Merge tag 'riscv-for-linus-6.8-mw4' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull more RISC-V updates from Palmer Dabbelt:

 - Support for tuning for systems with fast misaligned accesses.

 - Support for SBI-based suspend.

 - Support for the new SBI debug console extension.

 - The T-Head CMOs now use PA-based flushes.

 - Support for enabling the V extension in kernel code.

 - Optimized IP checksum routines.

 - Various ftrace improvements.

 - Support for archrandom, which depends on the Zkr extension.

 - The build is no longer broken under NET=n, KUNIT=y for ports that
   don't define their own ipv6 checksum.

* tag 'riscv-for-linus-6.8-mw4' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (56 commits)
  lib: checksum: Fix build with CONFIG_NET=n
  riscv: lib: Check if output in asm goto supported
  riscv: Fix build error on rv32 + XIP
  riscv: optimize ELF relocation function in riscv
  RISC-V: Implement archrandom when Zkr is available
  riscv: Optimize hweight API with Zbb extension
  riscv: add dependency among Image(.gz), loader(.bin), and vmlinuz.efi
  samples: ftrace: Add RISC-V support for SAMPLE_FTRACE_DIRECT[_MULTI]
  riscv: ftrace: Add DYNAMIC_FTRACE_WITH_DIRECT_CALLS support
  riscv: ftrace: Make function graph use ftrace directly
  riscv: select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
  lib/Kconfig.debug: Update AS_HAS_NON_CONST_LEB128 comment and name
  riscv: Restrict DWARF5 when building with LLVM to known working versions
  riscv: Hoist linker relaxation disabling logic into Kconfig
  kunit: Add tests for csum_ipv6_magic and ip_fast_csum
  riscv: Add checksum library
  riscv: Add checksum header
  riscv: Add static key for misaligned accesses
  asm-generic: Improve csum_fold
  RISC-V: selftests: cbo: Ensure asm operands match constraints
  ...

14 files changed, 720 insertions, 81 deletions

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index c92c623b311e..f71910718053 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -64,6 +64,7 @@ obj-$(CONFIG_MMU) += vdso.o vdso/
 obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
+obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SMP)		+= cpu_ops.o
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index e32591e9da90..89920f84d0a3 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -8,8 +8,10 @@
 
 #include <linux/acpi.h>
 #include <linux/bitmap.h>
+#include <linux/cpu.h>
 #include <linux/cpuhotplug.h>
 #include <linux/ctype.h>
+#include <linux/jump_label.h>
 #include <linux/log2.h>
 #include <linux/memory.h>
 #include <linux/module.h>
@@ -44,6 +46,8 @@ struct riscv_isainfo hart_isa[NR_CPUS];
 /* Performance information */
 DEFINE_PER_CPU(long, misaligned_access_speed);
 
+static cpumask_t fast_misaligned_access;
+
 /**
  * riscv_isa_extension_base() - Get base extension word
  *
@@ -784,6 +788,16 @@ static int check_unaligned_access(void *param)
 		(speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
 
 	per_cpu(misaligned_access_speed, cpu) = speed;
+
+	/*
+	 * Set the value of fast_misaligned_access of a CPU. These operations
+	 * are atomic to avoid race conditions.
+	 */
+	if (speed == RISCV_HWPROBE_MISALIGNED_FAST)
+		cpumask_set_cpu(cpu, &fast_misaligned_access);
+	else
+		cpumask_clear_cpu(cpu, &fast_misaligned_access);
+
 	return 0;
 }
 
@@ -796,13 +810,69 @@ static void check_unaligned_access_nonboot_cpu(void *param)
 		check_unaligned_access(pages[cpu]);
 }
 
+DEFINE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
+
+static void modify_unaligned_access_branches(cpumask_t *mask, int weight)
+{
+	if (cpumask_weight(mask) == weight)
+		static_branch_enable_cpuslocked(&fast_misaligned_access_speed_key);
+	else
+		static_branch_disable_cpuslocked(&fast_misaligned_access_speed_key);
+}
+
+static void set_unaligned_access_static_branches_except_cpu(int cpu)
+{
+	/*
+	 * Same as set_unaligned_access_static_branches, except excludes the
+	 * given CPU from the result. When a CPU is hotplugged into an offline
+	 * state, this function is called before the CPU is set to offline in
+	 * the cpumask, and thus the CPU needs to be explicitly excluded.
+	 */
+
+	cpumask_t fast_except_me;
+
+	cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask);
+	cpumask_clear_cpu(cpu, &fast_except_me);
+
+	modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1);
+}
+
+static void set_unaligned_access_static_branches(void)
+{
+	/*
+	 * This will be called after check_unaligned_access_all_cpus so the
+	 * result of unaligned access speed for all CPUs will be available.
+	 *
+	 * To avoid the number of online cpus changing between reading
+	 * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be
+	 * held before calling this function.
+	 */
+
+	cpumask_t fast_and_online;
+
+	cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask);
+
+	modify_unaligned_access_branches(&fast_and_online, num_online_cpus());
+}
+
+static int lock_and_set_unaligned_access_static_branch(void)
+{
+	cpus_read_lock();
+	set_unaligned_access_static_branches();
+	cpus_read_unlock();
+
+	return 0;
+}
+
+arch_initcall_sync(lock_and_set_unaligned_access_static_branch);
+
 static int riscv_online_cpu(unsigned int cpu)
 {
 	static struct page *buf;
 
 	/* We are already set since the last check */
 	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
-		return 0;
+		goto exit;
 
 	buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
 	if (!buf) {
@@ -812,6 +882,17 @@ static int riscv_online_cpu(unsigned int cpu)
 
 	check_unaligned_access(buf);
 	__free_pages(buf, MISALIGNED_BUFFER_ORDER);
+
+exit:
+	set_unaligned_access_static_branches();
+
+	return 0;
+}
+
+static int riscv_offline_cpu(unsigned int cpu)
+{
+	set_unaligned_access_static_branches_except_cpu(cpu);
+
 	return 0;
 }
 
@@ -846,9 +927,12 @@ static int check_unaligned_access_all_cpus(void)
 	/* Check core 0. */
 	smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
 
-	/* Setup hotplug callback for any new CPUs that come online. */
+	/*
+	 * Setup hotplug callbacks for any new CPUs that come online or go
+	 * offline.
+	 */
 	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
-				  riscv_online_cpu, NULL);
+				  riscv_online_cpu, riscv_offline_cpu);
 
 out:
 	unaligned_emulation_finish();
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 54ca4564a926..9d1a305d5508 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -83,6 +83,10 @@ SYM_CODE_START(handle_exception)
 	/* Load the kernel shadow call stack pointer if coming from userspace */
 	scs_load_current_if_task_changed s5
 
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	move a0, sp
+	call riscv_v_context_nesting_start
+#endif
 	move a0, sp /* pt_regs */
 	la ra, ret_from_exception
 
@@ -138,6 +142,10 @@ SYM_CODE_START_NOALIGN(ret_from_exception)
 	 */
 	csrw CSR_SCRATCH, tp
 1:
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	move a0, sp
+	call riscv_v_context_nesting_end
+#endif
 	REG_L a0, PT_STATUS(sp)
 	/*
 	 * The current load reservation is effectively part of the processor's
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 03a6434a8cdd..f5aa24d9e1c1 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -178,32 +178,28 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+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));
+}
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 extern void ftrace_graph_call(void);
-extern void ftrace_graph_regs_call(void);
 int ftrace_enable_ftrace_graph_caller(void)
 {
-	int ret;
-
-	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
-				    (unsigned long)&prepare_ftrace_return, true, true);
-	if (ret)
-		return ret;
-
-	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
 				    (unsigned long)&prepare_ftrace_return, true, true);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
-	int ret;
-
-	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
-				    (unsigned long)&prepare_ftrace_return, false, true);
-	if (ret)
-		return ret;
-
-	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+	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 */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
new file mode 100644
index 000000000000..6afe80c7f03a
--- /dev/null
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -0,0 +1,247 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2021 SiFive
+ */
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+#include <asm/vector.h>
+#include <asm/switch_to.h>
+#include <asm/simd.h>
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+#include <asm/asm-prototypes.h>
+#endif
+
+static inline void riscv_v_flags_set(u32 flags)
+{
+	WRITE_ONCE(current->thread.riscv_v_flags, flags);
+}
+
+static inline void riscv_v_start(u32 flags)
+{
+	int orig;
+
+	orig = riscv_v_flags();
+	BUG_ON((orig & flags) != 0);
+	riscv_v_flags_set(orig | flags);
+	barrier();
+}
+
+static inline void riscv_v_stop(u32 flags)
+{
+	int orig;
+
+	barrier();
+	orig = riscv_v_flags();
+	BUG_ON((orig & flags) == 0);
+	riscv_v_flags_set(orig & ~flags);
+}
+
+/*
+ * Claim ownership of the CPU vector context for use by the calling context.
+ *
+ * The caller may freely manipulate the vector context metadata until
+ * put_cpu_vector_context() is called.
+ */
+void get_cpu_vector_context(void)
+{
+	/*
+	 * disable softirqs so it is impossible for softirqs to nest
+	 * get_cpu_vector_context() when kernel is actively using Vector.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_disable();
+	else
+		preempt_disable();
+
+	riscv_v_start(RISCV_KERNEL_MODE_V);
+}
+
+/*
+ * Release the CPU vector context.
+ *
+ * Must be called from a context in which get_cpu_vector_context() was
+ * previously called, with no call to put_cpu_vector_context() in the
+ * meantime.
+ */
+void put_cpu_vector_context(void)
+{
+	riscv_v_stop(RISCV_KERNEL_MODE_V);
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_enable();
+	else
+		preempt_enable();
+}
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static __always_inline u32 *riscv_v_flags_ptr(void)
+{
+	return &current->thread.riscv_v_flags;
+}
+
+static inline void riscv_preempt_v_set_dirty(void)
+{
+	*riscv_v_flags_ptr() |= RISCV_PREEMPT_V_DIRTY;
+}
+
+static inline void riscv_preempt_v_reset_flags(void)
+{
+	*riscv_v_flags_ptr() &= ~(RISCV_PREEMPT_V_DIRTY | RISCV_PREEMPT_V_NEED_RESTORE);
+}
+
+static inline void riscv_v_ctx_depth_inc(void)
+{
+	*riscv_v_flags_ptr() += RISCV_V_CTX_UNIT_DEPTH;
+}
+
+static inline void riscv_v_ctx_depth_dec(void)
+{
+	*riscv_v_flags_ptr() -= RISCV_V_CTX_UNIT_DEPTH;
+}
+
+static inline u32 riscv_v_ctx_get_depth(void)
+{
+	return *riscv_v_flags_ptr() & RISCV_V_CTX_DEPTH_MASK;
+}
+
+static int riscv_v_stop_kernel_context(void)
+{
+	if (riscv_v_ctx_get_depth() != 0 || !riscv_preempt_v_started(current))
+		return 1;
+
+	riscv_preempt_v_clear_dirty(current);
+	riscv_v_stop(RISCV_PREEMPT_V);
+	return 0;
+}
+
+static int riscv_v_start_kernel_context(bool *is_nested)
+{
+	struct __riscv_v_ext_state *kvstate, *uvstate;
+
+	kvstate = &current->thread.kernel_vstate;
+	if (!kvstate->datap)
+		return -ENOENT;
+
+	if (riscv_preempt_v_started(current)) {
+		WARN_ON(riscv_v_ctx_get_depth() == 0);
+		*is_nested = true;
+		get_cpu_vector_context();
+		if (riscv_preempt_v_dirty(current)) {
+			__riscv_v_vstate_save(kvstate, kvstate->datap);
+			riscv_preempt_v_clear_dirty(current);
+		}
+		riscv_preempt_v_set_restore(current);
+		return 0;
+	}
+
+	/* Transfer the ownership of V from user to kernel, then save */
+	riscv_v_start(RISCV_PREEMPT_V | RISCV_PREEMPT_V_DIRTY);
+	if ((task_pt_regs(current)->status & SR_VS) == SR_VS_DIRTY) {
+		uvstate = &current->thread.vstate;
+		__riscv_v_vstate_save(uvstate, uvstate->datap);
+	}
+	riscv_preempt_v_clear_dirty(current);
+	return 0;
+}
+
+/* low-level V context handling code, called with irq disabled */
+asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs)
+{
+	int depth;
+
+	if (!riscv_preempt_v_started(current))
+		return;
+
+	depth = riscv_v_ctx_get_depth();
+	if (depth == 0 && (regs->status & SR_VS) == SR_VS_DIRTY)
+		riscv_preempt_v_set_dirty();
+
+	riscv_v_ctx_depth_inc();
+}
+
+asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs)
+{
+	struct __riscv_v_ext_state *vstate = &current->thread.kernel_vstate;
+	u32 depth;
+
+	WARN_ON(!irqs_disabled());
+
+	if (!riscv_preempt_v_started(current))
+		return;
+
+	riscv_v_ctx_depth_dec();
+	depth = riscv_v_ctx_get_depth();
+	if (depth == 0) {
+		if (riscv_preempt_v_restore(current)) {
+			__riscv_v_vstate_restore(vstate, vstate->datap);
+			__riscv_v_vstate_clean(regs);
+			riscv_preempt_v_reset_flags();
+		}
+	}
+}
+#else
+#define riscv_v_start_kernel_context(nested)	(-ENOENT)
+#define riscv_v_stop_kernel_context()		(-ENOENT)
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
+/*
+ * kernel_vector_begin(): obtain the CPU vector registers for use by the calling
+ * context
+ *
+ * Must not be called unless may_use_simd() returns true.
+ * Task context in the vector registers is saved back to memory as necessary.
+ *
+ * A matching call to kernel_vector_end() must be made before returning from the
+ * calling context.
+ *
+ * The caller may freely use the vector registers until kernel_vector_end() is
+ * called.
+ */
+void kernel_vector_begin(void)
+{
+	bool nested = false;
+
+	if (WARN_ON(!has_vector()))
+		return;
+
+	BUG_ON(!may_use_simd());
+
+	if (riscv_v_start_kernel_context(&nested)) {
+		get_cpu_vector_context();
+		riscv_v_vstate_save(&current->thread.vstate, task_pt_regs(current));
+	}
+
+	if (!nested)
+		riscv_v_vstate_set_restore(current, task_pt_regs(current));
+
+	riscv_v_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_begin);
+
+/*
+ * kernel_vector_end(): give the CPU vector registers back to the current task
+ *
+ * Must be called from a context in which kernel_vector_begin() was previously
+ * called, with no call to kernel_vector_end() in the meantime.
+ *
+ * The caller must not use the vector registers after this function is called,
+ * unless kernel_vector_begin() is called again in the meantime.
+ */
+void kernel_vector_end(void)
+{
+	if (WARN_ON(!has_vector()))
+		return;
+
+	riscv_v_disable();
+
+	if (riscv_v_stop_kernel_context())
+		put_cpu_vector_context();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_end);
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index 79dc81223238..b7561288e8da 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -57,31 +57,150 @@
 	.endm
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-	.macro SAVE_ALL
+
+/**
+* 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.
+*
+* 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
+* 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.
+*
+* The other regs are saved at the respective localtion and accessed
+* by the respective pt_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    +   +
+*                       + 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)
-	REG_S x2,  PT_SP(sp)
-	REG_S x3,  PT_GP(sp)
-	REG_S x4,  PT_TP(sp)
-	REG_S x5,  PT_T0(sp)
-	save_from_x6_to_x31
+	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
+
+	.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
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	REG_S	x8, PT_S0(sp)
+#endif
+	.endif
 	.endm
 
-	.macro RESTORE_ALL
-	REG_L x1,  PT_RA(sp)
-	REG_L x2,  PT_SP(sp)
-	REG_L x3,  PT_GP(sp)
-	REG_L x4,  PT_TP(sp)
-	/* Restore t0 with PT_EPC */
-	REG_L x5,  PT_EPC(sp)
-	restore_from_x6_to_x31
+	.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
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	REG_L	x8, PT_S0(sp)
+#endif
+	.endif
 	addi	sp, sp, PT_SIZE_ON_STACK
 	.endm
+
+	.macro PREPARE_ARGS
+	addi	a0, t0, -FENTRY_RA_OFFSET
+	la	a1, function_trace_op
+	REG_L	a2, 0(a1)
+	mv	a1, ra
+	mv	a3, sp
+	.endm
+
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
+#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 SYM_FUNC_START(ftrace_caller)
 	SAVE_ABI
 
@@ -105,34 +224,39 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 #endif
 	RESTORE_ABI
-	jr t0
+	jr	t0
 SYM_FUNC_END(ftrace_caller)
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 SYM_FUNC_START(ftrace_regs_caller)
-	SAVE_ALL
-
-	addi	a0, t0, -FENTRY_RA_OFFSET
-	la	a1, function_trace_op
-	REG_L	a2, 0(a1)
-	mv	a1, ra
-	mv	a3, sp
+	mv	t1, zero
+	SAVE_ABI_REGS 1
+	PREPARE_ARGS
 
 SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	addi	a0, sp, PT_RA
-	REG_L	a1, PT_EPC(sp)
-	addi	a1, a1, -FENTRY_RA_OFFSET
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	mv	a2, s0
-#endif
-SYM_INNER_LABEL(ftrace_graph_regs_call, SYM_L_GLOBAL)
+	RESTORE_ABI_REGS 1
+	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
-#endif
 
-	RESTORE_ALL
-	jr t0
-SYM_FUNC_END(ftrace_regs_caller)
+	RESTORE_ABI_REGS 0
+	jr	t0
+SYM_FUNC_END(ftrace_caller)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+SYM_CODE_START(ftrace_stub_direct_tramp)
+	jr	t0
+SYM_CODE_END(ftrace_stub_direct_tramp)
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 862834bb1d64..5e5a82644451 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -723,8 +723,8 @@ static int add_relocation_to_accumulate(struct module *me, int type,
 
 			if (!bucket) {
 				kfree(entry);
-				kfree(rel_head);
 				kfree(rel_head->rel_entry);
+				kfree(rel_head);
 				return -ENOMEM;
 			}
 
@@ -747,6 +747,10 @@ initialize_relocation_hashtable(unsigned int num_relocations,
 {
 	/* Can safely assume that bits is not greater than sizeof(long) */
 	unsigned long hashtable_size = roundup_pow_of_two(num_relocations);
+	/*
+	 * When hashtable_size == 1, hashtable_bits == 0.
+	 * This is valid because the hashing algorithm returns 0 in this case.
+	 */
 	unsigned int hashtable_bits = ilog2(hashtable_size);
 
 	/*
@@ -760,10 +764,10 @@ initialize_relocation_hashtable(unsigned int num_relocations,
 	hashtable_size <<= should_double_size;
 
 	*relocation_hashtable = kmalloc_array(hashtable_size,
-					      sizeof(*relocation_hashtable),
+					      sizeof(**relocation_hashtable),
 					      GFP_KERNEL);
 	if (!*relocation_hashtable)
-		return -ENOMEM;
+		return 0;
 
 	__hash_init(*relocation_hashtable, hashtable_size);
 
@@ -779,6 +783,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 	Elf_Sym *sym;
 	void *location;
 	unsigned int i, type;
+	unsigned int j_idx = 0;
 	Elf_Addr v;
 	int res;
 	unsigned int num_relocations = sechdrs[relsec].sh_size / sizeof(*rel);
@@ -789,8 +794,8 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 	hashtable_bits = initialize_relocation_hashtable(num_relocations,
 							 &relocation_hashtable);
 
-	if (hashtable_bits < 0)
-		return hashtable_bits;
+	if (!relocation_hashtable)
+		return -ENOMEM;
 
 	INIT_LIST_HEAD(&used_buckets_list);
 
@@ -829,9 +834,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 		v = sym->st_value + rel[i].r_addend;
 
 		if (type == R_RISCV_PCREL_LO12_I || type == R_RISCV_PCREL_LO12_S) {
-			unsigned int j;
+			unsigned int j = j_idx;
+			bool found = false;
 
-			for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
+			do {
 				unsigned long hi20_loc =
 					sechdrs[sechdrs[relsec].sh_info].sh_addr
 					+ rel[j].r_offset;
@@ -860,16 +866,26 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 					hi20 = (offset + 0x800) & 0xfffff000;
 					lo12 = offset - hi20;
 					v = lo12;
+					found = true;
 
 					break;
 				}
-			}
-			if (j == sechdrs[relsec].sh_size / sizeof(*rel)) {
+
+				j++;
+				if (j > sechdrs[relsec].sh_size / sizeof(*rel))
+					j = 0;
+
+			} while (j_idx != j);
+
+			if (!found) {
 				pr_err(
 				  "%s: Can not find HI20 relocation information\n",
 				  me->name);
 				return -EINVAL;
 			}
+
+			/* Record the previous j-loop end index */
+			j_idx = j;
 		}
 
 		if (reloc_handlers[type].accumulate_handler)
diff --git a/arch/riscv/kernel/pi/cmdline_early.c b/arch/riscv/kernel/pi/cmdline_early.c
index 68e786c84c94..f6d4dedffb84 100644
--- a/arch/riscv/kernel/pi/cmdline_early.c
+++ b/arch/riscv/kernel/pi/cmdline_early.c
@@ -38,8 +38,7 @@ static char *get_early_cmdline(uintptr_t dtb_pa)
 	if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) ||
 	    IS_ENABLED(CONFIG_CMDLINE_FORCE) ||
 	    fdt_cmdline_size == 0 /* CONFIG_CMDLINE_FALLBACK */) {
-		strncat(early_cmdline, CONFIG_CMDLINE,
-			COMMAND_LINE_SIZE - fdt_cmdline_size);
+		strlcat(early_cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
 	}
 
 	return early_cmdline;
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 4f21d970a129..92922dbd5b5c 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -171,6 +171,7 @@ void flush_thread(void)
 	riscv_v_vstate_off(task_pt_regs(current));
 	kfree(current->thread.vstate.datap);
 	memset(&current->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	clear_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE);
 #endif
 }
 
@@ -178,7 +179,7 @@ void arch_release_task_struct(struct task_struct *tsk)
 {
 	/* Free the vector context of datap. */
 	if (has_vector())
-		kfree(tsk->thread.vstate.datap);
+		riscv_v_thread_free(tsk);
 }
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
@@ -187,6 +188,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	*dst = *src;
 	/* clear entire V context, including datap for a new task */
 	memset(&dst->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	memset(&dst->thread.kernel_vstate, 0, sizeof(struct __riscv_v_ext_state));
+	clear_tsk_thread_flag(dst, TIF_RISCV_V_DEFER_RESTORE);
 
 	return 0;
 }
@@ -221,7 +224,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		childregs->a0 = 0; /* Return value of fork() */
 		p->thread.s[0] = 0;
 	}
+	p->thread.riscv_v_flags = 0;
+	if (has_vector())
+		riscv_v_thread_alloc(p);
 	p->thread.ra = (unsigned long)ret_from_fork;
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
 }
+
+void __init arch_task_cache_init(void)
+{
+	riscv_v_setup_ctx_cache();
+}
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 2afe460de16a..e8515aa9d80b 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -99,8 +99,11 @@ static int riscv_vr_get(struct task_struct *target,
 	 * Ensure the vector registers have been saved to the memory before
 	 * copying them to membuf.
 	 */
-	if (target == current)
-		riscv_v_vstate_save(current, task_pt_regs(current));
+	if (target == current) {
+		get_cpu_vector_context();
+		riscv_v_vstate_save(&current->thread.vstate, task_pt_regs(current));
+		put_cpu_vector_context();
+	}
 
 	ptrace_vstate.vstart = vstate->vstart;
 	ptrace_vstate.vl = vstate->vl;
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index 5a62ed1da453..e66e0999a800 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -7,6 +7,7 @@
 
 #include <linux/bits.h>
 #include <linux/init.h>
+#include <linux/mm.h>
 #include <linux/pm.h>
 #include <linux/reboot.h>
 #include <asm/sbi.h>
@@ -571,6 +572,66 @@ long sbi_get_mimpid(void)
 }
 EXPORT_SYMBOL_GPL(sbi_get_mimpid);
 
+bool sbi_debug_console_available;
+
+int sbi_debug_console_write(const char *bytes, unsigned int num_bytes)
+{
+	phys_addr_t base_addr;
+	struct sbiret ret;
+
+	if (!sbi_debug_console_available)
+		return -EOPNOTSUPP;
+
+	if (is_vmalloc_addr(bytes))
+		base_addr = page_to_phys(vmalloc_to_page(bytes)) +
+			    offset_in_page(bytes);
+	else
+		base_addr = __pa(bytes);
+	if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes))
+		num_bytes = PAGE_SIZE - offset_in_page(bytes);
+
+	if (IS_ENABLED(CONFIG_32BIT))
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE,
+				num_bytes, lower_32_bits(base_addr),
+				upper_32_bits(base_addr), 0, 0, 0);
+	else
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE,
+				num_bytes, base_addr, 0, 0, 0, 0);
+
+	if (ret.error == SBI_ERR_FAILURE)
+		return -EIO;
+	return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value;
+}
+
+int sbi_debug_console_read(char *bytes, unsigned int num_bytes)
+{
+	phys_addr_t base_addr;
+	struct sbiret ret;
+
+	if (!sbi_debug_console_available)
+		return -EOPNOTSUPP;
+
+	if (is_vmalloc_addr(bytes))
+		base_addr = page_to_phys(vmalloc_to_page(bytes)) +
+			    offset_in_page(bytes);
+	else
+		base_addr = __pa(bytes);
+	if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes))
+		num_bytes = PAGE_SIZE - offset_in_page(bytes);
+
+	if (IS_ENABLED(CONFIG_32BIT))
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ,
+				num_bytes, lower_32_bits(base_addr),
+				upper_32_bits(base_addr), 0, 0, 0);
+	else
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ,
+				num_bytes, base_addr, 0, 0, 0, 0);
+
+	if (ret.error == SBI_ERR_FAILURE)
+		return -EIO;
+	return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value;
+}
+
 void __init sbi_init(void)
 {
 	int ret;
@@ -612,6 +673,11 @@ void __init sbi_init(void)
 			sbi_srst_reboot_nb.priority = 192;
 			register_restart_handler(&sbi_srst_reboot_nb);
 		}
+		if ((sbi_spec_version >= sbi_mk_version(2, 0)) &&
+		    (sbi_probe_extension(SBI_EXT_DBCN) > 0)) {
+			pr_info("SBI DBCN extension detected\n");
+			sbi_debug_console_available = true;
+		}
 	} else {
 		__sbi_set_timer = __sbi_set_timer_v01;
 		__sbi_send_ipi	= __sbi_send_ipi_v01;
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 33dfb5078301..501e66debf69 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -86,7 +86,10 @@ static long save_v_state(struct pt_regs *regs, void __user **sc_vec)
 	/* datap is designed to be 16 byte aligned for better performance */
 	WARN_ON(unlikely(!IS_ALIGNED((unsigned long)datap, 16)));
 
-	riscv_v_vstate_save(current, regs);
+	get_cpu_vector_context();
+	riscv_v_vstate_save(&current->thread.vstate, regs);
+	put_cpu_vector_context();
+
 	/* Copy everything of vstate but datap. */
 	err = __copy_to_user(&state->v_state, &current->thread.vstate,
 			     offsetof(struct __riscv_v_ext_state, datap));
@@ -134,7 +137,7 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
 	if (unlikely(err))
 		return err;
 
-	riscv_v_vstate_restore(current, regs);
+	riscv_v_vstate_set_restore(current, regs);
 
 	return err;
 }
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index 3c89b8ec69c4..239509367e42 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -4,8 +4,12 @@
  * Copyright (c) 2022 Ventana Micro Systems Inc.
  */
 
+#define pr_fmt(fmt) "suspend: " fmt
+
 #include <linux/ftrace.h>
+#include <linux/suspend.h>
 #include <asm/csr.h>
+#include <asm/sbi.h>
 #include <asm/suspend.h>
 
 void suspend_save_csrs(struct suspend_context *context)
@@ -85,3 +89,43 @@ int cpu_suspend(unsigned long arg,
 
 	return rc;
 }
+
+#ifdef CONFIG_RISCV_SBI
+static int sbi_system_suspend(unsigned long sleep_type,
+			      unsigned long resume_addr,
+			      unsigned long opaque)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_SUSP, SBI_EXT_SUSP_SYSTEM_SUSPEND,
+			sleep_type, resume_addr, opaque, 0, 0, 0);
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+
+	return ret.value;
+}
+
+static int sbi_system_suspend_enter(suspend_state_t state)
+{
+	return cpu_suspend(SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM, sbi_system_suspend);
+}
+
+static const struct platform_suspend_ops sbi_system_suspend_ops = {
+	.valid = suspend_valid_only_mem,
+	.enter = sbi_system_suspend_enter,
+};
+
+static int __init sbi_system_suspend_init(void)
+{
+	if (sbi_spec_version >= sbi_mk_version(2, 0) &&
+	    sbi_probe_extension(SBI_EXT_SUSP) > 0) {
+		pr_info("SBI SUSP extension detected\n");
+		if (IS_ENABLED(CONFIG_SUSPEND))
+			suspend_set_ops(&sbi_system_suspend_ops);
+	}
+
+	return 0;
+}
+
+arch_initcall(sbi_system_suspend_init);
+#endif /* CONFIG_RISCV_SBI */
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 578b6292487e..6727d1d3b8f2 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -21,6 +21,10 @@
 #include <asm/bug.h>
 
 static bool riscv_v_implicit_uacc = IS_ENABLED(CONFIG_RISCV_ISA_V_DEFAULT_ENABLE);
+static struct kmem_cache *riscv_v_user_cachep;
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static struct kmem_cache *riscv_v_kernel_cachep;
+#endif
 
 unsigned long riscv_v_vsize __read_mostly;
 EXPORT_SYMBOL_GPL(riscv_v_vsize);
@@ -47,6 +51,21 @@ int riscv_v_setup_vsize(void)
 	return 0;
 }
 
+void __init riscv_v_setup_ctx_cache(void)
+{
+	if (!has_vector())
+		return;
+
+	riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx",
+							 riscv_v_vsize, 16, SLAB_PANIC,
+							 0, riscv_v_vsize, NULL);
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	riscv_v_kernel_cachep = kmem_cache_create("riscv_vector_kctx",
+						  riscv_v_vsize, 16,
+						  SLAB_PANIC, NULL);
+#endif
+}
+
 static bool insn_is_vector(u32 insn_buf)
 {
 	u32 opcode = insn_buf & __INSN_OPCODE_MASK;
@@ -80,20 +99,37 @@ static bool insn_is_vector(u32 insn_buf)
 	return false;
 }
 
-static int riscv_v_thread_zalloc(void)
+static int riscv_v_thread_zalloc(struct kmem_cache *cache,
+				 struct __riscv_v_ext_state *ctx)
 {
 	void *datap;
 
-	datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
+	datap = kmem_cache_zalloc(cache, GFP_KERNEL);
 	if (!datap)
 		return -ENOMEM;
 
-	current->thread.vstate.datap = datap;
-	memset(&current->thread.vstate, 0, offsetof(struct __riscv_v_ext_state,
-						    datap));
+	ctx->datap = datap;
+	memset(ctx, 0, offsetof(struct __riscv_v_ext_state, datap));
 	return 0;
 }
 
+void riscv_v_thread_alloc(struct task_struct *tsk)
+{
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	riscv_v_thread_zalloc(riscv_v_kernel_cachep, &tsk->thread.kernel_vstate);
+#endif
+}
+
+void riscv_v_thread_free(struct task_struct *tsk)
+{
+	if (tsk->thread.vstate.datap)
+		kmem_cache_free(riscv_v_user_cachep, tsk->thread.vstate.datap);
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	if (tsk->thread.kernel_vstate.datap)
+		kmem_cache_free(riscv_v_kernel_cachep, tsk->thread.kernel_vstate.datap);
+#endif
+}
+
 #define VSTATE_CTRL_GET_CUR(x) ((x) & PR_RISCV_V_VSTATE_CTRL_CUR_MASK)
 #define VSTATE_CTRL_GET_NEXT(x) (((x) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) >> 2)
 #define VSTATE_CTRL_MAKE_NEXT(x) (((x) << 2) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK)
@@ -122,7 +158,8 @@ static inline void riscv_v_ctrl_set(struct task_struct *tsk, int cur, int nxt,
 	ctrl |= VSTATE_CTRL_MAKE_NEXT(nxt);
 	if (inherit)
 		ctrl |= PR_RISCV_V_VSTATE_CTRL_INHERIT;
-	tsk->thread.vstate_ctrl = ctrl;
+	tsk->thread.vstate_ctrl &= ~PR_RISCV_V_VSTATE_CTRL_MASK;
+	tsk->thread.vstate_ctrl |= ctrl;
 }
 
 bool riscv_v_vstate_ctrl_user_allowed(void)
@@ -162,12 +199,12 @@ bool riscv_v_first_use_handler(struct pt_regs *regs)
 	 * context where VS has been off. So, try to allocate the user's V
 	 * context and resume execution.
 	 */
-	if (riscv_v_thread_zalloc()) {
+	if (riscv_v_thread_zalloc(riscv_v_user_cachep, &current->thread.vstate)) {
 		force_sig(SIGBUS);
 		return true;
 	}
 	riscv_v_vstate_on(regs);
-	riscv_v_vstate_restore(current, regs);
+	riscv_v_vstate_set_restore(current, regs);
 	return true;
 }