Merge tag 'riscv-mw1-6.16-rc1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/alexghiti/linux into for-next

riscv patches for 6.16-rc1

* Implement atomic patching support for ftrace which finally allows to
  get rid of stop_machine().
* Support for kexec_file_load() syscall
* Improve module loading time by changing the algorithm that counts the
  number of plt/got entries in a module.
* Zicbop is now used in the kernel to prefetch instructions

[Palmer: There's been two rounds of surgery on this one, so as a result
it's a bit different than the PR.]

* alex-pr: (734 commits)
  riscv: Improve Kconfig help for RISCV_ISA_V_PREEMPTIVE
  MAINTAINERS: Update Atish's email address
  riscv: hwprobe: export Zabha extension
  riscv: Make regs_irqs_disabled() more clear
  perf symbols: Ignore mapping symbols on riscv
  RISC-V: Kconfig: Fix help text of CMDLINE_EXTEND
  riscv: module: Optimize PLT/GOT entry counting
  riscv: Add support for PUD THP
  riscv: xchg: Prefetch the destination word for sc.w
  riscv: Add ARCH_HAS_PREFETCH[W] support with Zicbop
  riscv: Add support for Zicbop
  riscv: Introduce Zicbop instructions
  riscv/kexec_file: Fix comment in purgatory relocator
  riscv: kexec_file: Support loading Image binary file
  riscv: kexec_file: Split the loading of kernel and others
  riscv: Documentation: add a description about dynamic ftrace
  riscv: ftrace: support direct call using call_ops
  riscv: Implement HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS
  riscv: ftrace: support PREEMPT
  riscv: add a data fence for CMODX in the kernel mode
  ...

Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>

18 files changed, 279 insertions, 62 deletions

diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h
index 721ec275ce57..231d777d936c 100644
--- a/arch/riscv/include/asm/alternative-macros.h
+++ b/arch/riscv/include/asm/alternative-macros.h
@@ -115,24 +115,19 @@
 	\old_c
 .endm
 
-#define _ALTERNATIVE_CFG(old_c, ...)	\
-	ALTERNATIVE_CFG old_c
-
-#define _ALTERNATIVE_CFG_2(old_c, ...)	\
-	ALTERNATIVE_CFG old_c
+#define __ALTERNATIVE_CFG(old_c, ...)		ALTERNATIVE_CFG old_c
+#define __ALTERNATIVE_CFG_2(old_c, ...)		ALTERNATIVE_CFG old_c
 
 #else /* !__ASSEMBLY__ */
 
-#define __ALTERNATIVE_CFG(old_c)	\
-	old_c "\n"
+#define __ALTERNATIVE_CFG(old_c, ...)		old_c "\n"
+#define __ALTERNATIVE_CFG_2(old_c, ...)		old_c "\n"
 
-#define _ALTERNATIVE_CFG(old_c, ...)	\
-	__ALTERNATIVE_CFG(old_c)
+#endif /* __ASSEMBLY__ */
 
-#define _ALTERNATIVE_CFG_2(old_c, ...)	\
-	__ALTERNATIVE_CFG(old_c)
+#define _ALTERNATIVE_CFG(old_c, ...)		__ALTERNATIVE_CFG(old_c)
+#define _ALTERNATIVE_CFG_2(old_c, ...)		__ALTERNATIVE_CFG_2(old_c)
 
-#endif /* __ASSEMBLY__ */
 #endif /* CONFIG_RISCV_ALTERNATIVE */
 
 /*
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index e1d9bf1deca6..b8c5726d86ac 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -14,11 +14,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/fence.h>
 
-#define nop()		__asm__ __volatile__ ("nop")
-#define __nops(n)	".rept	" #n "\nnop\n.endr\n"
-#define nops(n)		__asm__ __volatile__ (__nops(n))
-
-
 /* These barriers need to enforce ordering on both devices or memory. */
 #define __mb()		RISCV_FENCE(iorw, iorw)
 #define __rmb()		RISCV_FENCE(ir, ir)
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 8de73f91bfa3..effa02c2e682 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -80,6 +80,7 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
 
 extern unsigned int riscv_cbom_block_size;
 extern unsigned int riscv_cboz_block_size;
+extern unsigned int riscv_cbop_block_size;
 void riscv_init_cbo_blocksizes(void);
 
 #ifdef CONFIG_RISCV_DMA_NONCOHERENT
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 2ec119eb147b..0b749e710216 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -13,6 +13,7 @@
 #include <asm/hwcap.h>
 #include <asm/insn-def.h>
 #include <asm/cpufeature-macros.h>
+#include <asm/processor.h>
 
 #define __arch_xchg_masked(sc_sfx, swap_sfx, prepend, sc_append,		\
 			   swap_append, r, p, n)				\
@@ -37,6 +38,7 @@
 										\
 		__asm__ __volatile__ (						\
 		       prepend							\
+		       PREFETCHW_ASM(%5)					\
 		       "0:	lr.w %0, %2\n"					\
 		       "	and  %1, %0, %z4\n"				\
 		       "	or   %1, %1, %z3\n"				\
@@ -44,7 +46,7 @@
 		       "	bnez %1, 0b\n"					\
 		       sc_append						\
 		       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
-		       : "rJ" (__newx), "rJ" (~__mask)				\
+		       : "rJ" (__newx), "rJ" (~__mask), "rJ" (__ptr32b)		\
 		       : "memory");						\
 										\
 		r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index d627f63ee289..22ebea3c2b26 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -20,10 +20,9 @@ extern void *return_address(unsigned int level);
 #define ftrace_return_address(n) return_address(n)
 
 void _mcount(void);
-static inline unsigned long ftrace_call_adjust(unsigned long addr)
-{
-	return addr;
-}
+unsigned long ftrace_call_adjust(unsigned long addr);
+unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip);
+#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip)
 
 /*
  * Let's do like x86/arm64 and ignore the compat syscalls.
@@ -57,12 +56,21 @@ struct dyn_arch_ftrace {
  * 2) jalr: setting low-12 offset to ra, jump to ra, and set ra to
  *          return address (original pc + 4)
  *
+ * The first 2 instructions for each tracable function is compiled to 2 nop
+ * instructions. Then, the kernel initializes the first instruction to auipc at
+ * boot time (<ftrace disable>). The second instruction is patched to jalr to
+ * start the trace.
+ *
+ *<Image>:
+ * 0: nop
+ * 4: nop
+ *
  *<ftrace enable>:
- * 0: auipc  t0/ra, 0x?
- * 4: jalr   t0/ra, ?(t0/ra)
+ * 0: auipc  t0, 0x?
+ * 4: jalr   t0, ?(t0)
  *
  *<ftrace disable>:
- * 0: nop
+ * 0: auipc  t0, 0x?
  * 4: nop
  *
  * Dynamic ftrace generates probes to call sites, so we must deal with
@@ -75,10 +83,9 @@ struct dyn_arch_ftrace {
 #define AUIPC_OFFSET_MASK	(0xfffff000)
 #define AUIPC_PAD		(0x00001000)
 #define JALR_SHIFT		20
-#define JALR_RA			(0x000080e7)
-#define AUIPC_RA		(0x00000097)
 #define JALR_T0			(0x000282e7)
 #define AUIPC_T0		(0x00000297)
+#define JALR_RANGE		(JALR_SIGN_MASK - 1)
 
 #define to_jalr_t0(offset)						\
 	(((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_T0)
@@ -96,26 +103,14 @@ do {									\
 	call[1] = to_jalr_t0(offset);					\
 } while (0)
 
-#define to_jalr_ra(offset)						\
-	(((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_RA)
-
-#define to_auipc_ra(offset)						\
-	((offset & JALR_SIGN_MASK) ?					\
-	(((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_RA) :	\
-	((offset & AUIPC_OFFSET_MASK) | AUIPC_RA))
-
-#define make_call_ra(caller, callee, call)				\
-do {									\
-	unsigned int offset =						\
-		(unsigned long) (callee) - (unsigned long) (caller);	\
-	call[0] = to_auipc_ra(offset);					\
-	call[1] = to_jalr_ra(offset);					\
-} while (0)
-
 /*
- * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here.
+ * Only the jalr insn in the auipc+jalr is patched, so we make it 4
+ * bytes here.
  */
-#define MCOUNT_INSN_SIZE 8
+#define MCOUNT_INSN_SIZE	4
+#define MCOUNT_AUIPC_SIZE	4
+#define MCOUNT_JALR_SIZE	4
+#define MCOUNT_NOP4_SIZE	4
 
 #ifndef __ASSEMBLY__
 struct dyn_ftrace;
@@ -135,6 +130,9 @@ struct __arch_ftrace_regs {
 	unsigned long sp;
 	unsigned long s0;
 	unsigned long t1;
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	unsigned long direct_tramp;
+#endif
 	union {
 		unsigned long args[8];
 		struct {
@@ -146,6 +144,13 @@ struct __arch_ftrace_regs {
 			unsigned long a5;
 			unsigned long a6;
 			unsigned long a7;
+#ifdef CONFIG_CC_IS_CLANG
+			unsigned long t2;
+			unsigned long t3;
+			unsigned long t4;
+			unsigned long t5;
+			unsigned long t6;
+#endif
 		};
 	};
 };
@@ -221,10 +226,13 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs);
 #define ftrace_graph_func ftrace_graph_func
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr)
 {
 	arch_ftrace_regs(fregs)->t1 = addr;
 }
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
+
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index e3cbf203cdde..affd63e11b0a 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -105,6 +105,7 @@
 #define RISCV_ISA_EXT_ZVFBFWMA		96
 #define RISCV_ISA_EXT_ZAAMO		97
 #define RISCV_ISA_EXT_ZALRSC		98
+#define RISCV_ISA_EXT_ZICBOP		99
 
 #define RISCV_ISA_EXT_XLINUXENVCFG	127
 
diff --git a/arch/riscv/include/asm/image.h b/arch/riscv/include/asm/image.h
index e0b319af3681..8927a6ea1127 100644
--- a/arch/riscv/include/asm/image.h
+++ b/arch/riscv/include/asm/image.h
@@ -30,6 +30,8 @@
 			      RISCV_HEADER_VERSION_MINOR)
 
 #ifndef __ASSEMBLY__
+#define riscv_image_flag_field(flags, field)\
+			       (((flags) >> field##_SHIFT) & field##_MASK)
 /**
  * struct riscv_image_header - riscv kernel image header
  * @code0:		Executable code
diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h
index 71060a2f838e..d5adbaec1d01 100644
--- a/arch/riscv/include/asm/insn-def.h
+++ b/arch/riscv/include/asm/insn-def.h
@@ -18,6 +18,13 @@
 #define INSN_I_RD_SHIFT			 7
 #define INSN_I_OPCODE_SHIFT		 0
 
+#define INSN_S_SIMM7_SHIFT		25
+#define INSN_S_RS2_SHIFT		20
+#define INSN_S_RS1_SHIFT		15
+#define INSN_S_FUNC3_SHIFT		12
+#define INSN_S_SIMM5_SHIFT		 7
+#define INSN_S_OPCODE_SHIFT		 0
+
 #ifdef __ASSEMBLY__
 
 #ifdef CONFIG_AS_HAS_INSN
@@ -30,6 +37,10 @@
 	.insn	i \opcode, \func3, \rd, \rs1, \simm12
 	.endm
 
+	.macro insn_s, opcode, func3, rs2, simm12, rs1
+	.insn	s \opcode, \func3, \rs2, \simm12(\rs1)
+	.endm
+
 #else
 
 #include <asm/gpr-num.h>
@@ -51,10 +62,20 @@
 		 (\simm12 << INSN_I_SIMM12_SHIFT))
 	.endm
 
+	.macro insn_s, opcode, func3, rs2, simm12, rs1
+	.4byte	((\opcode << INSN_S_OPCODE_SHIFT) |		\
+		 (\func3 << INSN_S_FUNC3_SHIFT) |		\
+		 (.L__gpr_num_\rs2 << INSN_S_RS2_SHIFT) |	\
+		 (.L__gpr_num_\rs1 << INSN_S_RS1_SHIFT) |	\
+		 ((\simm12 & 0x1f) << INSN_S_SIMM5_SHIFT) |	\
+		 (((\simm12 >> 5) & 0x7f) << INSN_S_SIMM7_SHIFT))
+	.endm
+
 #endif
 
 #define __INSN_R(...)	insn_r __VA_ARGS__
 #define __INSN_I(...)	insn_i __VA_ARGS__
+#define __INSN_S(...)	insn_s __VA_ARGS__
 
 #else /* ! __ASSEMBLY__ */
 
@@ -66,6 +87,9 @@
 #define __INSN_I(opcode, func3, rd, rs1, simm12)	\
 	".insn	i " opcode ", " func3 ", " rd ", " rs1 ", " simm12 "\n"
 
+#define __INSN_S(opcode, func3, rs2, simm12, rs1)	\
+	".insn	s " opcode ", " func3 ", " rs2 ", " simm12 "(" rs1 ")\n"
+
 #else
 
 #include <linux/stringify.h>
@@ -92,12 +116,26 @@
 "		 (\\simm12 << " __stringify(INSN_I_SIMM12_SHIFT) "))\n"	\
 "	.endm\n"
 
+#define DEFINE_INSN_S							\
+	__DEFINE_ASM_GPR_NUMS						\
+"	.macro insn_s, opcode, func3, rs2, simm12, rs1\n"		\
+"	.4byte	((\\opcode << " __stringify(INSN_S_OPCODE_SHIFT) ") |"	\
+"		 (\\func3 << " __stringify(INSN_S_FUNC3_SHIFT) ") |"	\
+"		 (.L__gpr_num_\\rs2 << " __stringify(INSN_S_RS2_SHIFT) ") |" \
+"		 (.L__gpr_num_\\rs1 << " __stringify(INSN_S_RS1_SHIFT) ") |" \
+"		 ((\\simm12 & 0x1f) << " __stringify(INSN_S_SIMM5_SHIFT) ") |" \
+"		 (((\\simm12 >> 5) & 0x7f) << " __stringify(INSN_S_SIMM7_SHIFT) "))\n" \
+"	.endm\n"
+
 #define UNDEFINE_INSN_R							\
 "	.purgem insn_r\n"
 
 #define UNDEFINE_INSN_I							\
 "	.purgem insn_i\n"
 
+#define UNDEFINE_INSN_S							\
+"	.purgem insn_s\n"
+
 #define __INSN_R(opcode, func3, func7, rd, rs1, rs2)			\
 	DEFINE_INSN_R							\
 	"insn_r " opcode ", " func3 ", " func7 ", " rd ", " rs1 ", " rs2 "\n" \
@@ -108,6 +146,11 @@
 	"insn_i " opcode ", " func3 ", " rd ", " rs1 ", " simm12 "\n" \
 	UNDEFINE_INSN_I
 
+#define __INSN_S(opcode, func3, rs2, simm12, rs1)			\
+	DEFINE_INSN_S							\
+	"insn_s " opcode ", " func3 ", " rs2 ", " simm12 ", " rs1 "\n"	\
+	UNDEFINE_INSN_S
+
 #endif
 
 #endif /* ! __ASSEMBLY__ */
@@ -120,6 +163,10 @@
 	__INSN_I(RV_##opcode, RV_##func3, RV_##rd,		\
 		 RV_##rs1, RV_##simm12)
 
+#define INSN_S(opcode, func3, rs2, simm12, rs1)			\
+	__INSN_S(RV_##opcode, RV_##func3, RV_##rs2,		\
+		 RV_##simm12, RV_##rs1)
+
 #define RV_OPCODE(v)		__ASM_STR(v)
 #define RV_FUNC3(v)		__ASM_STR(v)
 #define RV_FUNC7(v)		__ASM_STR(v)
@@ -133,6 +180,7 @@
 #define RV___RS2(v)		__RV_REG(v)
 
 #define RV_OPCODE_MISC_MEM	RV_OPCODE(15)
+#define RV_OPCODE_OP_IMM	RV_OPCODE(19)
 #define RV_OPCODE_SYSTEM	RV_OPCODE(115)
 
 #define HFENCE_VVMA(vaddr, asid)				\
@@ -196,6 +244,18 @@
 	INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0),		\
 	       RS1(base), SIMM12(4))
 
+#define PREFETCH_I(base, offset)				\
+	INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(0),		\
+	       SIMM12((offset) & 0xfe0), RS1(base))
+
+#define PREFETCH_R(base, offset)				\
+	INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(1),		\
+	       SIMM12((offset) & 0xfe0), RS1(base))
+
+#define PREFETCH_W(base, offset)				\
+	INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(3),		\
+	       SIMM12((offset) & 0xfe0), RS1(base))
+
 #define RISCV_PAUSE	".4byte 0x100000f"
 #define ZAWRS_WRS_NTO	".4byte 0x00d00073"
 #define ZAWRS_WRS_STO	".4byte 0x01d00073"
@@ -203,4 +263,10 @@
 
 #define RISCV_INSN_NOP4	_AC(0x00000013, U)
 
+#ifndef __ASSEMBLY__
+#define nop()           __asm__ __volatile__ ("nop")
+#define __nops(n)       ".rept  " #n "\nnop\n.endr\n"
+#define nops(n)         __asm__ __volatile__ (__nops(n))
+#endif
+
 #endif /* __ASM_INSN_DEF_H */
diff --git a/arch/riscv/include/asm/kexec.h b/arch/riscv/include/asm/kexec.h
index 2b56769cb530..b9ee8346cc8c 100644
--- a/arch/riscv/include/asm/kexec.h
+++ b/arch/riscv/include/asm/kexec.h
@@ -56,6 +56,7 @@ extern riscv_kexec_method riscv_kexec_norelocate;
 
 #ifdef CONFIG_KEXEC_FILE
 extern const struct kexec_file_ops elf_kexec_ops;
+extern const struct kexec_file_ops image_kexec_ops;
 
 struct purgatory_info;
 int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
@@ -67,6 +68,11 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 struct kimage;
 int arch_kimage_file_post_load_cleanup(struct kimage *image);
 #define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup
+
+int load_extra_segments(struct kimage *image, unsigned long kernel_start,
+			unsigned long kernel_len, char *initrd,
+			unsigned long initrd_len, char *cmdline,
+			unsigned long cmdline_len);
 #endif
 
 #endif
diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h
index 46677daf708b..cc11c4544cff 100644
--- a/arch/riscv/include/asm/kgdb.h
+++ b/arch/riscv/include/asm/kgdb.h
@@ -19,16 +19,9 @@
 
 #ifndef	__ASSEMBLY__
 
+void arch_kgdb_breakpoint(void);
 extern unsigned long kgdb_compiled_break;
 
-static inline void arch_kgdb_breakpoint(void)
-{
-	asm(".global kgdb_compiled_break\n"
-	    ".option norvc\n"
-	    "kgdb_compiled_break: ebreak\n"
-	    ".option rvc\n");
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #define DBG_REG_ZERO "zero"
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 0897dd99ab8d..a2c00235c447 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -184,7 +184,7 @@ static inline int pud_none(pud_t pud)
 
 static inline int pud_bad(pud_t pud)
 {
-	return !pud_present(pud);
+	return !pud_present(pud) || (pud_val(pud) & _PAGE_LEAF);
 }
 
 #define pud_leaf	pud_leaf
@@ -401,6 +401,7 @@ p4d_t *p4d_offset(pgd_t *pgd, unsigned long address);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline int pte_devmap(pte_t pte);
 static inline pte_t pmd_pte(pmd_t pmd);
+static inline pte_t pud_pte(pud_t pud);
 
 static inline int pmd_devmap(pmd_t pmd)
 {
@@ -409,7 +410,7 @@ static inline int pmd_devmap(pmd_t pmd)
 
 static inline int pud_devmap(pud_t pud)
 {
-	return 0;
+	return pte_devmap(pud_pte(pud));
 }
 
 static inline int pgd_devmap(pgd_t pgd)
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 428e48e5f57d..b84e2ff83cb7 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -902,6 +902,103 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 #define pmdp_collapse_flush pmdp_collapse_flush
 extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
 				 unsigned long address, pmd_t *pmdp);
+
+static inline pud_t pud_wrprotect(pud_t pud)
+{
+	return pte_pud(pte_wrprotect(pud_pte(pud)));
+}
+
+static inline int pud_trans_huge(pud_t pud)
+{
+	return pud_leaf(pud);
+}
+
+static inline int pud_dirty(pud_t pud)
+{
+	return pte_dirty(pud_pte(pud));
+}
+
+static inline pud_t pud_mkyoung(pud_t pud)
+{
+	return pte_pud(pte_mkyoung(pud_pte(pud)));
+}
+
+static inline pud_t pud_mkold(pud_t pud)
+{
+	return pte_pud(pte_mkold(pud_pte(pud)));
+}
+
+static inline pud_t pud_mkdirty(pud_t pud)
+{
+	return pte_pud(pte_mkdirty(pud_pte(pud)));
+}
+
+static inline pud_t pud_mkclean(pud_t pud)
+{
+	return pte_pud(pte_mkclean(pud_pte(pud)));
+}
+
+static inline pud_t pud_mkwrite(pud_t pud)
+{
+	return pte_pud(pte_mkwrite_novma(pud_pte(pud)));
+}
+
+static inline pud_t pud_mkhuge(pud_t pud)
+{
+	return pud;
+}
+
+static inline pud_t pud_mkdevmap(pud_t pud)
+{
+	return pte_pud(pte_mkdevmap(pud_pte(pud)));
+}
+
+static inline int pudp_set_access_flags(struct vm_area_struct *vma,
+					unsigned long address, pud_t *pudp,
+					pud_t entry, int dirty)
+{
+	return ptep_set_access_flags(vma, address, (pte_t *)pudp, pud_pte(entry), dirty);
+}
+
+static inline int pudp_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long address, pud_t *pudp)
+{
+	return ptep_test_and_clear_young(vma, address, (pte_t *)pudp);
+}
+
+static inline int pud_young(pud_t pud)
+{
+	return pte_young(pud_pte(pud));
+}
+
+static inline void update_mmu_cache_pud(struct vm_area_struct *vma,
+					unsigned long address, pud_t *pudp)
+{
+	pte_t *ptep = (pte_t *)pudp;
+
+	update_mmu_cache(vma, address, ptep);
+}
+
+static inline pud_t pudp_establish(struct vm_area_struct *vma,
+				   unsigned long address, pud_t *pudp, pud_t pud)
+{
+	page_table_check_pud_set(vma->vm_mm, pudp, pud);
+	return __pud(atomic_long_xchg((atomic_long_t *)pudp, pud_val(pud)));
+}
+
+static inline pud_t pud_mkinvalid(pud_t pud)
+{
+	return __pud(pud_val(pud) & ~(_PAGE_PRESENT | _PAGE_PROT_NONE));
+}
+
+extern pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			     pud_t *pudp);
+
+static inline pud_t pud_modify(pud_t pud, pgprot_t newprot)
+{
+	return pte_pud(pte_modify(pud_pte(pud), newprot));
+}
+
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /*
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 58fd11c89fe9..8111250f3c1b 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -13,6 +13,9 @@
 #include <vdso/processor.h>
 
 #include <asm/ptrace.h>
+#include <asm/insn-def.h>
+#include <asm/alternative-macros.h>
+#include <asm/hwcap.h>
 
 #define arch_get_mmap_end(addr, len, flags)			\
 ({								\
@@ -52,7 +55,6 @@
 #endif
 
 #ifndef __ASSEMBLY__
-#include <linux/cpumask.h>
 
 struct task_struct;
 struct pt_regs;
@@ -79,6 +81,10 @@ struct pt_regs;
  *       Thus, the task does not own preempt_v. Any use of Vector will have to
  *       save preempt_v, if dirty, and fallback to non-preemptible kernel-mode
  *       Vector.
+ *  - bit 29: The thread voluntarily calls schedule() while holding an active
+ *    preempt_v. All preempt_v context should be dropped in such case because
+ *    V-regs are caller-saved. Only sstatus.VS=ON is persisted across a
+ *    schedule() call.
  *  - bit 30: The in-kernel preempt_v context is saved, and requries to be
  *    restored when returning to the context that owns the preempt_v.
  *  - bit 31: The in-kernel preempt_v context is dirty, as signaled by the
@@ -93,6 +99,7 @@ struct pt_regs;
 #define RISCV_PREEMPT_V			0x00000100
 #define RISCV_PREEMPT_V_DIRTY		0x80000000
 #define RISCV_PREEMPT_V_NEED_RESTORE	0x40000000
+#define RISCV_PREEMPT_V_IN_SCHEDULE	0x20000000
 
 /* CPU-specific state of a task */
 struct thread_struct {
@@ -137,6 +144,27 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset,
 #define KSTK_EIP(tsk)		(task_pt_regs(tsk)->epc)
 #define KSTK_ESP(tsk)		(task_pt_regs(tsk)->sp)
 
+#define PREFETCH_ASM(x)							\
+	ALTERNATIVE(__nops(1), PREFETCH_R(x, 0), 0,			\
+		    RISCV_ISA_EXT_ZICBOP, CONFIG_RISCV_ISA_ZICBOP)
+
+#define PREFETCHW_ASM(x)						\
+	ALTERNATIVE(__nops(1), PREFETCH_W(x, 0), 0,			\
+		    RISCV_ISA_EXT_ZICBOP, CONFIG_RISCV_ISA_ZICBOP)
+
+#ifdef CONFIG_RISCV_ISA_ZICBOP
+#define ARCH_HAS_PREFETCH
+static inline void prefetch(const void *x)
+{
+	__asm__ __volatile__(PREFETCH_ASM(%0) : : "r" (x) : "memory");
+}
+
+#define ARCH_HAS_PREFETCHW
+static inline void prefetchw(const void *x)
+{
+	__asm__ __volatile__(PREFETCHW_ASM(%0) : : "r" (x) : "memory");
+}
+#endif /* CONFIG_RISCV_ISA_ZICBOP */
 
 /* Do necessary setup to start up a newly executed thread. */
 extern void start_thread(struct pt_regs *regs,
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
index 2910231977cb..a7dc0e330757 100644
--- a/arch/riscv/include/asm/ptrace.h
+++ b/arch/riscv/include/asm/ptrace.h
@@ -175,7 +175,7 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
 	return 0;
 }
 
-static inline int regs_irqs_disabled(struct pt_regs *regs)
+static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
 {
 	return !(regs->status & SR_PIE);
 }
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index 121fff429dce..eceabf59ae48 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -62,8 +62,11 @@ static inline void syscall_get_arguments(struct task_struct *task,
 					 unsigned long *args)
 {
 	args[0] = regs->orig_a0;
-	args++;
-	memcpy(args, &regs->a1, 5 * sizeof(args[0]));
+	args[1] = regs->a1;
+	args[2] = regs->a2;
+	args[3] = regs->a3;
+	args[4] = regs->a4;
+	args[5] = regs->a5;
 }
 
 static inline int syscall_get_arch(struct task_struct *task)
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index ce0dd0fed764..1a20dd746a49 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -56,6 +56,8 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end);
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end);
+void flush_pud_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			 unsigned long end);
 #endif
 
 bool arch_tlbbatch_should_defer(struct mm_struct *mm);
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index e8a83f55be2b..45c9b426fcc5 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -120,6 +120,11 @@ static __always_inline void riscv_v_disable(void)
 		csr_clear(CSR_SSTATUS, SR_VS);
 }
 
+static __always_inline bool riscv_v_is_on(void)
+{
+	return !!(csr_read(CSR_SSTATUS) & SR_VS);
+}
+
 static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest)
 {
 	asm volatile (
@@ -366,6 +371,11 @@ static inline void __switch_to_vector(struct task_struct *prev,
 	struct pt_regs *regs;
 
 	if (riscv_preempt_v_started(prev)) {
+		if (riscv_v_is_on()) {
+			WARN_ON(prev->thread.riscv_v_flags & RISCV_V_CTX_DEPTH_MASK);
+			riscv_v_disable();
+			prev->thread.riscv_v_flags |= RISCV_PREEMPT_V_IN_SCHEDULE;
+		}
 		if (riscv_preempt_v_dirty(prev)) {
 			__riscv_v_vstate_save(&prev->thread.kernel_vstate,
 					      prev->thread.kernel_vstate.datap);
@@ -376,10 +386,16 @@ static inline void __switch_to_vector(struct task_struct *prev,
 		riscv_v_vstate_save(&prev->thread.vstate, regs);
 	}
 
-	if (riscv_preempt_v_started(next))
-		riscv_preempt_v_set_restore(next);
-	else
+	if (riscv_preempt_v_started(next)) {
+		if (next->thread.riscv_v_flags & RISCV_PREEMPT_V_IN_SCHEDULE) {
+			next->thread.riscv_v_flags &= ~RISCV_PREEMPT_V_IN_SCHEDULE;
+			riscv_v_enable();
+		} else {
+			riscv_preempt_v_set_restore(next);
+		}
+	} else {
 		riscv_v_vstate_set_restore(next, task_pt_regs(next));
+	}
 }
 
 void riscv_v_vstate_ctrl_init(struct task_struct *tsk);
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 9c70101f021b..aaf6ad970499 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -81,6 +81,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZICBOM	(1ULL << 55)
 #define		RISCV_HWPROBE_EXT_ZAAMO		(1ULL << 56)
 #define		RISCV_HWPROBE_EXT_ZALRSC	(1ULL << 57)
+#define		RISCV_HWPROBE_EXT_ZABHA		(1ULL << 58)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)