Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

22 files changed, 232 insertions, 312 deletions

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 81d94a8ee1..5b243d46f4 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -67,6 +67,7 @@ obj-$(CONFIG_RISCV_MISALIGNED)	+= unaligned_access_speed.o
 obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)	+= copy-unaligned.o
 
 obj-$(CONFIG_FPU)		+= fpu.o
+obj-$(CONFIG_FPU)		+= kernel_mode_fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
 obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index a03129f40c..b09ca5f944 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -9,6 +9,7 @@
 #include <linux/kbuild.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/ftrace.h>
 #include <linux/suspend.h>
 #include <asm/kvm_host.h>
 #include <asm/thread_info.h>
@@ -488,4 +489,21 @@ void asm_offsets(void)
 	DEFINE(STACKFRAME_SIZE_ON_STACK, ALIGN(sizeof(struct stackframe), STACK_ALIGN));
 	OFFSET(STACKFRAME_FP, stackframe, fp);
 	OFFSET(STACKFRAME_RA, stackframe, ra);
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+	DEFINE(FREGS_SIZE_ON_STACK, ALIGN(sizeof(struct ftrace_regs), STACK_ALIGN));
+	DEFINE(FREGS_EPC,	    offsetof(struct ftrace_regs, epc));
+	DEFINE(FREGS_RA,	    offsetof(struct ftrace_regs, ra));
+	DEFINE(FREGS_SP,	    offsetof(struct ftrace_regs, sp));
+	DEFINE(FREGS_S0,	    offsetof(struct ftrace_regs, s0));
+	DEFINE(FREGS_T1,	    offsetof(struct ftrace_regs, t1));
+	DEFINE(FREGS_A0,	    offsetof(struct ftrace_regs, a0));
+	DEFINE(FREGS_A1,	    offsetof(struct ftrace_regs, a1));
+	DEFINE(FREGS_A2,	    offsetof(struct ftrace_regs, a2));
+	DEFINE(FREGS_A3,	    offsetof(struct ftrace_regs, a3));
+	DEFINE(FREGS_A4,	    offsetof(struct ftrace_regs, a4));
+	DEFINE(FREGS_A5,	    offsetof(struct ftrace_regs, a5));
+	DEFINE(FREGS_A6,	    offsetof(struct ftrace_regs, a6));
+	DEFINE(FREGS_A7,	    offsetof(struct ftrace_regs, a7));
+#endif
 }
diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile
index 3df4cb788c..24e37d1ef7 100644
--- a/arch/riscv/kernel/compat_vdso/Makefile
+++ b/arch/riscv/kernel/compat_vdso/Makefile
@@ -34,12 +34,6 @@ obj-compat_vdso := $(addprefix $(obj)/, $(obj-compat_vdso))
 obj-y += compat_vdso.o
 CPPFLAGS_compat_vdso.lds += -P -C -DCOMPAT_VDSO -U$(ARCH)
 
-# Disable profiling and instrumentation for VDSO code
-GCOV_PROFILE := n
-KCOV_INSTRUMENT := n
-KASAN_SANITIZE := n
-UBSAN_SANITIZE := n
-
 # Force dependency
 $(obj)/compat_vdso.o: $(obj)/compat_vdso.so
 
@@ -58,7 +52,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
 # Generate VDSO offsets using helper script
-gen-compat_vdsosym := $(srctree)/$(src)/gen_compat_vdso_offsets.sh
+gen-compat_vdsosym := $(src)/gen_compat_vdso_offsets.sh
 quiet_cmd_compat_vdsosym = VDSOSYM $@
 	cmd_compat_vdsosym = $(NM) $< | $(gen-compat_vdsosym) | LC_ALL=C sort > $@
 
diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c
index 54260c16f9..11c0d2e0be 100644
--- a/arch/riscv/kernel/elf_kexec.c
+++ b/arch/riscv/kernel/elf_kexec.c
@@ -19,6 +19,7 @@
 #include <linux/libfdt.h>
 #include <linux/types.h>
 #include <linux/memblock.h>
+#include <linux/vmalloc.h>
 #include <asm/setup.h>
 
 int arch_kimage_file_post_load_cleanup(struct kimage *image)
diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S
index 2c543f130f..327cf527dd 100644
--- a/arch/riscv/kernel/fpu.S
+++ b/arch/riscv/kernel/fpu.S
@@ -211,7 +211,7 @@ SYM_FUNC_START(put_f64_reg)
 SYM_FUNC_END(put_f64_reg)
 
 /*
- * put_f64_reg - Get a 64 bits FP register value and returned it or store it to
+ * get_f64_reg - Get a 64 bits FP register value and returned it or store it to
  *	 	 a pointer.
  * a0 = FP register index to be retrieved
  * a1 = If xlen == 32, pointer which should be loaded with the FP register value
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index f5aa24d9e1..4b95c574fd 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -8,6 +8,7 @@
 #include <linux/ftrace.h>
 #include <linux/uaccess.h>
 #include <linux/memory.h>
+#include <linux/stop_machine.h>
 #include <asm/cacheflush.h>
 #include <asm/patch.h>
 
@@ -75,8 +76,7 @@ static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target,
 		make_call_t0(hook_pos, target, call);
 
 	/* Replace the auipc-jalr pair at once. Return -EPERM on write error. */
-	if (patch_text_nosync
-	    ((void *)hook_pos, enable ? call : nops, MCOUNT_INSN_SIZE))
+	if (patch_insn_write((void *)hook_pos, enable ? call : nops, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
 	return 0;
@@ -88,7 +88,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	make_call_t0(rec->ip, addr, call);
 
-	if (patch_text_nosync((void *)rec->ip, call, MCOUNT_INSN_SIZE))
+	if (patch_insn_write((void *)rec->ip, call, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
 	return 0;
@@ -99,7 +99,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 {
 	unsigned int nops[2] = {NOP4, NOP4};
 
-	if (patch_text_nosync((void *)rec->ip, nops, MCOUNT_INSN_SIZE))
+	if (patch_insn_write((void *)rec->ip, nops, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
 	return 0;
@@ -127,16 +127,48 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	int ret = __ftrace_modify_call((unsigned long)&ftrace_call,
 				       (unsigned long)func, true, true);
-	if (!ret) {
-		ret = __ftrace_modify_call((unsigned long)&ftrace_regs_call,
-					   (unsigned long)func, true, true);
-	}
 
 	return ret;
 }
+
+struct ftrace_modify_param {
+	int command;
+	atomic_t cpu_count;
+};
+
+static int __ftrace_modify_code(void *data)
+{
+	struct ftrace_modify_param *param = data;
+
+	if (atomic_inc_return(&param->cpu_count) == num_online_cpus()) {
+		ftrace_modify_all_code(param->command);
+		/*
+		 * Make sure the patching store is effective *before* we
+		 * increment the counter which releases all waiting CPUs
+		 * by using the release variant of atomic increment. The
+		 * release pairs with the call to local_flush_icache_all()
+		 * on the waiting CPU.
+		 */
+		atomic_inc_return_release(&param->cpu_count);
+	} else {
+		while (atomic_read(&param->cpu_count) <= num_online_cpus())
+			cpu_relax();
+
+		local_flush_icache_all();
+	}
+
+	return 0;
+}
+
+void arch_ftrace_update_code(int command)
+{
+	struct ftrace_modify_param param = { command, ATOMIC_INIT(0) };
+
+	stop_machine(__ftrace_modify_code, &param, cpu_online_mask);
+}
 #endif
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 		       unsigned long addr)
 {
@@ -178,16 +210,13 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
-	struct pt_regs *regs = arch_ftrace_get_regs(fregs);
-	unsigned long *parent = (unsigned long *)&regs->ra;
-
-	prepare_ftrace_return(parent, ip, frame_pointer(regs));
+	prepare_ftrace_return(&fregs->ra, ip, fregs->s0);
 }
-#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 extern void ftrace_graph_call(void);
 int ftrace_enable_ftrace_graph_caller(void)
 {
@@ -200,6 +229,6 @@ int ftrace_disable_ftrace_graph_caller(void)
 	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
 				    (unsigned long)&prepare_ftrace_return, false, true);
 }
-#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 4236a69c35..a00f7523cb 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -165,10 +165,21 @@ secondary_start_sbi:
 #endif
 	call .Lsetup_trap_vector
 	scs_load_current
-	tail smp_callin
+	call smp_callin
 #endif /* CONFIG_SMP */
 
 .align 2
+.Lsecondary_park:
+	/*
+	 * Park this hart if we:
+	 *  - have too many harts on CONFIG_RISCV_BOOT_SPINWAIT
+	 *  - receive an early trap, before setup_trap_vector finished
+	 *  - fail in smp_callin(), as a successful one wouldn't return
+	 */
+	wfi
+	j .Lsecondary_park
+
+.align 2
 .Lsetup_trap_vector:
 	/* Set trap vector to exception handler */
 	la a0, handle_exception
@@ -181,12 +192,6 @@ secondary_start_sbi:
 	csrw CSR_SCRATCH, zero
 	ret
 
-.align 2
-.Lsecondary_park:
-	/* We lack SMP support or have too many harts, so park this hart */
-	wfi
-	j .Lsecondary_park
-
 SYM_CODE_END(_start)
 
 SYM_CODE_START(_start_kernel)
diff --git a/arch/riscv/kernel/kernel_mode_fpu.c b/arch/riscv/kernel/kernel_mode_fpu.c
new file mode 100644
index 0000000000..0ac8348876
--- /dev/null
+++ b/arch/riscv/kernel/kernel_mode_fpu.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#include <linux/export.h>
+#include <linux/preempt.h>
+
+#include <asm/csr.h>
+#include <asm/fpu.h>
+#include <asm/processor.h>
+#include <asm/switch_to.h>
+
+void kernel_fpu_begin(void)
+{
+	preempt_disable();
+	fstate_save(current, task_pt_regs(current));
+	csr_set(CSR_SSTATUS, SR_FS);
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+
+void kernel_fpu_end(void)
+{
+	csr_clear(CSR_SSTATUS, SR_FS);
+	fstate_restore(current, task_pt_regs(current));
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_end);
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index b7561288e8..745dd4c4a6 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -56,138 +56,77 @@
 	addi	sp, sp, ABI_SIZE_ON_STACK
 	.endm
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
 
 /**
-* SAVE_ABI_REGS - save regs against the pt_regs struct
-*
-* @all: tell if saving all the regs
-*
-* If all is set, all the regs will be saved, otherwise only ABI
-* related regs (a0-a7,epc,ra and optional s0) will be saved.
+* SAVE_ABI_REGS - save regs against the ftrace_regs struct
 *
 * After the stack is established,
 *
 * 0(sp) stores the PC of the traced function which can be accessed
-* by &(fregs)->regs->epc in tracing function. Note that the real
+* by &(fregs)->epc in tracing function. Note that the real
 * function entry address should be computed with -FENTRY_RA_OFFSET.
 *
 * 8(sp) stores the function return address (i.e. parent IP) that
-* can be accessed by &(fregs)->regs->ra in tracing function.
+* can be accessed by &(fregs)->ra in tracing function.
 *
 * The other regs are saved at the respective localtion and accessed
-* by the respective pt_regs member.
+* by the respective ftrace_regs member.
 *
 * Here is the layout of stack for your reference.
 *
 * PT_SIZE_ON_STACK  ->  +++++++++
 *                       + ..... +
-*                       + t3-t6 +
-*                       + s2-s11+
 *                       + a0-a7 + --++++-> ftrace_caller saved
-*                       + s1    +   +
-*                       + s0    + --+
-*                       + t0-t2 +   +
-*                       + tp    +   +
-*                       + gp    +   +
+*                       + t1    + --++++-> direct tramp address
+*                       + s0    + --+ // frame pointer
 *                       + sp    +   +
 *                       + ra    + --+ // parent IP
 *               sp  ->  + epc   + --+ // PC
 *                       +++++++++
 **/
-	.macro SAVE_ABI_REGS, all=0
-	addi	sp, sp, -PT_SIZE_ON_STACK
-
-	REG_S	t0,  PT_EPC(sp)
-	REG_S	x1,  PT_RA(sp)
-
-	// save the ABI regs
-
-	REG_S	x10, PT_A0(sp)
-	REG_S	x11, PT_A1(sp)
-	REG_S	x12, PT_A2(sp)
-	REG_S	x13, PT_A3(sp)
-	REG_S	x14, PT_A4(sp)
-	REG_S	x15, PT_A5(sp)
-	REG_S	x16, PT_A6(sp)
-	REG_S	x17, PT_A7(sp)
-
-	// save the leftover regs
+	.macro SAVE_ABI_REGS
+	mv	t4, sp			// Save original SP in T4
+	addi	sp, sp, -FREGS_SIZE_ON_STACK
 
-	.if \all == 1
-	REG_S	x2, PT_SP(sp)
-	REG_S	x3, PT_GP(sp)
-	REG_S	x4, PT_TP(sp)
-	REG_S	x5, PT_T0(sp)
-	REG_S	x6, PT_T1(sp)
-	REG_S	x7, PT_T2(sp)
-	REG_S	x8, PT_S0(sp)
-	REG_S	x9, PT_S1(sp)
-	REG_S	x18, PT_S2(sp)
-	REG_S	x19, PT_S3(sp)
-	REG_S	x20, PT_S4(sp)
-	REG_S	x21, PT_S5(sp)
-	REG_S	x22, PT_S6(sp)
-	REG_S	x23, PT_S7(sp)
-	REG_S	x24, PT_S8(sp)
-	REG_S	x25, PT_S9(sp)
-	REG_S	x26, PT_S10(sp)
-	REG_S	x27, PT_S11(sp)
-	REG_S	x28, PT_T3(sp)
-	REG_S	x29, PT_T4(sp)
-	REG_S	x30, PT_T5(sp)
-	REG_S	x31, PT_T6(sp)
-
-	// save s0 if FP_TEST defined
-
-	.else
+	REG_S	t0,  FREGS_EPC(sp)
+	REG_S	x1,  FREGS_RA(sp)
+	REG_S	t4,  FREGS_SP(sp)	// Put original SP on stack
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	REG_S	x8, PT_S0(sp)
+	REG_S	x8,  FREGS_S0(sp)
 #endif
-	.endif
+	REG_S	x6,  FREGS_T1(sp)
+
+	// save the arguments
+	REG_S	x10, FREGS_A0(sp)
+	REG_S	x11, FREGS_A1(sp)
+	REG_S	x12, FREGS_A2(sp)
+	REG_S	x13, FREGS_A3(sp)
+	REG_S	x14, FREGS_A4(sp)
+	REG_S	x15, FREGS_A5(sp)
+	REG_S	x16, FREGS_A6(sp)
+	REG_S	x17, FREGS_A7(sp)
 	.endm
 
 	.macro RESTORE_ABI_REGS, all=0
-	REG_L	t0, PT_EPC(sp)
-	REG_L	x1, PT_RA(sp)
-	REG_L	x10, PT_A0(sp)
-	REG_L	x11, PT_A1(sp)
-	REG_L	x12, PT_A2(sp)
-	REG_L	x13, PT_A3(sp)
-	REG_L	x14, PT_A4(sp)
-	REG_L	x15, PT_A5(sp)
-	REG_L	x16, PT_A6(sp)
-	REG_L	x17, PT_A7(sp)
-
-	.if \all == 1
-	REG_L	x2, PT_SP(sp)
-	REG_L	x3, PT_GP(sp)
-	REG_L	x4, PT_TP(sp)
-	REG_L	x6, PT_T1(sp)
-	REG_L	x7, PT_T2(sp)
-	REG_L	x8, PT_S0(sp)
-	REG_L	x9, PT_S1(sp)
-	REG_L	x18, PT_S2(sp)
-	REG_L	x19, PT_S3(sp)
-	REG_L	x20, PT_S4(sp)
-	REG_L	x21, PT_S5(sp)
-	REG_L	x22, PT_S6(sp)
-	REG_L	x23, PT_S7(sp)
-	REG_L	x24, PT_S8(sp)
-	REG_L	x25, PT_S9(sp)
-	REG_L	x26, PT_S10(sp)
-	REG_L	x27, PT_S11(sp)
-	REG_L	x28, PT_T3(sp)
-	REG_L	x29, PT_T4(sp)
-	REG_L	x30, PT_T5(sp)
-	REG_L	x31, PT_T6(sp)
-
-	.else
+	REG_L	t0, FREGS_EPC(sp)
+	REG_L	x1, FREGS_RA(sp)
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	REG_L	x8, PT_S0(sp)
+	REG_L	x8, FREGS_S0(sp)
 #endif
-	.endif
-	addi	sp, sp, PT_SIZE_ON_STACK
+	REG_L	x6,  FREGS_T1(sp)
+
+	// restore the arguments
+	REG_L	x10, FREGS_A0(sp)
+	REG_L	x11, FREGS_A1(sp)
+	REG_L	x12, FREGS_A2(sp)
+	REG_L	x13, FREGS_A3(sp)
+	REG_L	x14, FREGS_A4(sp)
+	REG_L	x15, FREGS_A5(sp)
+	REG_L	x16, FREGS_A6(sp)
+	REG_L	x17, FREGS_A7(sp)
+
+	addi	sp, sp, FREGS_SIZE_ON_STACK
 	.endm
 
 	.macro PREPARE_ARGS
@@ -198,9 +137,9 @@
 	mv	a3, sp
 	.endm
 
-#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 
-#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
 SYM_FUNC_START(ftrace_caller)
 	SAVE_ABI
 
@@ -227,33 +166,23 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
 	jr	t0
 SYM_FUNC_END(ftrace_caller)
 
-#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
-SYM_FUNC_START(ftrace_regs_caller)
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
+SYM_FUNC_START(ftrace_caller)
 	mv	t1, zero
-	SAVE_ABI_REGS 1
+	SAVE_ABI_REGS
 	PREPARE_ARGS
 
-SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
-	RESTORE_ABI_REGS 1
+	RESTORE_ABI_REGS
 	bnez	t1, .Ldirect
 	jr	t0
 .Ldirect:
 	jr	t1
-SYM_FUNC_END(ftrace_regs_caller)
-
-SYM_FUNC_START(ftrace_caller)
-	SAVE_ABI_REGS 0
-	PREPARE_ARGS
-
-SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
-	call	ftrace_stub
-
-	RESTORE_ABI_REGS 0
-	jr	t0
 SYM_FUNC_END(ftrace_caller)
-#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 SYM_CODE_START(ftrace_stub_direct_tramp)
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 5e5a826444..906f9a3a5d 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/log2.h>
 #include <linux/moduleloader.h>
-#include <linux/vmalloc.h>
 #include <linux/sizes.h>
 #include <linux/pgtable.h>
 #include <asm/alternative.h>
@@ -905,17 +904,6 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 	return 0;
 }
 
-#if defined(CONFIG_MMU) && defined(CONFIG_64BIT)
-void *module_alloc(unsigned long size)
-{
-	return __vmalloc_node_range(size, 1, MODULES_VADDR,
-				    MODULES_END, GFP_KERNEL,
-				    PAGE_KERNEL, VM_FLUSH_RESET_PERMS,
-				    NUMA_NO_NODE,
-				    __builtin_return_address(0));
-}
-#endif
-
 int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
diff --git a/arch/riscv/kernel/paravirt.c b/arch/riscv/kernel/paravirt.c
index 0d6225fd31..fa6b0339a6 100644
--- a/arch/riscv/kernel/paravirt.c
+++ b/arch/riscv/kernel/paravirt.c
@@ -62,7 +62,7 @@ static int sbi_sta_steal_time_set_shmem(unsigned long lo, unsigned long hi,
 	ret = sbi_ecall(SBI_EXT_STA, SBI_EXT_STA_STEAL_TIME_SET_SHMEM,
 			lo, hi, flags, 0, 0, 0);
 	if (ret.error) {
-		if (lo == SBI_STA_SHMEM_DISABLE && hi == SBI_STA_SHMEM_DISABLE)
+		if (lo == SBI_SHMEM_DISABLE && hi == SBI_SHMEM_DISABLE)
 			pr_warn("Failed to disable steal-time shmem");
 		else
 			pr_warn("Failed to set steal-time shmem");
@@ -84,8 +84,8 @@ static int pv_time_cpu_online(unsigned int cpu)
 
 static int pv_time_cpu_down_prepare(unsigned int cpu)
 {
-	return sbi_sta_steal_time_set_shmem(SBI_STA_SHMEM_DISABLE,
-					    SBI_STA_SHMEM_DISABLE, 0);
+	return sbi_sta_steal_time_set_shmem(SBI_SHMEM_DISABLE,
+					    SBI_SHMEM_DISABLE, 0);
 }
 
 static u64 pv_time_steal_clock(int cpu)
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 30e12b310c..ab03732d06 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -89,6 +89,14 @@ static int __patch_insn_set(void *addr, u8 c, size_t len)
 
 	memset(waddr, c, len);
 
+	/*
+	 * We could have just patched a function that is about to be
+	 * called so make sure we don't execute partially patched
+	 * instructions by flushing the icache as soon as possible.
+	 */
+	local_flush_icache_range((unsigned long)waddr,
+				 (unsigned long)waddr + len);
+
 	patch_unmap(FIX_TEXT_POKE0);
 
 	if (across_pages)
@@ -135,6 +143,14 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len)
 
 	ret = copy_to_kernel_nofault(waddr, insn, len);
 
+	/*
+	 * We could have just patched a function that is about to be
+	 * called so make sure we don't execute partially patched
+	 * instructions by flushing the icache as soon as possible.
+	 */
+	local_flush_icache_range((unsigned long)waddr,
+				 (unsigned long)waddr + len);
+
 	patch_unmap(FIX_TEXT_POKE0);
 
 	if (across_pages)
@@ -189,14 +205,11 @@ int patch_text_set_nosync(void *addr, u8 c, size_t len)
 
 	ret = patch_insn_set(tp, c, len);
 
-	if (!ret)
-		flush_icache_range((uintptr_t)tp, (uintptr_t)tp + len);
-
 	return ret;
 }
 NOKPROBE_SYMBOL(patch_text_set_nosync);
 
-static int patch_insn_write(void *addr, const void *insn, size_t len)
+int patch_insn_write(void *addr, const void *insn, size_t len)
 {
 	size_t patched = 0;
 	size_t size;
@@ -224,9 +237,6 @@ int patch_text_nosync(void *addr, const void *insns, size_t len)
 
 	ret = patch_insn_write(tp, insns, len);
 
-	if (!ret)
-		flush_icache_range((uintptr_t) tp, (uintptr_t) tp + len);
-
 	return ret;
 }
 NOKPROBE_SYMBOL(patch_text_nosync);
@@ -240,14 +250,21 @@ static int patch_text_cb(void *data)
 	if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) {
 		for (i = 0; ret == 0 && i < patch->ninsns; i++) {
 			len = GET_INSN_LENGTH(patch->insns[i]);
-			ret = patch_text_nosync(patch->addr + i * len,
-						&patch->insns[i], len);
+			ret = patch_insn_write(patch->addr + i * len, &patch->insns[i], len);
 		}
-		atomic_inc(&patch->cpu_count);
+		/*
+		 * Make sure the patching store is effective *before* we
+		 * increment the counter which releases all waiting CPUs
+		 * by using the release variant of atomic increment. The
+		 * release pairs with the call to local_flush_icache_all()
+		 * on the waiting CPU.
+		 */
+		atomic_inc_return_release(&patch->cpu_count);
 	} else {
 		while (atomic_read(&patch->cpu_count) <= num_online_cpus())
 			cpu_relax();
-		smp_mb();
+
+		local_flush_icache_all();
 	}
 
 	return ret;
diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile
index b75f150b92..50bc5ef7dd 100644
--- a/arch/riscv/kernel/pi/Makefile
+++ b/arch/riscv/kernel/pi/Makefile
@@ -17,12 +17,6 @@ KBUILD_CFLAGS	+= -mcmodel=medany
 CFLAGS_cmdline_early.o += -D__NO_FORTIFY
 CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY
 
-GCOV_PROFILE	:= n
-KASAN_SANITIZE	:= n
-KCSAN_SANITIZE	:= n
-UBSAN_SANITIZE	:= n
-KCOV_INSTRUMENT	:= n
-
 $(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \
 			       --remove-section=.note.gnu.property \
 			       --prefix-alloc-sections=.init.pi
diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c
index 2f08c14a93..dfb28e57d9 100644
--- a/arch/riscv/kernel/probes/kprobes.c
+++ b/arch/riscv/kernel/probes/kprobes.c
@@ -6,6 +6,7 @@
 #include <linux/extable.h>
 #include <linux/slab.h>
 #include <linux/stop_machine.h>
+#include <linux/vmalloc.h>
 #include <asm/ptrace.h>
 #include <linux/uaccess.h>
 #include <asm/sections.h>
@@ -104,16 +105,6 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	return 0;
 }
 
-#ifdef CONFIG_MMU
-void *alloc_insn_page(void)
-{
-	return  __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END,
-				     GFP_KERNEL, PAGE_KERNEL_READ_EXEC,
-				     VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
-				     __builtin_return_address(0));
-}
-#endif
-
 /* install breakpoint in text */
 void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
diff --git a/arch/riscv/kernel/sbi-ipi.c b/arch/riscv/kernel/sbi-ipi.c
index a4559695ce..1026e22955 100644
--- a/arch/riscv/kernel/sbi-ipi.c
+++ b/arch/riscv/kernel/sbi-ipi.c
@@ -13,6 +13,9 @@
 #include <linux/irqdomain.h>
 #include <asm/sbi.h>
 
+DEFINE_STATIC_KEY_FALSE(riscv_sbi_for_rfence);
+EXPORT_SYMBOL_GPL(riscv_sbi_for_rfence);
+
 static int sbi_ipi_virq;
 
 static void sbi_ipi_handle(struct irq_desc *desc)
@@ -72,6 +75,12 @@ void __init sbi_ipi_init(void)
 			  "irqchip/sbi-ipi:starting",
 			  sbi_ipi_starting_cpu, NULL);
 
-	riscv_ipi_set_virq_range(virq, BITS_PER_BYTE, false);
+	riscv_ipi_set_virq_range(virq, BITS_PER_BYTE);
 	pr_info("providing IPIs using SBI IPI extension\n");
+
+	/*
+	 * Use the SBI remote fence extension to avoid
+	 * the extra context switch needed to handle IPIs.
+	 */
+	static_branch_enable(&riscv_sbi_for_rfence);
 }
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index 45dd403541..8e6eb64459 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -171,10 +171,7 @@ bool riscv_ipi_have_virq_range(void)
 	return (ipi_virq_base) ? true : false;
 }
 
-DEFINE_STATIC_KEY_FALSE(riscv_ipi_for_rfence);
-EXPORT_SYMBOL_GPL(riscv_ipi_for_rfence);
-
-void riscv_ipi_set_virq_range(int virq, int nr, bool use_for_rfence)
+void riscv_ipi_set_virq_range(int virq, int nr)
 {
 	int i, err;
 
@@ -197,12 +194,6 @@ void riscv_ipi_set_virq_range(int virq, int nr, bool use_for_rfence)
 
 	/* Enabled IPIs for boot CPU immediately */
 	riscv_ipi_enable();
-
-	/* Update RFENCE static key */
-	if (use_for_rfence)
-		static_branch_enable(&riscv_ipi_for_rfence);
-	else
-		static_branch_disable(&riscv_ipi_for_rfence);
 }
 
 static const char * const ipi_names[] = {
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 4b3c50da48..19baf0d574 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -214,6 +214,15 @@ asmlinkage __visible void smp_callin(void)
 	struct mm_struct *mm = &init_mm;
 	unsigned int curr_cpuid = smp_processor_id();
 
+	if (has_vector()) {
+		/*
+		 * Return as early as possible so the hart with a mismatching
+		 * vlen won't boot.
+		 */
+		if (riscv_v_setup_vsize())
+			return;
+	}
+
 	/* All kernel threads share the same mm context.  */
 	mmgrab(mm);
 	current->active_mm = mm;
@@ -224,12 +233,7 @@ asmlinkage __visible void smp_callin(void)
 	riscv_ipi_enable();
 
 	numa_add_cpu(curr_cpuid);
-	set_cpu_online(curr_cpuid, 1);
-
-	if (has_vector()) {
-		if (riscv_v_setup_vsize())
-			elf_hwcap &= ~COMPAT_HWCAP_ISA_V;
-	}
+	set_cpu_online(curr_cpuid, true);
 
 	riscv_user_isa_enable();
 
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index 8a327b485b..c8cec0cc58 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -14,7 +14,6 @@
 
 void suspend_save_csrs(struct suspend_context *context)
 {
-	context->scratch = csr_read(CSR_SCRATCH);
 	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG))
 		context->envcfg = csr_read(CSR_ENVCFG);
 	context->tvec = csr_read(CSR_TVEC);
@@ -37,7 +36,7 @@ void suspend_save_csrs(struct suspend_context *context)
 
 void suspend_restore_csrs(struct suspend_context *context)
 {
-	csr_write(CSR_SCRATCH, context->scratch);
+	csr_write(CSR_SCRATCH, 0);
 	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG))
 		csr_write(CSR_ENVCFG, context->envcfg);
 	csr_write(CSR_TVEC, context->tvec);
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index 8cae41a502..969ef3d59d 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -111,6 +111,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		EXT_KEY(ZTSO);
 		EXT_KEY(ZACAS);
 		EXT_KEY(ZICOND);
+		EXT_KEY(ZIHINTPAUSE);
 
 		if (has_vector()) {
 			EXT_KEY(ZVBB);
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index f1c1416a9f..d77afe0557 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -7,7 +7,6 @@
 
 #include <linux/syscalls.h>
 #include <asm/cacheflush.h>
-#include <asm-generic/mman-common.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 			   unsigned long prot, unsigned long flags,
@@ -24,7 +23,7 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 #ifdef CONFIG_64BIT
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 	unsigned long, prot, unsigned long, flags,
-	unsigned long, fd, off_t, offset)
+	unsigned long, fd, unsigned long, offset)
 {
 	return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 0);
 }
@@ -33,7 +32,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 #if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT)
 SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
 	unsigned long, prot, unsigned long, flags,
-	unsigned long, fd, off_t, offset)
+	unsigned long, fd, unsigned long, offset)
 {
 	/*
 	 * Note that the shift for mmap2 is constant (12),
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 2adb7c3e4d..b62d5a2f45 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -264,86 +264,14 @@ static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset,
 #define GET_F32_RS2C(insn, regs) (get_f32_rs(insn, 2, regs))
 #define GET_F32_RS2S(insn, regs) (get_f32_rs(RVC_RS2S(insn), 0, regs))
 
-#ifdef CONFIG_RISCV_M_MODE
-static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val)
-{
-	u8 val;
-
-	asm volatile("lbu %0, %1" : "=&r" (val) : "m" (*addr));
-	*r_val = val;
-
-	return 0;
-}
-
-static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val)
-{
-	asm volatile ("sb %0, %1\n" : : "r" (val), "m" (*addr));
-
-	return 0;
-}
-
-static inline int get_insn(struct pt_regs *regs, ulong mepc, ulong *r_insn)
-{
-	register ulong __mepc asm ("a2") = mepc;
-	ulong val, rvc_mask = 3, tmp;
-
-	asm ("and %[tmp], %[addr], 2\n"
-		"bnez %[tmp], 1f\n"
-#if defined(CONFIG_64BIT)
-		__stringify(LWU) " %[insn], (%[addr])\n"
-#else
-		__stringify(LW) " %[insn], (%[addr])\n"
-#endif
-		"and %[tmp], %[insn], %[rvc_mask]\n"
-		"beq %[tmp], %[rvc_mask], 2f\n"
-		"sll %[insn], %[insn], %[xlen_minus_16]\n"
-		"srl %[insn], %[insn], %[xlen_minus_16]\n"
-		"j 2f\n"
-		"1:\n"
-		"lhu %[insn], (%[addr])\n"
-		"and %[tmp], %[insn], %[rvc_mask]\n"
-		"bne %[tmp], %[rvc_mask], 2f\n"
-		"lhu %[tmp], 2(%[addr])\n"
-		"sll %[tmp], %[tmp], 16\n"
-		"add %[insn], %[insn], %[tmp]\n"
-		"2:"
-	: [insn] "=&r" (val), [tmp] "=&r" (tmp)
-	: [addr] "r" (__mepc), [rvc_mask] "r" (rvc_mask),
-	  [xlen_minus_16] "i" (XLEN_MINUS_16));
-
-	*r_insn = val;
-
-	return 0;
-}
-#else
-static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val)
-{
-	if (user_mode(regs)) {
-		return __get_user(*r_val, (u8 __user *)addr);
-	} else {
-		*r_val = *addr;
-		return 0;
-	}
-}
-
-static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val)
-{
-	if (user_mode(regs)) {
-		return __put_user(val, (u8 __user *)addr);
-	} else {
-		*addr = val;
-		return 0;
-	}
-}
-
-#define __read_insn(regs, insn, insn_addr)		\
+#define __read_insn(regs, insn, insn_addr, type)	\
 ({							\
 	int __ret;					\
 							\
 	if (user_mode(regs)) {				\
-		__ret = __get_user(insn, insn_addr);	\
+		__ret = __get_user(insn, (type __user *) insn_addr); \
 	} else {					\
-		insn = *(__force u16 *)insn_addr;	\
+		insn = *(type *)insn_addr;		\
 		__ret = 0;				\
 	}						\
 							\
@@ -356,9 +284,8 @@ static inline int get_insn(struct pt_regs *regs, ulong epc, ulong *r_insn)
 
 	if (epc & 0x2) {
 		ulong tmp = 0;
-		u16 __user *insn_addr = (u16 __user *)epc;
 
-		if (__read_insn(regs, insn, insn_addr))
+		if (__read_insn(regs, insn, epc, u16))
 			return -EFAULT;
 		/* __get_user() uses regular "lw" which sign extend the loaded
 		 * value make sure to clear higher order bits in case we "or" it
@@ -369,16 +296,14 @@ static inline int get_insn(struct pt_regs *regs, ulong epc, ulong *r_insn)
 			*r_insn = insn;
 			return 0;
 		}
-		insn_addr++;
-		if (__read_insn(regs, tmp, insn_addr))
+		epc += sizeof(u16);
+		if (__read_insn(regs, tmp, epc, u16))
 			return -EFAULT;
 		*r_insn = (tmp << 16) | insn;
 
 		return 0;
 	} else {
-		u32 __user *insn_addr = (u32 __user *)epc;
-
-		if (__read_insn(regs, insn, insn_addr))
+		if (__read_insn(regs, insn, epc, u32))
 			return -EFAULT;
 		if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) {
 			*r_insn = insn;
@@ -390,7 +315,6 @@ static inline int get_insn(struct pt_regs *regs, ulong epc, ulong *r_insn)
 		return 0;
 	}
 }
-#endif
 
 union reg_data {
 	u8 data_bytes[8];
@@ -409,7 +333,7 @@ int handle_misaligned_load(struct pt_regs *regs)
 	unsigned long epc = regs->epc;
 	unsigned long insn;
 	unsigned long addr = regs->badaddr;
-	int i, fp = 0, shift = 0, len = 0;
+	int fp = 0, shift = 0, len = 0;
 
 	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
 
@@ -492,9 +416,11 @@ int handle_misaligned_load(struct pt_regs *regs)
 		return -EOPNOTSUPP;
 
 	val.data_u64 = 0;
-	for (i = 0; i < len; i++) {
-		if (load_u8(regs, (void *)(addr + i), &val.data_bytes[i]))
+	if (user_mode(regs)) {
+		if (raw_copy_from_user(&val, (u8 __user *)addr, len))
 			return -1;
+	} else {
+		memcpy(&val, (u8 *)addr, len);
 	}
 
 	if (!fp)
@@ -515,7 +441,7 @@ int handle_misaligned_store(struct pt_regs *regs)
 	unsigned long epc = regs->epc;
 	unsigned long insn;
 	unsigned long addr = regs->badaddr;
-	int i, len = 0, fp = 0;
+	int len = 0, fp = 0;
 
 	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
 
@@ -588,9 +514,11 @@ int handle_misaligned_store(struct pt_regs *regs)
 	if (!IS_ENABLED(CONFIG_FPU) && fp)
 		return -EOPNOTSUPP;
 
-	for (i = 0; i < len; i++) {
-		if (store_u8(regs, (void *)(addr + i), val.data_bytes[i]))
+	if (user_mode(regs)) {
+		if (raw_copy_to_user((u8 __user *)addr, &val, len))
 			return -1;
+	} else {
+		memcpy((u8 *)addr, &val, len);
 	}
 
 	regs->epc = epc + INSN_LEN(insn);
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 272c431ac5..f7ef8ad9b5 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -39,12 +39,6 @@ endif
 CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
 CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
 
-# Disable profiling and instrumentation for VDSO code
-GCOV_PROFILE := n
-KCOV_INSTRUMENT := n
-KASAN_SANITIZE := n
-UBSAN_SANITIZE := n
-
 # Force dependency
 $(obj)/vdso.o: $(obj)/vdso.so
 
@@ -60,7 +54,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
 # Generate VDSO offsets using helper script
-gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh
+gen-vdsosym := $(src)/gen_vdso_offsets.sh
 quiet_cmd_vdsosym = VDSOSYM $@
 	cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@