("kernel", sbi_pmu_sysctl_table);
 
 	return 0;
 
···
 static struct platform_driver pmu_sbi_driver = {
 	.probe		= pmu_sbi_device_probe,
 	.driver		= {
-		.name	= RISCV_PMU_PDEV_NAME,
+		.name	= RISCV_PMU_SBI_PDEV_NAME,
 	},
 };
 
···
 	if (ret)
 		return ret;
 
-	pdev = platform_device_register_simple(RISCV_PMU_PDEV_NAME, -1, NULL, 0);
+	pdev = platform_device_register_simple(RISCV_PMU_SBI_PDEV_NAME, -1, NULL, 0);
 	if (IS_ERR(pdev)) {
 		platform_driver_unregister(&pmu_sbi_driver);
 		return PTR_ERR(pdev);

fs/Kconfig.binfmt

···
 config BINFMT_ELF_FDPIC
 	bool "Kernel support for FDPIC ELF binaries"
 	default y if !BINFMT_ELF
-	depends on ARM || ((M68K || SUPERH || XTENSA) && !MMU)
+	depends on ARM || ((M68K || RISCV || SUPERH || XTENSA) && !MMU)
 	select ELFCORE
 	help
 	  ELF FDPIC binaries are based on ELF, but allow the individual load

fs/binfmt_elf_fdpic.c

···
 static int elf_fdpic_fetch_phdrs(struct elf_fdpic_params *params,
 				 struct file *file)
 {
-	struct elf32_phdr *phdr;
+	struct elf_phdr *phdr;
 	unsigned long size;
 	int retval, loop;
 	loff_t pos = params->hdr.e_phoff;
···
 	sp &= ~7UL;
 
 	/* stack the load map(s) */
-	len = sizeof(struct elf32_fdpic_loadmap);
-	len += sizeof(struct elf32_fdpic_loadseg) * exec_params->loadmap->nsegs;
+	len = sizeof(struct elf_fdpic_loadmap);
+	len += sizeof(struct elf_fdpic_loadseg) * exec_params->loadmap->nsegs;
 	sp = (sp - len) & ~7UL;
 	exec_params->map_addr = sp;
 
···
 	current->mm->context.exec_fdpic_loadmap = (unsigned long) sp;
 
 	if (interp_params->loadmap) {
-		len = sizeof(struct elf32_fdpic_loadmap);
-		len += sizeof(struct elf32_fdpic_loadseg) *
+		len = sizeof(struct elf_fdpic_loadmap);
+		len += sizeof(struct elf_fdpic_loadseg) *
 			interp_params->loadmap->nsegs;
 		sp = (sp - len) & ~7UL;
 		interp_params->map_addr = sp;
···
 			      struct mm_struct *mm,
 			      const char *what)
 {
-	struct elf32_fdpic_loadmap *loadmap;
+	struct elf_fdpic_loadmap *loadmap;
 #ifdef CONFIG_MMU
-	struct elf32_fdpic_loadseg *mseg;
+	struct elf_fdpic_loadseg *mseg;
 	unsigned long load_addr;
 #endif
-	struct elf32_fdpic_loadseg *seg;
-	struct elf32_phdr *phdr;
+	struct elf_fdpic_loadseg *seg;
+	struct elf_phdr *phdr;
 	unsigned nloads, tmp;
 	unsigned long stop;
 	int loop, ret;
···
 
 	params->loadmap = loadmap;
 
-	loadmap->version = ELF32_FDPIC_LOADMAP_VERSION;
+	loadmap->version = ELF_FDPIC_LOADMAP_VERSION;
 	loadmap->nsegs = nloads;
 
 	/* map the requested LOADs into the memory space */
···
 			if (phdr->p_vaddr >= seg->p_vaddr &&
 			    phdr->p_vaddr + phdr->p_memsz <=
 			    seg->p_vaddr + seg->p_memsz) {
-				Elf32_Dyn __user *dyn;
-				Elf32_Sword d_tag;
+				Elf_Dyn __user *dyn;
+				Elf_Sword d_tag;
 
 				params->dynamic_addr =
 					(phdr->p_vaddr - seg->p_vaddr) +
···
 				 * one item, and that the last item is a NULL
 				 * entry */
 				if (phdr->p_memsz == 0 ||
-				    phdr->p_memsz % sizeof(Elf32_Dyn) != 0)
+				    phdr->p_memsz % sizeof(Elf_Dyn) != 0)
 					goto dynamic_error;
 
-				tmp = phdr->p_memsz / sizeof(Elf32_Dyn);
-				dyn = (Elf32_Dyn __user *)params->dynamic_addr;
+				tmp = phdr->p_memsz / sizeof(Elf_Dyn);
+				dyn = (Elf_Dyn __user *)params->dynamic_addr;
 				if (get_user(d_tag, &dyn[tmp - 1].d_tag) ||
 				    d_tag != 0)
 					goto dynamic_error;
···
 	struct file *file,
 	struct mm_struct *mm)
 {
-	struct elf32_fdpic_loadseg *seg;
-	struct elf32_phdr *phdr;
+	struct elf_fdpic_loadseg *seg;
+	struct elf_phdr *phdr;
 	unsigned long load_addr, base = ULONG_MAX, top = 0, maddr = 0;
 	int loop, ret;
 
···
 					     struct file *file,
 					     struct mm_struct *mm)
 {
-	struct elf32_fdpic_loadseg *seg;
-	struct elf32_phdr *phdr;
+	struct elf_fdpic_loadseg *seg;
+	struct elf_phdr *phdr;
 	unsigned long load_addr, delta_vaddr;
 	int loop, dvset;
 

include/asm-generic/preempt.h

···
 
 #ifdef CONFIG_PREEMPTION
 extern asmlinkage void preempt_schedule(void);
-#define __preempt_schedule() preempt_schedule()
 extern asmlinkage void preempt_schedule_notrace(void);
+
+#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+
+void dynamic_preempt_schedule(void);
+void dynamic_preempt_schedule_notrace(void);
+#define __preempt_schedule()		dynamic_preempt_schedule()
+#define __preempt_schedule_notrace()	dynamic_preempt_schedule_notrace()
+
+#else /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_KEY*/
+
+#define __preempt_schedule() preempt_schedule()
 #define __preempt_schedule_notrace() preempt_schedule_notrace()
+
+#endif /* CONFIG_PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_KEY*/
 #endif /* CONFIG_PREEMPTION */
 
 #endif /* __ASM_PREEMPT_H */

include/linux/elf-fdpic.h

···
 
 #include <uapi/linux/elf-fdpic.h>
 
+#if ELF_CLASS == ELFCLASS32
+#define Elf_Sword			Elf32_Sword
+#define elf_fdpic_loadseg		elf32_fdpic_loadseg
+#define elf_fdpic_loadmap		elf32_fdpic_loadmap
+#define ELF_FDPIC_LOADMAP_VERSION	ELF32_FDPIC_LOADMAP_VERSION
+#else
+#define Elf_Sword			Elf64_Sxword
+#define elf_fdpic_loadmap		elf64_fdpic_loadmap
+#define elf_fdpic_loadseg		elf64_fdpic_loadseg
+#define ELF_FDPIC_LOADMAP_VERSION	ELF64_FDPIC_LOADMAP_VERSION
+#endif
+
 /*
  * binfmt binary parameters structure
  */
 struct elf_fdpic_params {
 	struct elfhdr			hdr;		/* ref copy of ELF header */
 	struct elf_phdr			*phdrs;		/* ref copy of PT_PHDR table */
-	struct elf32_fdpic_loadmap	*loadmap;	/* loadmap to be passed to userspace */
+	struct elf_fdpic_loadmap	*loadmap;	/* loadmap to be passed to userspace */
 	unsigned long			elfhdr_addr;	/* mapped ELF header user address */
 	unsigned long			ph_addr;	/* mapped PT_PHDR user address */
 	unsigned long			map_addr;	/* mapped loadmap user address */

include/linux/perf/riscv_pmu.h

···
  *
  */
 
-#ifndef _ASM_RISCV_PERF_EVENT_H
-#define _ASM_RISCV_PERF_EVENT_H
+#ifndef _RISCV_PMU_H
+#define _RISCV_PMU_H
 
 #include <linux/perf_event.h>
 #include <linux/ptrace.h>
···
 
 #define RISCV_MAX_COUNTERS	64
 #define RISCV_OP_UNSUPP		(-EOPNOTSUPP)
-#define RISCV_PMU_PDEV_NAME	"riscv-pmu"
+#define RISCV_PMU_SBI_PDEV_NAME	"riscv-pmu-sbi"
 #define RISCV_PMU_LEGACY_PDEV_NAME	"riscv-pmu-legacy"
 
 #define RISCV_PMU_STOP_FLAG_RESET 1
···
 	void		(*ctr_start)(struct perf_event *event, u64 init_val);
 	void		(*ctr_stop)(struct perf_event *event, unsigned long flag);
 	int		(*event_map)(struct perf_event *event, u64 *config);
+	void		(*event_init)(struct perf_event *event);
+	void		(*event_mapped)(struct perf_event *event, struct mm_struct *mm);
+	void		(*event_unmapped)(struct perf_event *event, struct mm_struct *mm);
+	uint8_t		(*csr_index)(struct perf_event *event);
 
 	struct cpu_hw_events	__percpu *hw_events;
 	struct hlist_node	node;
···
 
 #endif /* CONFIG_RISCV_PMU */
 
-#endif /* _ASM_RISCV_PERF_EVENT_H */
+#endif /* _RISCV_PMU_H */

include/linux/perf_event.h

···
 
 	/*
 	 * Will return the value for perf_event_mmap_page::index for this event,
-	 * if no implementation is provided it will default to: event->hw.idx + 1.
+	 * if no implementation is provided it will default to 0 (see
+	 * perf_event_idx_default).
 	 */
 	int (*event_idx)		(struct perf_event *event); /*optional */
 

include/uapi/linux/elf-fdpic.h

···
 
 #define ELF32_FDPIC_LOADMAP_VERSION	0x0000
 
+/* segment mappings for ELF FDPIC libraries/executables/interpreters */
+struct elf64_fdpic_loadseg {
+	Elf64_Addr	addr;		/* core address to which mapped */
+	Elf64_Addr	p_vaddr;	/* VMA recorded in file */
+	Elf64_Word	p_memsz;	/* allocation size recorded in file */
+};
+
+struct elf64_fdpic_loadmap {
+	Elf64_Half	version;	/* version of these structures, just in case... */
+	Elf64_Half	nsegs;		/* number of segments */
+	struct elf64_fdpic_loadseg segs[];
+};
+
+#define ELF64_FDPIC_LOADMAP_VERSION	0x0000
+
 #endif /* _UAPI_LINUX_ELF_FDPIC_H */

lib/Kconfig.debug

···
 config DEBUG_INFO_SPLIT
 	bool "Produce split debuginfo in .dwo files"
 	depends on $(cc-option,-gsplit-dwarf)
+	# RISC-V linker relaxation + -gsplit-dwarf has issues with LLVM and GCC
+	# prior to 12.x:
+	# https://github.com/llvm/llvm-project/issues/56642
+	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99090
+	depends on !RISCV || GCC_VERSION >= 120000
 	help
 	  Generate debug info into separate .dwo files. This significantly
 	  reduces the build directory size for builds with DEBUG_INFO,
···
 
 config DEBUG_FORCE_FUNCTION_ALIGN_64B
 	bool "Force all function address 64B aligned"
-	depends on EXPERT && (X86_64 || ARM64 || PPC32 || PPC64 || ARC || S390)
+	depends on EXPERT && (X86_64 || ARM64 || PPC32 || PPC64 || ARC || RISCV || S390)
 	select FUNCTION_ALIGNMENT_64B
 	help
 	  There are cases that a commit from one domain changes the function

tools/lib/perf/mmap.c

···
 
 static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); }
 
+/* __riscv_xlen contains the witdh of the native base integer, here 64-bit */
+#elif defined(__riscv) && __riscv_xlen == 64
+
+/* TODO: implement rv32 support */
+
+#define CSR_CYCLE	0xc00
+#define CSR_TIME	0xc01
+
+#define csr_read(csr)						\
+({								\
+	register unsigned long __v;				\
+		__asm__ __volatile__ ("csrr %0, %1"		\
+		 : "=r" (__v)					\
+		 : "i" (csr) : );				\
+		 __v;						\
+})
+
+static unsigned long csr_read_num(int csr_num)
+{
+#define switchcase_csr_read(__csr_num, __val)           {\
+	case __csr_num:                                 \
+		__val = csr_read(__csr_num);            \
+		break; }
+#define switchcase_csr_read_2(__csr_num, __val)         {\
+	switchcase_csr_read(__csr_num + 0, __val)        \
+	switchcase_csr_read(__csr_num + 1, __val)}
+#define switchcase_csr_read_4(__csr_num, __val)         {\
+	switchcase_csr_read_2(__csr_num + 0, __val)      \
+	switchcase_csr_read_2(__csr_num + 2, __val)}
+#define switchcase_csr_read_8(__csr_num, __val)         {\
+	switchcase_csr_read_4(__csr_num + 0, __val)      \
+	switchcase_csr_read_4(__csr_num + 4, __val)}
+#define switchcase_csr_read_16(__csr_num, __val)        {\
+	switchcase_csr_read_8(__csr_num + 0, __val)      \
+	switchcase_csr_read_8(__csr_num + 8, __val)}
+#define switchcase_csr_read_32(__csr_num, __val)        {\
+	switchcase_csr_read_16(__csr_num + 0, __val)     \
+	switchcase_csr_read_16(__csr_num + 16, __val)}
+
+	unsigned long ret = 0;
+
+	switch (csr_num) {
+	switchcase_csr_read_32(CSR_CYCLE, ret)
+	default:
+		break;
+	}
+
+	return ret;
+#undef switchcase_csr_read_32
+#undef switchcase_csr_read_16
+#undef switchcase_csr_read_8
+#undef switchcase_csr_read_4
+#undef switchcase_csr_read_2
+#undef switchcase_csr_read
+}
+
+static u64 read_perf_counter(unsigned int counter)
+{
+	return csr_read_num(CSR_CYCLE + counter);
+}
+
+static u64 read_timestamp(void)
+{
+	return csr_read_num(CSR_TIME);
+}
+
 #else
 static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; }
 static u64 read_timestamp(void) { return 0; }

tools/perf/tests/mmap-basic.c

···
 			 "permissions"),
 	TEST_CASE_REASON("User space counter reading of instructions",
 			 mmap_user_read_instr,
-#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \
+			 (defined(__riscv) && __riscv_xlen == 64)
 			 "permissions"
 #else
 			 "unsupported"
···
 		),
 	TEST_CASE_REASON("User space counter reading of cycles",
 			 mmap_user_read_cycles,
-#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \
+			 (defined(__riscv) && __riscv_xlen == 64)
 			 "permissions"
 #else
 			 "unsupported"

tools/testing/selftests/riscv/Makefile

···
 ARCH ?= $(shell uname -m 2>/dev/null || echo not)
 
 ifneq (,$(filter $(ARCH),riscv))
-RISCV_SUBTARGETS ?= hwprobe vector
+RISCV_SUBTARGETS ?= hwprobe vector mm
 else
 RISCV_SUBTARGETS :=
 endif

tools/testing/selftests/riscv/mm/.gitignore

···
+mmap_bottomup
+mmap_default

tools/testing/selftests/riscv/mm/Makefile

···
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2021 ARM Limited
+# Originally tools/testing/arm64/abi/Makefile
+
+# Additional include paths needed by kselftest.h and local headers
+CFLAGS += -D_GNU_SOURCE -std=gnu99 -I.
+
+TEST_GEN_FILES := testcases/mmap_default testcases/mmap_bottomup
+
+TEST_PROGS := testcases/run_mmap.sh
+
+include ../../lib.mk
+
+$(OUTPUT)/mm: testcases/mmap_default.c testcases/mmap_bottomup.c testcases/mmap_tests.h
+	$(CC) -o$@ $(CFLAGS) $(LDFLAGS) $^

tools/testing/selftests/riscv/mm/testcases/mmap_bottomup.c

···
+// SPDX-License-Identifier: GPL-2.0-only
+#include <sys/mman.h>
+#include <testcases/mmap_test.h>
+
+#include "../../kselftest_harness.h"
+
+TEST(infinite_rlimit)
+{
+// Only works on 64 bit
+#if __riscv_xlen == 64
+	struct addresses mmap_addresses;
+
+	EXPECT_EQ(BOTTOM_UP, memory_layout());
+
+	do_mmaps(&mmap_addresses);
+
+	EXPECT_NE(MAP_FAILED, mmap_addresses.no_hint);
+	EXPECT_NE(MAP_FAILED, mmap_addresses.on_37_addr);
+	EXPECT_NE(MAP_FAILED, mmap_addresses.on_38_addr);
+	EXPECT_NE(MAP_FAILED, mmap_addresses.on_46_addr);
+	EXPECT_NE(MAP_FAILED, mmap_addresses.on_47_addr);
+	EXPECT_NE(MAP_FAILED, mmap_addresses.on_55_addr);
+	EXPECT_NE(MAP_FAILED, mmap_addresses.on_56_addr);
+
+	EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.no_hint);
+	EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_37_addr);
+	EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_38_addr);
+	EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_46_addr);
+	EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.on_47_addr);
+	EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.on_55_addr);
+	EXPECT_GT(1UL << 56, (unsigned long)mmap_addresses.on_56_addr);
+#endif
+}
+
+TEST_HARNESS_MAIN

tools/testing/selftests/riscv/mm/testcases/mmap_default.c

···
+// SPDX-License-Identifier: GPL-2.0-only
+#include <sys/mman.h>
+#include <testcases/mmap_test.h>
+
+#include "../../kselftest_harness.h"
+
+TEST(default_rlimit)
+{
+// Only works on 64 bit
+#if __riscv_xlen == 64
+	struct addresses mmap_addresses;
+
+	EXPECT_EQ(TOP_DOWN, memory_layout());
+
+	do_mmaps(&mmap_addresses);
+
+	EXPECT_NE(MAP_FAILED, mmap_addresses.no_hint);
+	EXPECT_NE(MAP_FAILED, mmap_addresses.on_37_addr);
+	EXPECT_NE(MAP_FAILED, mmap_addresses.on_38_addr);
+	EXPECT_NE(MAP_FAILED, mmap_addresses.on_46_addr);
+	EXPECT_NE(MAP_FAILED, mmap_addresses.on_47_addr);
+	EXPECT_NE(MAP_FAILED, mmap_addresses.on_55_addr);
+	EXPECT_NE(MAP_FAILED, mmap_addresses.on_56_addr);
+
+	EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.no_hint);
+	EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_37_addr);
+	EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_38_addr);
+	EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_46_addr);
+	EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.on_47_addr);
+	EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.on_55_addr);
+	EXPECT_GT(1UL << 56, (unsigned long)mmap_addresses.on_56_addr);
+#endif
+}
+
+TEST_HARNESS_MAIN

tools/testing/selftests/riscv/mm/testcases/mmap_test.h

···
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _TESTCASES_MMAP_TEST_H
+#define _TESTCASES_MMAP_TEST_H
+#include <sys/mman.h>
+#include <sys/resource.h>
+#include <stddef.h>
+
+#define TOP_DOWN 0
+#define BOTTOM_UP 1
+
+struct addresses {
+	int *no_hint;
+	int *on_37_addr;
+	int *on_38_addr;
+	int *on_46_addr;
+	int *on_47_addr;
+	int *on_55_addr;
+	int *on_56_addr;
+};
+
+static inline void do_mmaps(struct addresses *mmap_addresses)
+{
+	/*
+	 * Place all of the hint addresses on the boundaries of mmap
+	 * sv39, sv48, sv57
+	 * User addresses end at 1<<38, 1<<47, 1<<56 respectively
+	 */
+	void *on_37_bits = (void *)(1UL << 37);
+	void *on_38_bits = (void *)(1UL << 38);
+	void *on_46_bits = (void *)(1UL << 46);
+	void *on_47_bits = (void *)(1UL << 47);
+	void *on_55_bits = (void *)(1UL << 55);
+	void *on_56_bits = (void *)(1UL << 56);
+
+	int prot = PROT_READ | PROT_WRITE;
+	int flags = MAP_PRIVATE | MAP_ANONYMOUS;
+
+	mmap_addresses->no_hint =
+		mmap(NULL, 5 * sizeof(int), prot, flags, 0, 0);
+	mmap_addresses->on_37_addr =
+		mmap(on_37_bits, 5 * sizeof(int), prot, flags, 0, 0);
+	mmap_addresses->on_38_addr =
+		mmap(on_38_bits, 5 * sizeof(int), prot, flags, 0, 0);
+	mmap_addresses->on_46_addr =
+		mmap(on_46_bits, 5 * sizeof(int), prot, flags, 0, 0);
+	mmap_addresses->on_47_addr =
+		mmap(on_47_bits, 5 * sizeof(int), prot, flags, 0, 0);
+	mmap_addresses->on_55_addr =
+		mmap(on_55_bits, 5 * sizeof(int), prot, flags, 0, 0);
+	mmap_addresses->on_56_addr =
+		mmap(on_56_bits, 5 * sizeof(int), prot, flags, 0, 0);
+}
+
+static inline int memory_layout(void)
+{
+	int prot = PROT_READ | PROT_WRITE;
+	int flags = MAP_PRIVATE | MAP_ANONYMOUS;
+
+	void *value1 = mmap(NULL, sizeof(int), prot, flags, 0, 0);
+	void *value2 = mmap(NULL, sizeof(int), prot, flags, 0, 0);
+
+	return value2 > value1;
+}
+#endif /* _TESTCASES_MMAP_TEST_H */

tools/testing/selftests/riscv/mm/testcases/run_mmap.sh

···
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+original_stack_limit=$(ulimit -s)
+
+./mmap_default
+
+# Force mmap_bottomup to be ran with bottomup memory due to
+# the unlimited stack
+ulimit -s unlimited
+./mmap_bottomup
+ulimit -s $original_stack_limit