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

@@ -873,7 +873,7 @@
 			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.
@@ -886,14 +886,14 @@
 			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
@@ -904,6 +904,7 @@
 			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.
@@ -5554,6 +5555,13 @@
 			[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
 
 	rodata=		[KNL]

Documentation/admin-guide/sysctl/kernel.rst

@@ -941,16 +941,35 @@ enabled, otherwise writing to this file will return ``-EBUSY``.
 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

@@ -133,3 +133,25 @@ RISC-V Linux Kernel SV57
    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

@@ -35,6 +35,7 @@ config RISCV
 	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
@@ -42,12 +43,14 @@ config RISCV
 	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
@@ -62,6 +65,7 @@ config RISCV
 	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
@@ -130,6 +134,7 @@ config RISCV
 	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
@@ -267,6 +272,7 @@ config RISCV_DMA_NONCOHERENT
 	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
@@ -836,6 +842,24 @@ config XIP_PHYS_ADDR
 	  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"
 
 config BUILTIN_DTB

arch/riscv/Makefile

@@ -87,9 +87,6 @@ endif
 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

@@ -146,7 +146,7 @@
  * 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

@@ -13,6 +13,7 @@
 
 #ifdef CONFIG_RISCV_DMA_NONCOHERENT
 #define ARCH_DMA_MINALIGN L1_CACHE_BYTES
+#define ARCH_KMALLOC_MINALIGN	(8)
 #endif
 
 /*
@@ -23,4 +24,17 @@
 #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

@@ -58,8 +58,10 @@ void riscv_init_cbo_blocksizes(void);
 
 #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

@@ -0,0 +1,22 @@
+/* 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

@@ -41,6 +41,7 @@ extern bool compat_elf_check_arch(Elf32_Ehdr *hdr);
 #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)
 
 /*
@@ -49,7 +50,7 @@ extern bool compat_elf_check_arch(Elf32_Ehdr *hdr);
  * 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
@@ -69,6 +70,13 @@ extern bool compat_elf_check_arch(Elf32_Ehdr *hdr);
 #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
@@ -78,7 +86,6 @@ extern unsigned long elf_hwcap;
 
 #define COMPAT_ELF_PLATFORM	(NULL)
 
-#ifdef CONFIG_MMU
 #define ARCH_DLINFO						\
 do {								\
 	/*							\
@@ -115,6 +122,8 @@ 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

@@ -14,12 +14,17 @@
 #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')
@@ -55,7 +60,6 @@
 #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
@@ -70,12 +74,15 @@
 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);
 
 #define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext)

arch/riscv/include/asm/insn.h

@@ -63,6 +63,7 @@
 #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 */
@@ -130,6 +131,7 @@
 #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
@@ -289,6 +291,10 @@ static __always_inline bool riscv_insn_is_c_jalr(u32 code)
 #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)); })
@@ -316,6 +322,10 @@ static __always_inline bool riscv_insn_is_c_jalr(u32 code)
 	(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); \
 	(RVC_X(x_, RVC_J_IMM_3_1_OPOFF, RVC_J_IMM_3_1_MASK) << RVC_J_IMM_3_1_OFF) | \

arch/riscv/include/asm/mmu.h

@@ -20,6 +20,10 @@ typedef struct {
 	/* 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

@@ -62,11 +62,16 @@
  * 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 \
@@ -111,11 +116,27 @@
 #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 */
@@ -843,14 +864,16 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
  * 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

@@ -13,19 +13,59 @@
 
 #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

@@ -75,7 +75,7 @@ static inline int syscall_get_arch(struct task_struct *task)
 #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;
@@ -87,8 +87,7 @@ static inline void syscall_handler(struct pt_regs *regs, ulong syscall)
 #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

@@ -0,0 +1,87 @@
+/* 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

@@ -10,6 +10,11 @@
 
 #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

@@ -25,7 +25,7 @@ struct __sc_riscv_v_state {
  * 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

@@ -91,6 +91,8 @@ obj-$(CONFIG_CRASH_CORE)	+= crash_core.o
 
 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