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.
 
-Controls user space access for reading perf event counters. When set to 1,
-user space can read performance monitor counter registers directly.
+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

+/* 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

+/* 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

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

@@ -9,11 +9,15 @@
 #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

@@ -46,7 +46,7 @@ int riscv_of_processor_hartid(struct device_node *node, unsigned long *hart)
 	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;
 
@@ -66,16 +66,53 @@ int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *har
 		return -ENODEV;
 	}
 
+	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_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 (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\" property\n", *hart);
+		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))
+	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))
+	if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7)) {
+		pr_warn("CPU with hartid=%lu does not support rv64ima", *hart);
 		return -ENODEV;
+	}
 
 	return 0;
 }
@@ -165,132 +202,46 @@ arch_initcall(riscv_cpuinfo_init);
 
 #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;
+	seq_puts(f, "isa\t\t: ");
 
-	/* No extension support available */
-	if (arr_sz <= 0)
-		return;
+	if (IS_ENABLED(CONFIG_32BIT))
+		seq_write(f, "rv32", 4);
+	else
+		seq_write(f, "rv64", 4);
 
-	for (i = 0; i <= arr_sz; i++) {
-		edata = &isa_ext_arr[i];
-		if (!__riscv_isa_extension_available(NULL, edata->isa_ext_id))
+	for (int i = 0; i < riscv_isa_ext_count; i++) {
+		if (!__riscv_isa_extension_available(NULL, riscv_isa_ext[i].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";
+		/* Only multi-letter extensions are split by underscores */
+		if (strnlen(riscv_isa_ext[i].name, 2) != 1)
+			seq_puts(f, "_");
 
-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);
+		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);
 }
@@ -321,27 +272,21 @@ static int c_show(struct seq_file *m, void *v)
 	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/head.S

@@ -289,10 +289,6 @@ clear_bss:
 	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)
@@ -306,7 +302,7 @@ clear_bss_done:
 	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

@@ -3,6 +3,7 @@
 
 #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>
@@ -47,15 +48,19 @@
 	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

@@ -29,13 +29,14 @@ riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *api)
 	 * 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

@@ -188,3 +188,108 @@ bool __kprobes simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *r
 
 	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

@@ -24,5 +24,10 @@ bool simulate_auipc(u32 opcode, unsigned long addr, struct pt_regs *regs);
 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

@@ -178,6 +178,11 @@ static void __init init_resources(void)
 		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
@@ -311,6 +316,7 @@ void __init setup_arch(char **cmdline_p)
 	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

@@ -5,6 +5,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/assembler.h>
@@ -58,7 +59,7 @@ ENTRY(__cpu_suspend_enter)
 	ret
 END(__cpu_suspend_enter)
 
-ENTRY(__cpu_resume_enter)
+SYM_TYPED_FUNC_START(__cpu_resume_enter)
 	/* Load the global pointer */
 	.option push
 	.option norelax
@@ -94,4 +95,4 @@ ENTRY(__cpu_resume_enter)
 
 	/* Return to C code */
 	ret
-END(__cpu_resume_enter)
+SYM_FUNC_END(__cpu_resume_enter)

arch/riscv/kernel/sys_riscv.c

@@ -335,3 +335,9 @@ SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
 	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

@@ -10,9 +10,13 @@
 #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

@@ -21,6 +21,7 @@
 
 #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>
@@ -271,7 +272,8 @@ void handle_break(struct pt_regs *regs)
 								== 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

@@ -67,7 +67,7 @@ static void __flush_context(void)
 	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

@@ -11,6 +11,8 @@
 #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)
@@ -78,3 +80,9 @@ void riscv_noncoherent_supported(void)
 	     "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

@@ -1299,6 +1299,28 @@ static inline void setup_vm_final(void)
 }
 #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
  *
@@ -1310,8 +1332,12 @@ static void __init reserve_crashkernel(void)
 {
 	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;
 
@@ -1327,14 +1353,36 @@ static void __init reserve_crashkernel(void)
 		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;
 	}
@@ -1347,12 +1395,37 @@ static void __init reserve_crashkernel(void)
 	 * 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);
@@ -1360,6 +1433,12 @@ static void __init reserve_crashkernel(void)
 		}
 	}
 
+	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",
 		crash_base, crash_base + crash_size, crash_size >> 20);
 

arch/riscv/mm/kasan_init.c

@@ -22,9 +22,9 @@
  * 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)
 {
@@ -438,7 +438,7 @@ static void __init kasan_shallow_populate(void *start, void *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

@@ -77,6 +77,10 @@ ifdef CONFIG_STACKPROTECTOR_STRONG
 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

@@ -14,9 +14,81 @@
 #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)
 {
 #define switchcase_csr_read(__csr_num, __val)		{\
@@ -171,6 +243,8 @@ int riscv_pmu_event_set_period(struct perf_event *event)
 
 	local64_set(&hwc->prev_count, (u64)-left);
 
+	perf_event_update_userpage(event);
+
 	return overflow;
 }
 
@@ -264,6 +338,9 @@ static int riscv_pmu_event_init(struct perf_event *event)
 	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
@@ -280,6 +357,39 @@ static int riscv_pmu_event_init(struct perf_event *event)
 	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)
 {
 	struct riscv_pmu *pmu;
@@ -304,6 +414,9 @@ 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

@@ -13,7 +13,7 @@
 #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;
 
@@ -71,6 +71,29 @@ static void pmu_legacy_ctr_start(struct perf_event *event, u64 ival)
 	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.
@@ -91,6 +114,9 @@ static void pmu_legacy_init(struct riscv_pmu *pmu)
 	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

@@ -24,6 +24,14 @@
 #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");
 
@@ -43,6 +51,9 @@ static const struct attribute_group *riscv_pmu_attr_groups[] = {
 	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
  * per_cpu in case of harts with different pmu counters
@@ -301,6 +312,11 @@ int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr)
 }
 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;
@@ -329,18 +345,34 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event)
 	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",
@@ -474,6 +506,22 @@ static u64 pmu_sbi_ctr_read(struct perf_event *event)
 	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;
@@ -490,6 +538,10 @@ static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival)
 	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)
@@ -497,6 +549,10 @@ 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) &&
 		flag != SBI_PMU_STOP_FLAG_RESET)
@@ -704,10 +760,13 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node)
 	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);
@@ -838,6 +897,121 @@ static void riscv_pmu_destroy(struct riscv_pmu *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;
@@ -881,6 +1055,10 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 	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)
@@ -894,6 +1072,8 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_unregister;
 
+	register_sysctl("kernel", sbi_pmu_sysctl_table);
+
 	return 0;
 
 out_unregister:
@@ -907,7 +1087,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 static struct platform_driver pmu_sbi_driver = {
 	.probe		= pmu_sbi_device_probe,
 	.driver		= {
-		.name	= RISCV_PMU_PDEV_NAME,
+		.name	= RISCV_PMU_SBI_PDEV_NAME,
 	},
 };
 
@@ -934,7 +1114,7 @@ static int __init pmu_sbi_devinit(void)
 	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

@@ -58,7 +58,7 @@ config ARCH_USE_GNU_PROPERTY
 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

@@ -138,7 +138,7 @@ static int is_constdisp(struct elfhdr *hdr)
 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;
@@ -560,8 +560,8 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 	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;
 
@@ -571,8 +571,8 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 	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;
@@ -740,13 +740,13 @@ static int elf_fdpic_map_file(struct elf_fdpic_params *params,
 			      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;
@@ -766,7 +766,7 @@ static int elf_fdpic_map_file(struct elf_fdpic_params *params,
 
 	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 */
@@ -839,8 +839,8 @@ static int elf_fdpic_map_file(struct elf_fdpic_params *params,
 			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) +
@@ -850,11 +850,11 @@ static int elf_fdpic_map_file(struct elf_fdpic_params *params,
 				 * 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;
@@ -923,8 +923,8 @@ static int elf_fdpic_map_file_constdisp_on_uclinux(
 	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;
 
@@ -1007,8 +1007,8 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params,
 					     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

@@ -80,9 +80,21 @@ static __always_inline bool should_resched(int preempt_offset)
 
 #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

@@ -10,13 +10,25 @@
 
 #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

@@ -6,8 +6,8 @@
  *
  */
 
-#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>
@@ -21,7 +21,7 @@
 
 #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
@@ -55,6 +55,10 @@ struct riscv_pmu {
 	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;
@@ -81,4 +85,4 @@ int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr);
 
 #endif /* CONFIG_RISCV_PMU */
 
-#endif /* _ASM_RISCV_PERF_EVENT_H */
+#endif /* _RISCV_PMU_H */

include/linux/perf_event.h

@@ -444,7 +444,8 @@ struct pmu {
 
 	/*
 	 * 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

@@ -32,4 +32,19 @@ struct elf32_fdpic_loadmap {
 
 #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

@@ -355,6 +355,11 @@ endchoice # "Compressed Debug information"
 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,
@@ -502,7 +507,7 @@ config SECTION_MISMATCH_WARN_ONLY
 
 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

@@ -392,6 +392,72 @@ static u64 read_perf_counter(unsigned int counter)
 
 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

@@ -284,7 +284,8 @@ static struct test_case tests__basic_mmap[] = {
 			 "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"
@@ -292,7 +293,8 @@ static struct test_case tests__basic_mmap[] = {
 		),
 	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

@@ -5,7 +5,7 @@
 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