Merge tag 'riscv-for-linus-6.7-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull more RISC-V updates from Palmer Dabbelt:

 - Support for handling misaligned accesses in S-mode

 - Probing for misaligned access support is now properly cached and
   handled in parallel

 - PTDUMP now reflects the SW reserved bits, as well as the PBMT and
   NAPOT extensions

 - Performance improvements for TLB flushing

 - Support for many new relocations in the module loader

 - Various bug fixes and cleanups

* tag 'riscv-for-linus-6.7-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (51 commits)
  riscv: Optimize bitops with Zbb extension
  riscv: Rearrange hwcap.h and cpufeature.h
  drivers: perf: Do not broadcast to other cpus when starting a counter
  drivers: perf: Check find_first_bit() return value
  of: property: Add fw_devlink support for msi-parent
  RISC-V: Don't fail in riscv_of_parent_hartid() for disabled HARTs
  riscv: Fix set_memory_XX() and set_direct_map_XX() by splitting huge linear mappings
  riscv: Don't use PGD entries for the linear mapping
  RISC-V: Probe misaligned access speed in parallel
  RISC-V: Remove __init on unaligned_emulation_finish()
  RISC-V: Show accurate per-hart isa in /proc/cpuinfo
  RISC-V: Don't rely on positional structure initialization
  riscv: Add tests for riscv module loading
  riscv: Add remaining module relocations
  riscv: Avoid unaligned access when relocating modules
  riscv: split cache ops out of dma-noncoherent.c
  riscv: Improve flush_tlb_kernel_range()
  riscv: Make __flush_tlb_range() loop over pte instead of flushing the whole tlb
  riscv: Improve flush_tlb_range() for hugetlb pages
  riscv: Improve tlb_flush()
  ...

81 files changed, 2509 insertions, 683 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 18b03ad0e6b9..95a2a06acc6a 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -642,6 +642,15 @@ config THREAD_SIZE_ORDER
 	  Specify the Pages of thread stack size (from 4KB to 64KB), which also
 	  affects irq stack size, which is equal to thread stack size.
 
+config RISCV_MISALIGNED
+	bool "Support misaligned load/store traps for kernel and userspace"
+	select SYSCTL_ARCH_UNALIGN_ALLOW
+	default y
+	help
+	  Say Y here if you want the kernel to embed support for misaligned
+	  load/store for both kernel and userspace. When disable, misaligned
+	  accesses will generate SIGBUS in userspace and panic in kernel.
+
 endmenu # "Platform type"
 
 menu "Kernel features"
@@ -909,6 +918,9 @@ config PORTABLE
 	select MMU
 	select OF
 
+config ARCH_PROC_KCORE_TEXT
+	def_bool y
+
 menu "Power management options"
 
 source "kernel/power/Kconfig"
diff --git a/arch/riscv/Kconfig.debug b/arch/riscv/Kconfig.debug
index e69de29bb2d1..eafe17ebf710 100644
--- a/arch/riscv/Kconfig.debug
+++ b/arch/riscv/Kconfig.debug
@@ -0,0 +1 @@
+source "arch/riscv/kernel/tests/Kconfig.debug"
diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile
index 22b13947bd13..8e7fc0edf21d 100644
--- a/arch/riscv/boot/Makefile
+++ b/arch/riscv/boot/Makefile
@@ -17,6 +17,7 @@
 KCOV_INSTRUMENT := n
 
 OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
+OBJCOPYFLAGS_loader.bin :=-O binary
 OBJCOPYFLAGS_xipImage :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
 
 targets := Image Image.* loader loader.o loader.lds loader.bin
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 938fa07ddf77..905881282a7c 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -215,6 +215,8 @@ CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_CADENCE=y
 CONFIG_MMC_SPI=y
+CONFIG_MMC_DW=y
+CONFIG_MMC_DW_STARFIVE=y
 CONFIG_MMC_SDHI=y
 CONFIG_MMC_SUNXI=y
 CONFIG_RTC_CLASS=y
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 65f6eee4ab8d..224b4dc02b50 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -15,13 +15,261 @@
 #include <asm/barrier.h>
 #include <asm/bitsperlong.h>
 
+#if !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE)
 #include <asm-generic/bitops/__ffs.h>
-#include <asm-generic/bitops/ffz.h>
-#include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/ffs.h>
+#include <asm-generic/bitops/fls.h>
+
+#else
+#include <asm/alternative-macros.h>
+#include <asm/hwcap.h>
+
+#if (BITS_PER_LONG == 64)
+#define CTZW	"ctzw "
+#define CLZW	"clzw "
+#elif (BITS_PER_LONG == 32)
+#define CTZW	"ctz "
+#define CLZW	"clz "
+#else
+#error "Unexpected BITS_PER_LONG"
+#endif
+
+static __always_inline unsigned long variable__ffs(unsigned long word)
+{
+	int num;
+
+	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm volatile (".option push\n"
+		      ".option arch,+zbb\n"
+		      "ctz %0, %1\n"
+		      ".option pop\n"
+		      : "=r" (word) : "r" (word) :);
+
+	return word;
+
+legacy:
+	num = 0;
+#if BITS_PER_LONG == 64
+	if ((word & 0xffffffff) == 0) {
+		num += 32;
+		word >>= 32;
+	}
+#endif
+	if ((word & 0xffff) == 0) {
+		num += 16;
+		word >>= 16;
+	}
+	if ((word & 0xff) == 0) {
+		num += 8;
+		word >>= 8;
+	}
+	if ((word & 0xf) == 0) {
+		num += 4;
+		word >>= 4;
+	}
+	if ((word & 0x3) == 0) {
+		num += 2;
+		word >>= 2;
+	}
+	if ((word & 0x1) == 0)
+		num += 1;
+	return num;
+}
+
+/**
+ * __ffs - find first set bit in a long word
+ * @word: The word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+#define __ffs(word)				\
+	(__builtin_constant_p(word) ?		\
+	 (unsigned long)__builtin_ctzl(word) :	\
+	 variable__ffs(word))
+
+static __always_inline unsigned long variable__fls(unsigned long word)
+{
+	int num;
+
+	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm volatile (".option push\n"
+		      ".option arch,+zbb\n"
+		      "clz %0, %1\n"
+		      ".option pop\n"
+		      : "=r" (word) : "r" (word) :);
+
+	return BITS_PER_LONG - 1 - word;
+
+legacy:
+	num = BITS_PER_LONG - 1;
+#if BITS_PER_LONG == 64
+	if (!(word & (~0ul << 32))) {
+		num -= 32;
+		word <<= 32;
+	}
+#endif
+	if (!(word & (~0ul << (BITS_PER_LONG - 16)))) {
+		num -= 16;
+		word <<= 16;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG - 8)))) {
+		num -= 8;
+		word <<= 8;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG - 4)))) {
+		num -= 4;
+		word <<= 4;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG - 2)))) {
+		num -= 2;
+		word <<= 2;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG - 1))))
+		num -= 1;
+	return num;
+}
+
+/**
+ * __fls - find last set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+#define __fls(word)							\
+	(__builtin_constant_p(word) ?					\
+	 (unsigned long)(BITS_PER_LONG - 1 - __builtin_clzl(word)) :	\
+	 variable__fls(word))
+
+static __always_inline int variable_ffs(int x)
+{
+	int r;
+
+	if (!x)
+		return 0;
+
+	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm volatile (".option push\n"
+		      ".option arch,+zbb\n"
+		      CTZW "%0, %1\n"
+		      ".option pop\n"
+		      : "=r" (r) : "r" (x) :);
+
+	return r + 1;
+
+legacy:
+	r = 1;
+	if (!(x & 0xffff)) {
+		x >>= 16;
+		r += 16;
+	}
+	if (!(x & 0xff)) {
+		x >>= 8;
+		r += 8;
+	}
+	if (!(x & 0xf)) {
+		x >>= 4;
+		r += 4;
+	}
+	if (!(x & 3)) {
+		x >>= 2;
+		r += 2;
+	}
+	if (!(x & 1)) {
+		x >>= 1;
+		r += 1;
+	}
+	return r;
+}
+
+/**
+ * ffs - find first set bit in a word
+ * @x: the word to search
+ *
+ * This is defined the same way as the libc and compiler builtin ffs routines.
+ *
+ * ffs(value) returns 0 if value is 0 or the position of the first set bit if
+ * value is nonzero. The first (least significant) bit is at position 1.
+ */
+#define ffs(x) (__builtin_constant_p(x) ? __builtin_ffs(x) : variable_ffs(x))
+
+static __always_inline int variable_fls(unsigned int x)
+{
+	int r;
+
+	if (!x)
+		return 0;
+
+	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm volatile (".option push\n"
+		      ".option arch,+zbb\n"
+		      CLZW "%0, %1\n"
+		      ".option pop\n"
+		      : "=r" (r) : "r" (x) :);
+
+	return 32 - r;
+
+legacy:
+	r = 32;
+	if (!(x & 0xffff0000u)) {
+		x <<= 16;
+		r -= 16;
+	}
+	if (!(x & 0xff000000u)) {
+		x <<= 8;
+		r -= 8;
+	}
+	if (!(x & 0xf0000000u)) {
+		x <<= 4;
+		r -= 4;
+	}
+	if (!(x & 0xc0000000u)) {
+		x <<= 2;
+		r -= 2;
+	}
+	if (!(x & 0x80000000u)) {
+		x <<= 1;
+		r -= 1;
+	}
+	return r;
+}
+
+/**
+ * fls - find last set bit in a word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as ffs, but returns the position of the most
+ * significant set bit.
+ *
+ * fls(value) returns 0 if value is 0 or the position of the last set bit if
+ * value is nonzero. The last (most significant) bit is at position 32.
+ */
+#define fls(x)							\
+({								\
+	typeof(x) x_ = (x);					\
+	__builtin_constant_p(x_) ?				\
+	 (int)((x_ != 0) ? (32 - __builtin_clz(x_)) : 0)	\
+	 :							\
+	 variable_fls(x_);					\
+})
+
+#endif /* !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE) */
+
+#include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/ffs.h>
 
 #include <asm-generic/bitops/hweight.h>
 
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 13b7d35648a9..a418c3112cd6 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -7,7 +7,10 @@
 #define _ASM_CPUFEATURE_H
 
 #include <linux/bitmap.h>
+#include <linux/jump_label.h>
 #include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
+#include <asm/errno.h>
 
 /*
  * These are probed via a device_initcall(), via either the SBI or directly
@@ -30,7 +33,104 @@ DECLARE_PER_CPU(long, misaligned_access_speed);
 /* Per-cpu ISA extensions. */
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
-void check_unaligned_access(int cpu);
 void riscv_user_isa_enable(void);
 
+#ifdef CONFIG_RISCV_MISALIGNED
+bool unaligned_ctl_available(void);
+bool check_unaligned_access_emulated(int cpu);
+void unaligned_emulation_finish(void);
+#else
+static inline bool unaligned_ctl_available(void)
+{
+	return false;
+}
+
+static inline bool check_unaligned_access_emulated(int cpu)
+{
+	return false;
+}
+
+static inline void unaligned_emulation_finish(void) {}
+#endif
+
+unsigned long riscv_get_elf_hwcap(void);
+
+struct riscv_isa_ext_data {
+	const unsigned int id;
+	const char *name;
+	const char *property;
+};
+
+extern const struct riscv_isa_ext_data riscv_isa_ext[];
+extern const size_t riscv_isa_ext_count;
+extern bool riscv_isa_fallback;
+
+unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
+
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit);
+#define riscv_isa_extension_available(isa_bitmap, ext)	\
+	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
+
+static __always_inline bool
+riscv_has_extension_likely(const unsigned long ext)
+{
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX,
+			   "ext must be < RISCV_ISA_EXT_MAX");
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		asm_volatile_goto(
+		ALTERNATIVE("j	%l[l_no]", "nop", 0, %[ext], 1)
+		:
+		: [ext] "i" (ext)
+		:
+		: l_no);
+	} else {
+		if (!__riscv_isa_extension_available(NULL, ext))
+			goto l_no;
+	}
+
+	return true;
+l_no:
+	return false;
+}
+
+static __always_inline bool
+riscv_has_extension_unlikely(const unsigned long ext)
+{
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX,
+			   "ext must be < RISCV_ISA_EXT_MAX");
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		asm_volatile_goto(
+		ALTERNATIVE("nop", "j	%l[l_yes]", 0, %[ext], 1)
+		:
+		: [ext] "i" (ext)
+		:
+		: l_yes);
+	} else {
+		if (__riscv_isa_extension_available(NULL, ext))
+			goto l_yes;
+	}
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_likely(ext))
+		return true;
+
+	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
+}
+
+static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_unlikely(ext))
+		return true;
+
+	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
+}
+
 #endif
diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
index b3b2dfbdf945..06c236bfab53 100644
--- a/arch/riscv/include/asm/elf.h
+++ b/arch/riscv/include/asm/elf.h
@@ -14,7 +14,7 @@
 #include <asm/auxvec.h>
 #include <asm/byteorder.h>
 #include <asm/cacheinfo.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 
 /*
  * These are used to set parameters in the core dumps.
diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h
index 6e4dee49d84b..7ab5e34318c8 100644
--- a/arch/riscv/include/asm/entry-common.h
+++ b/arch/riscv/include/asm/entry-common.h
@@ -8,4 +8,18 @@
 void handle_page_fault(struct pt_regs *regs);
 void handle_break(struct pt_regs *regs);
 
+#ifdef CONFIG_RISCV_MISALIGNED
+int handle_misaligned_load(struct pt_regs *regs);
+int handle_misaligned_store(struct pt_regs *regs);
+#else
+static inline int handle_misaligned_load(struct pt_regs *regs)
+{
+	return -1;
+}
+static inline int handle_misaligned_store(struct pt_regs *regs)
+{
+	return -1;
+}
+#endif
+
 #endif /* _ASM_RISCV_ENTRY_COMMON_H */
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 0ac18a4135be..83ed25e43553 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -117,9 +117,9 @@ asm volatile(ALTERNATIVE(						\
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
  *   0000000    11001     00000      000      00000  0001011
  */
-#define THEAD_inval_A0	".long 0x0265000b"
-#define THEAD_clean_A0	".long 0x0255000b"
-#define THEAD_flush_A0	".long 0x0275000b"
+#define THEAD_INVAL_A0	".long 0x0265000b"
+#define THEAD_CLEAN_A0	".long 0x0255000b"
+#define THEAD_FLUSH_A0	".long 0x0275000b"
 #define THEAD_SYNC_S	".long 0x0190000b"
 
 #define ALT_CMO_OP(_op, _start, _size, _cachesize)			\
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index fe6656af967a..06d30526ef3b 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -8,9 +8,6 @@
 #ifndef _ASM_RISCV_HWCAP_H
 #define _ASM_RISCV_HWCAP_H
 
-#include <asm/alternative-macros.h>
-#include <asm/errno.h>
-#include <linux/bits.h>
 #include <uapi/asm/hwcap.h>
 
 #define RISCV_ISA_EXT_a		('a' - 'a')
@@ -69,92 +66,4 @@
 #define RISCV_ISA_EXT_SxAIA		RISCV_ISA_EXT_SSAIA
 #endif
 
-#ifndef __ASSEMBLY__
-
-#include <linux/jump_label.h>
-#include <asm/cpufeature.h>
-
-unsigned long riscv_get_elf_hwcap(void);
-
-struct riscv_isa_ext_data {
-	const unsigned int id;
-	const char *name;
-	const char *property;
-};
-
-extern const struct riscv_isa_ext_data riscv_isa_ext[];
-extern const size_t riscv_isa_ext_count;
-extern bool riscv_isa_fallback;
-
-unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
-
-#define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext)
-
-bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit);
-#define riscv_isa_extension_available(isa_bitmap, ext)	\
-	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
-
-static __always_inline bool
-riscv_has_extension_likely(const unsigned long ext)
-{
-	compiletime_assert(ext < RISCV_ISA_EXT_MAX,
-			   "ext must be < RISCV_ISA_EXT_MAX");
-
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
-		ALTERNATIVE("j	%l[l_no]", "nop", 0, %[ext], 1)
-		:
-		: [ext] "i" (ext)
-		:
-		: l_no);
-	} else {
-		if (!__riscv_isa_extension_available(NULL, ext))
-			goto l_no;
-	}
-
-	return true;
-l_no:
-	return false;
-}
-
-static __always_inline bool
-riscv_has_extension_unlikely(const unsigned long ext)
-{
-	compiletime_assert(ext < RISCV_ISA_EXT_MAX,
-			   "ext must be < RISCV_ISA_EXT_MAX");
-
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
-		ALTERNATIVE("nop", "j	%l[l_yes]", 0, %[ext], 1)
-		:
-		: [ext] "i" (ext)
-		:
-		: l_yes);
-	} else {
-		if (__riscv_isa_extension_available(NULL, ext))
-			goto l_yes;
-	}
-
-	return false;
-l_yes:
-	return true;
-}
-
-static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext)
-{
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_likely(ext))
-		return true;
-
-	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
-}
-
-static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext)
-{
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_unlikely(ext))
-		return true;
-
-	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
-}
-#endif
-
 #endif /* _ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h
index 6960beb75f32..e27179b26086 100644
--- a/arch/riscv/include/asm/insn-def.h
+++ b/arch/riscv/include/asm/insn-def.h
@@ -180,19 +180,19 @@
 	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(51),		\
 	       __RD(0), RS1(gaddr), RS2(vmid))
 
-#define CBO_inval(base)						\
+#define CBO_INVAL(base)						\
 	INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0),		\
 	       RS1(base), SIMM12(0))
 
-#define CBO_clean(base)						\
+#define CBO_CLEAN(base)						\
 	INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0),		\
 	       RS1(base), SIMM12(1))
 
-#define CBO_flush(base)						\
+#define CBO_FLUSH(base)						\
 	INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0),		\
 	       RS1(base), SIMM12(2))
 
-#define CBO_zero(base)						\
+#define CBO_ZERO(base)						\
 	INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0),		\
 	       RS1(base), SIMM12(4))
 
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 7a5097202e15..9a2c780a11e9 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -126,14 +126,18 @@ enum napot_cont_order {
 
 /*
  * [63:59] T-Head Memory Type definitions:
- *
- * 00000 - NC   Weakly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable
+ * bit[63] SO - Strong Order
+ * bit[62] C - Cacheable
+ * bit[61] B - Bufferable
+ * bit[60] SH - Shareable
+ * bit[59] Sec - Trustable
+ * 00110 - NC   Weakly-ordered, Non-cacheable, Bufferable, Shareable, Non-trustable
  * 01110 - PMA  Weakly-ordered, Cacheable, Bufferable, Shareable, Non-trustable
- * 10000 - IO   Strongly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable
+ * 10010 - IO   Strongly-ordered, Non-cacheable, Non-bufferable, Shareable, Non-trustable
  */
 #define _PAGE_PMA_THEAD		((1UL << 62) | (1UL << 61) | (1UL << 60))
-#define _PAGE_NOCACHE_THEAD	0UL
-#define _PAGE_IO_THEAD		(1UL << 63)
+#define _PAGE_NOCACHE_THEAD	((1UL < 61) | (1UL << 60))
+#define _PAGE_IO_THEAD		((1UL << 63) | (1UL << 60))
 #define _PAGE_MTMASK_THEAD	(_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59))
 
 static inline u64 riscv_page_mtmask(void)
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index f896708e8331..179bd4afece4 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -16,9 +16,9 @@
 #define _PAGE_GLOBAL    (1 << 5)    /* Global */
 #define _PAGE_ACCESSED  (1 << 6)    /* Set by hardware on any access */
 #define _PAGE_DIRTY     (1 << 7)    /* Set by hardware on any write */
-#define _PAGE_SOFT      (1 << 8)    /* Reserved for software */
+#define _PAGE_SOFT      (3 << 8)    /* Reserved for software */
 
-#define _PAGE_SPECIAL   _PAGE_SOFT
+#define _PAGE_SPECIAL   (1 << 8)    /* RSW: 0x1 */
 #define _PAGE_TABLE     _PAGE_PRESENT
 
 /*
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index c8e8867c42f6..294044429e8e 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -291,6 +291,7 @@ static inline pte_t pud_pte(pud_t pud)
 }
 
 #ifdef CONFIG_RISCV_ISA_SVNAPOT
+#include <asm/cpufeature.h>
 
 static __always_inline bool has_svnapot(void)
 {
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 441da1839c94..f19f861cda54 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -8,6 +8,7 @@
 
 #include <linux/const.h>
 #include <linux/cache.h>
+#include <linux/prctl.h>
 
 #include <vdso/processor.h>
 
@@ -82,6 +83,7 @@ struct thread_struct {
 	unsigned long bad_cause;
 	unsigned long vstate_ctrl;
 	struct __riscv_v_ext_state vstate;
+	unsigned long align_ctl;
 };
 
 /* Whitelist the fstate from the task_struct for hardened usercopy */
@@ -94,6 +96,7 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset,
 
 #define INIT_THREAD {					\
 	.sp = sizeof(init_stack) + (long)&init_stack,	\
+	.align_ctl = PR_UNALIGN_NOPRINT,		\
 }
 
 #define task_pt_regs(tsk)						\
@@ -136,6 +139,12 @@ extern long riscv_v_vstate_ctrl_set_current(unsigned long arg);
 extern long riscv_v_vstate_ctrl_get_current(void);
 #endif /* CONFIG_RISCV_ISA_V */
 
+extern int get_unalign_ctl(struct task_struct *tsk, unsigned long addr);
+extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
+
+#define GET_UNALIGN_CTL(tsk, addr)	get_unalign_ctl((tsk), (addr))
+#define SET_UNALIGN_CTL(tsk, val)	set_unalign_ctl((tsk), (val))
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_RISCV_PROCESSOR_H */
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 12dfda6bb924..0892f4421bc4 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -280,9 +280,6 @@ void sbi_set_timer(uint64_t stime_value);
 void sbi_shutdown(void);
 void sbi_send_ipi(unsigned int cpu);
 int sbi_remote_fence_i(const struct cpumask *cpu_mask);
-int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
-			   unsigned long start,
-			   unsigned long size);
 
 int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
 				unsigned long start,
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index a727be723c56..f90d8e42f3c7 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -9,7 +9,7 @@
 #include <linux/jump_label.h>
 #include <linux/sched/task_stack.h>
 #include <asm/vector.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/csr.h>
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 120bcf2ed8a8..1eb5682b2af6 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -15,7 +15,13 @@ static void tlb_flush(struct mmu_gather *tlb);
 
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
-	flush_tlb_mm(tlb->mm);
+#ifdef CONFIG_MMU
+	if (tlb->fullmm || tlb->need_flush_all)
+		flush_tlb_mm(tlb->mm);
+	else
+		flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end,
+				   tlb_get_unmap_size(tlb));
+#endif
 }
 
 #endif /* _ASM_RISCV_TLB_H */
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index a09196f8de68..8f3418c5f172 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -11,6 +11,9 @@
 #include <asm/smp.h>
 #include <asm/errata_list.h>
 
+#define FLUSH_TLB_MAX_SIZE      ((unsigned long)-1)
+#define FLUSH_TLB_NO_ASID       ((unsigned long)-1)
+
 #ifdef CONFIG_MMU
 extern unsigned long asid_mask;
 
@@ -32,9 +35,12 @@ static inline void local_flush_tlb_page(unsigned long addr)
 #if defined(CONFIG_SMP) && defined(CONFIG_MMU)
 void flush_tlb_all(void);
 void flush_tlb_mm(struct mm_struct *mm);
+void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
+			unsigned long end, unsigned int page_size);
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end);
+void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
@@ -51,14 +57,15 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 	local_flush_tlb_all();
 }
 
-#define flush_tlb_mm(mm) flush_tlb_all()
-#endif /* !CONFIG_SMP || !CONFIG_MMU */
-
 /* Flush a range of kernel pages */
 static inline void flush_tlb_kernel_range(unsigned long start,
 	unsigned long end)
 {
-	flush_tlb_all();
+	local_flush_tlb_all();
 }
 
+#define flush_tlb_mm(mm) flush_tlb_all()
+#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
+#endif /* !CONFIG_SMP || !CONFIG_MMU */
+
 #endif /* _ASM_RISCV_TLBFLUSH_H */
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index c5ee07b3df07..87aaef656257 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -15,7 +15,7 @@
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 #include <asm/ptrace.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/csr.h>
 #include <asm/asm.h>
 
diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h
index d696d6610231..11a71b8533d5 100644
--- a/arch/riscv/include/uapi/asm/elf.h
+++ b/arch/riscv/include/uapi/asm/elf.h
@@ -49,6 +49,7 @@ typedef union __riscv_fp_state elf_fpregset_t;
 #define R_RISCV_TLS_DTPREL64	9
 #define R_RISCV_TLS_TPREL32	10
 #define R_RISCV_TLS_TPREL64	11
+#define R_RISCV_IRELATIVE	58
 
 /* Relocation types not used by the dynamic linker */
 #define R_RISCV_BRANCH		16
@@ -81,7 +82,6 @@ typedef union __riscv_fp_state elf_fpregset_t;
 #define R_RISCV_ALIGN		43
 #define R_RISCV_RVC_BRANCH	44
 #define R_RISCV_RVC_JUMP	45
-#define R_RISCV_LUI		46
 #define R_RISCV_GPREL_I		47
 #define R_RISCV_GPREL_S		48
 #define R_RISCV_TPREL_I		49
@@ -93,6 +93,9 @@ typedef union __riscv_fp_state elf_fpregset_t;
 #define R_RISCV_SET16		55
 #define R_RISCV_SET32		56
 #define R_RISCV_32_PCREL	57
+#define R_RISCV_PLT32		59
+#define R_RISCV_SET_ULEB128	60
+#define R_RISCV_SUB_ULEB128	61
 
 
 #endif /* _UAPI_ASM_RISCV_ELF_H */
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 95cf25d48405..fee22a3d1b53 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -57,9 +57,10 @@ obj-y	+= stacktrace.o
 obj-y	+= cacheinfo.o
 obj-y	+= patch.o
 obj-y	+= probes/
+obj-y	+= tests/
 obj-$(CONFIG_MMU) += vdso.o vdso/
 
-obj-$(CONFIG_RISCV_M_MODE)	+= traps_misaligned.o
+obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
diff --git a/arch/riscv/kernel/copy-unaligned.S b/arch/riscv/kernel/copy-unaligned.S
index cfdecfbaad62..2b3d9398c113 100644
--- a/arch/riscv/kernel/copy-unaligned.S
+++ b/arch/riscv/kernel/copy-unaligned.S
@@ -9,7 +9,7 @@
 /* void __riscv_copy_words_unaligned(void *, const void *, size_t) */
 /* Performs a memcpy without aligning buffers, using word loads and stores. */
 /* Note: The size is truncated to a multiple of 8 * SZREG */
-ENTRY(__riscv_copy_words_unaligned)
+SYM_FUNC_START(__riscv_copy_words_unaligned)
 	andi  a4, a2, ~((8*SZREG)-1)
 	beqz  a4, 2f
 	add   a3, a1, a4
@@ -36,12 +36,12 @@ ENTRY(__riscv_copy_words_unaligned)
 
 2:
 	ret
-END(__riscv_copy_words_unaligned)
+SYM_FUNC_END(__riscv_copy_words_unaligned)
 
 /* void __riscv_copy_bytes_unaligned(void *, const void *, size_t) */
 /* Performs a memcpy without aligning buffers, using only byte accesses. */
 /* Note: The size is truncated to a multiple of 8 */
-ENTRY(__riscv_copy_bytes_unaligned)
+SYM_FUNC_START(__riscv_copy_bytes_unaligned)
 	andi a4, a2, ~(8-1)
 	beqz a4, 2f
 	add  a3, a1, a4
@@ -68,4 +68,4 @@ ENTRY(__riscv_copy_bytes_unaligned)
 
 2:
 	ret
-END(__riscv_copy_bytes_unaligned)
+SYM_FUNC_END(__riscv_copy_bytes_unaligned)
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index c17dacb1141c..d11d6320fb0d 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -125,13 +125,14 @@ old_interface:
  */
 int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid)
 {
-	int rc;
-
 	for (; node; node = node->parent) {
 		if (of_device_is_compatible(node, "riscv")) {
-			rc = riscv_of_processor_hartid(node, hartid);
-			if (!rc)
-				return 0;
+			*hartid = (unsigned long)of_get_cpu_hwid(node, 0);
+			if (*hartid == ~0UL) {
+				pr_warn("Found CPU without hart ID\n");
+				return -ENODEV;
+			}
+			return 0;
 		}
 	}
 
@@ -202,9 +203,8 @@ arch_initcall(riscv_cpuinfo_init);
 
 #ifdef CONFIG_PROC_FS
 
-static void print_isa(struct seq_file *f)
+static void print_isa(struct seq_file *f, const unsigned long *isa_bitmap)
 {
-	seq_puts(f, "isa\t\t: ");
 
 	if (IS_ENABLED(CONFIG_32BIT))
 		seq_write(f, "rv32", 4);
@@ -212,7 +212,7 @@ static void print_isa(struct seq_file *f)
 		seq_write(f, "rv64", 4);
 
 	for (int i = 0; i < riscv_isa_ext_count; i++) {
-		if (!__riscv_isa_extension_available(NULL, riscv_isa_ext[i].id))
+		if (!__riscv_isa_extension_available(isa_bitmap, riscv_isa_ext[i].id))
 			continue;
 
 		/* Only multi-letter extensions are split by underscores */
@@ -276,7 +276,15 @@ static int c_show(struct seq_file *m, void *v)
 
 	seq_printf(m, "processor\t: %lu\n", cpu_id);
 	seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id));
-	print_isa(m);
+
+	/*
+	 * For historical raisins, the isa: line is limited to the lowest common
+	 * denominator of extensions supported across all harts. A true list of
+	 * extensions supported on this hart is printed later in the hart isa:
+	 * line.
+	 */
+	seq_puts(m, "isa\t\t: ");
+	print_isa(m, NULL);
 	print_mmu(m);
 
 	if (acpi_disabled) {
@@ -292,6 +300,13 @@ static int c_show(struct seq_file *m, void *v)
 	seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid);
 	seq_printf(m, "marchid\t\t: 0x%lx\n", ci->marchid);
 	seq_printf(m, "mimpid\t\t: 0x%lx\n", ci->mimpid);
+
+	/*
+	 * Print the ISA extensions specific to this hart, which may show
+	 * additional extensions not present across all harts.
+	 */
+	seq_puts(m, "hart isa\t: ");
+	print_isa(m, hart_isa[cpu_id].isa);
 	seq_puts(m, "\n");
 
 	return 0;
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 7aeba01dcfd4..b3785ffc1570 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -8,6 +8,7 @@
 
 #include <linux/acpi.h>
 #include <linux/bitmap.h>
+#include <linux/cpuhotplug.h>
 #include <linux/ctype.h>
 #include <linux/log2.h>
 #include <linux/memory.h>
@@ -29,6 +30,7 @@
 
 #define MISALIGNED_ACCESS_JIFFIES_LG2 1
 #define MISALIGNED_BUFFER_SIZE 0x4000
+#define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE)
 #define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80)
 
 unsigned long elf_hwcap __read_mostly;
@@ -559,23 +561,21 @@ unsigned long riscv_get_elf_hwcap(void)
 	return hwcap;
 }
 
-void check_unaligned_access(int cpu)
+static int check_unaligned_access(void *param)
 {
+	int cpu = smp_processor_id();
 	u64 start_cycles, end_cycles;
 	u64 word_cycles;
 	u64 byte_cycles;
 	int ratio;
 	unsigned long start_jiffies, now;
-	struct page *page;
+	struct page *page = param;
 	void *dst;
 	void *src;
 	long speed = RISCV_HWPROBE_MISALIGNED_SLOW;
 
-	page = alloc_pages(GFP_NOWAIT, get_order(MISALIGNED_BUFFER_SIZE));
-	if (!page) {
-		pr_warn("Can't alloc pages to measure memcpy performance");
-		return;
-	}
+	if (check_unaligned_access_emulated(cpu))
+		return 0;
 
 	/* Make an unaligned destination buffer. */
 	dst = (void *)((unsigned long)page_address(page) | 0x1);
@@ -629,7 +629,7 @@ void check_unaligned_access(int cpu)
 		pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n",
 			cpu);
 
-		goto out;
+		return 0;
 	}
 
 	if (word_cycles < byte_cycles)
@@ -643,18 +643,84 @@ void check_unaligned_access(int cpu)
 		(speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
 
 	per_cpu(misaligned_access_speed, cpu) = speed;
+	return 0;
+}
 
-out:
-	__free_pages(page, get_order(MISALIGNED_BUFFER_SIZE));
+static void check_unaligned_access_nonboot_cpu(void *param)
+{
+	unsigned int cpu = smp_processor_id();
+	struct page **pages = param;
+
+	if (smp_processor_id() != 0)
+		check_unaligned_access(pages[cpu]);
+}
+
+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;
+
+	buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
+	if (!buf) {
+		pr_warn("Allocation failure, not measuring misaligned performance\n");
+		return -ENOMEM;
+	}
+
+	check_unaligned_access(buf);
+	__free_pages(buf, MISALIGNED_BUFFER_ORDER);
+	return 0;
 }
 
-static int check_unaligned_access_boot_cpu(void)
+/* Measure unaligned access on all CPUs present at boot in parallel. */
+static int check_unaligned_access_all_cpus(void)
 {
-	check_unaligned_access(0);
+	unsigned int cpu;
+	unsigned int cpu_count = num_possible_cpus();
+	struct page **bufs = kzalloc(cpu_count * sizeof(struct page *),
+				     GFP_KERNEL);
+
+	if (!bufs) {
+		pr_warn("Allocation failure, not measuring misaligned performance\n");
+		return 0;
+	}
+
+	/*
+	 * Allocate separate buffers for each CPU so there's no fighting over
+	 * cache lines.
+	 */
+	for_each_cpu(cpu, cpu_online_mask) {
+		bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
+		if (!bufs[cpu]) {
+			pr_warn("Allocation failure, not measuring misaligned performance\n");
+			goto out;
+		}
+	}
+
+	/* Check everybody except 0, who stays behind to tend jiffies. */
+	on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1);
+
+	/* Check core 0. */
+	smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
+
+	/* Setup hotplug callback for any new CPUs that come online. */
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
+				  riscv_online_cpu, NULL);
+
+out:
+	unaligned_emulation_finish();
+	for_each_cpu(cpu, cpu_online_mask) {
+		if (bufs[cpu])
+			__free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER);
+	}
+
+	kfree(bufs);
 	return 0;
 }
 
-arch_initcall(check_unaligned_access_boot_cpu);
+arch_initcall(check_unaligned_access_all_cpus);
 
 void riscv_user_isa_enable(void)
 {
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 9f92c067f7e1..54ca4564a926 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -26,9 +26,9 @@ SYM_CODE_START(handle_exception)
 	 * register will contain 0, and we should continue on the current TP.
 	 */
 	csrrw tp, CSR_SCRATCH, tp
-	bnez tp, _save_context
+	bnez tp, .Lsave_context
 
-_restore_kernel_tpsp:
+.Lrestore_kernel_tpsp:
 	csrr tp, CSR_SCRATCH
 	REG_S sp, TASK_TI_KERNEL_SP(tp)
 
@@ -40,7 +40,7 @@ _restore_kernel_tpsp:
 	REG_L sp, TASK_TI_KERNEL_SP(tp)
 #endif
 
-_save_context:
+.Lsave_context:
 	REG_S sp, TASK_TI_USER_SP(tp)
 	REG_L sp, TASK_TI_KERNEL_SP(tp)
 	addi sp, sp, -(PT_SIZE_ON_STACK)
@@ -322,7 +322,7 @@ SYM_FUNC_END(__switch_to)
 	.section ".rodata"
 	.align LGREG
 	/* Exception vector table */
-SYM_CODE_START(excp_vect_table)
+SYM_DATA_START_LOCAL(excp_vect_table)
 	RISCV_PTR do_trap_insn_misaligned
 	ALT_INSN_FAULT(RISCV_PTR do_trap_insn_fault)
 	RISCV_PTR do_trap_insn_illegal
@@ -340,12 +340,11 @@ SYM_CODE_START(excp_vect_table)
 	RISCV_PTR do_page_fault   /* load page fault */
 	RISCV_PTR do_trap_unknown
 	RISCV_PTR do_page_fault   /* store page fault */
-excp_vect_table_end:
-SYM_CODE_END(excp_vect_table)
+SYM_DATA_END_LABEL(excp_vect_table, SYM_L_LOCAL, excp_vect_table_end)
 
 #ifndef CONFIG_MMU
-SYM_CODE_START(__user_rt_sigreturn)
+SYM_DATA_START(__user_rt_sigreturn)
 	li a7, __NR_rt_sigreturn
 	ecall
-SYM_CODE_END(__user_rt_sigreturn)
+SYM_DATA_END(__user_rt_sigreturn)
 #endif
diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S
index dd2205473de7..2c543f130f93 100644
--- a/arch/riscv/kernel/fpu.S
+++ b/arch/riscv/kernel/fpu.S
@@ -19,7 +19,7 @@
 #include <asm/csr.h>
 #include <asm/asm-offsets.h>
 
-ENTRY(__fstate_save)
+SYM_FUNC_START(__fstate_save)
 	li  a2,  TASK_THREAD_F0
 	add a0, a0, a2
 	li t1, SR_FS
@@ -60,9 +60,9 @@ ENTRY(__fstate_save)
 	sw t0, TASK_THREAD_FCSR_F0(a0)
 	csrc CSR_STATUS, t1
 	ret
-ENDPROC(__fstate_save)
+SYM_FUNC_END(__fstate_save)
 
-ENTRY(__fstate_restore)
+SYM_FUNC_START(__fstate_restore)
 	li  a2,  TASK_THREAD_F0
 	add a0, a0, a2
 	li t1, SR_FS
@@ -103,4 +103,125 @@ ENTRY(__fstate_restore)
 	fscsr t0
 	csrc CSR_STATUS, t1
 	ret
-ENDPROC(__fstate_restore)
+SYM_FUNC_END(__fstate_restore)
+
+#define get_f32(which) fmv.x.s a0, which; j 2f
+#define put_f32(which) fmv.s.x which, a1; j 2f
+#if __riscv_xlen == 64
+# define get_f64(which) fmv.x.d a0, which; j 2f
+# define put_f64(which) fmv.d.x which, a1; j 2f
+#else
+# define get_f64(which) fsd which, 0(a1); j 2f
+# define put_f64(which) fld which, 0(a1); j 2f
+#endif
+
+.macro fp_access_prologue
+	/*
+	 * Compute jump offset to store the correct FP register since we don't
+	 * have indirect FP register access
+	 */
+	sll t0, a0, 3
+	la t2, 1f
+	add t0, t0, t2
+	li t1, SR_FS
+	csrs CSR_STATUS, t1
+	jr t0
+1:
+.endm
+
+.macro fp_access_epilogue
+2:
+	csrc CSR_STATUS, t1
+	ret
+.endm
+
+#define fp_access_body(__access_func) \
+	__access_func(f0); \
+	__access_func(f1); \
+	__access_func(f2); \
+	__access_func(f3); \
+	__access_func(f4); \
+	__access_func(f5); \
+	__access_func(f6); \
+	__access_func(f7); \
+	__access_func(f8); \
+	__access_func(f9); \
+	__access_func(f10); \
+	__access_func(f11); \
+	__access_func(f12); \
+	__access_func(f13); \
+	__access_func(f14); \
+	__access_func(f15); \
+	__access_func(f16); \
+	__access_func(f17); \
+	__access_func(f18); \
+	__access_func(f19); \
+	__access_func(f20); \
+	__access_func(f21); \
+	__access_func(f22); \
+	__access_func(f23); \
+	__access_func(f24); \
+	__access_func(f25); \
+	__access_func(f26); \
+	__access_func(f27); \
+	__access_func(f28); \
+	__access_func(f29); \
+	__access_func(f30); \
+	__access_func(f31)
+
+
+#ifdef CONFIG_RISCV_MISALIGNED
+
+/*
+ * Disable compressed instructions set to keep a constant offset between FP
+ * load/store/move instructions
+ */
+.option norvc
+/*
+ * put_f32_reg - Set a FP register from a register containing the value
+ * a0 = FP register index to be set
+ * a1 = value to be loaded in the FP register
+ */
+SYM_FUNC_START(put_f32_reg)
+	fp_access_prologue
+	fp_access_body(put_f32)
+	fp_access_epilogue
+SYM_FUNC_END(put_f32_reg)
+
+/*
+ * get_f32_reg - Get a FP register value and return it
+ * a0 = FP register index to be retrieved
+ */
+SYM_FUNC_START(get_f32_reg)
+	fp_access_prologue
+	fp_access_body(get_f32)
+	fp_access_epilogue
+SYM_FUNC_END(get_f32_reg)
+
+/*
+ * put_f64_reg - Set a 64 bits FP register from a value or a pointer.
+ * a0 = FP register index to be set
+ * a1 = value/pointer to be loaded in the FP register (when xlen == 32 bits, we
+ * load the value to a pointer).
+ */
+SYM_FUNC_START(put_f64_reg)
+	fp_access_prologue
+	fp_access_body(put_f64)
+	fp_access_epilogue
+SYM_FUNC_END(put_f64_reg)
+
+/*
+ * put_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
+ *	or unused if xlen == 64. In which case the FP register value is returned
+ *	through a0
+ */
+SYM_FUNC_START(get_f64_reg)
+	fp_access_prologue
+	fp_access_body(get_f64)
+	fp_access_epilogue
+SYM_FUNC_END(get_f64_reg)
+
+#endif /* CONFIG_RISCV_MISALIGNED */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 18f97ec0f7ed..b77397432403 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -19,7 +19,7 @@
 #include "efi-header.S"
 
 __HEAD
-ENTRY(_start)
+SYM_CODE_START(_start)
 	/*
 	 * Image header expected by Linux boot-loaders. The image header data
 	 * structure is described in asm/image.h.
@@ -164,12 +164,12 @@ secondary_start_sbi:
 	XIP_FIXUP_OFFSET a0
 	call relocate_enable_mmu
 #endif
-	call setup_trap_vector
+	call .Lsetup_trap_vector
 	tail smp_callin
 #endif /* CONFIG_SMP */
 
 .align 2
-setup_trap_vector:
+.Lsetup_trap_vector:
 	/* Set trap vector to exception handler */
 	la a0, handle_exception
 	csrw CSR_TVEC, a0
@@ -187,9 +187,9 @@ setup_trap_vector:
 	wfi
 	j .Lsecondary_park
 
-END(_start)
+SYM_CODE_END(_start)
 
-ENTRY(_start_kernel)
+SYM_CODE_START(_start_kernel)
 	/* Mask all interrupts */
 	csrw CSR_IE, zero
 	csrw CSR_IP, zero
@@ -206,7 +206,7 @@ ENTRY(_start_kernel)
 	 * not implement PMPs, so we set up a quick trap handler to just skip
 	 * touching the PMPs on any trap.
 	 */
-	la a0, pmp_done
+	la a0, .Lpmp_done
 	csrw CSR_TVEC, a0
 
 	li a0, -1
@@ -214,7 +214,7 @@ ENTRY(_start_kernel)
 	li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X)
 	csrw CSR_PMPCFG0, a0
 .align 2
-pmp_done:
+.Lpmp_done:
 
 	/*
 	 * The hartid in a0 is expected later on, and we have no firmware
@@ -275,12 +275,12 @@ pmp_done:
 	/* Clear BSS for flat non-ELF images */
 	la a3, __bss_start
 	la a4, __bss_stop
-	ble a4, a3, clear_bss_done
-clear_bss:
+	ble a4, a3, .Lclear_bss_done
+.Lclear_bss:
 	REG_S zero, (a3)
 	add a3, a3, RISCV_SZPTR
-	blt a3, a4, clear_bss
-clear_bss_done:
+	blt a3, a4, .Lclear_bss
+.Lclear_bss_done:
 #endif
 	la a2, boot_cpu_hartid
 	XIP_FIXUP_OFFSET a2
@@ -305,7 +305,7 @@ clear_bss_done:
 	call relocate_enable_mmu
 #endif /* CONFIG_MMU */
 
-	call setup_trap_vector
+	call .Lsetup_trap_vector
 	/* Restore C environment */
 	la tp, init_task
 	la sp, init_thread_union + THREAD_SIZE
@@ -348,10 +348,10 @@ clear_bss_done:
 	tail .Lsecondary_start_common
 #endif /* CONFIG_RISCV_BOOT_SPINWAIT */
 
-END(_start_kernel)
+SYM_CODE_END(_start_kernel)
 
 #ifdef CONFIG_RISCV_M_MODE
-ENTRY(reset_regs)
+SYM_CODE_START_LOCAL(reset_regs)
 	li	sp, 0
 	li	gp, 0
 	li	tp, 0
@@ -449,5 +449,5 @@ ENTRY(reset_regs)
 .Lreset_regs_done_vector:
 #endif /* CONFIG_RISCV_ISA_V */
 	ret
-END(reset_regs)
+SYM_CODE_END(reset_regs)
 #endif /* CONFIG_RISCV_M_MODE */
diff --git a/arch/riscv/kernel/hibernate-asm.S b/arch/riscv/kernel/hibernate-asm.S
index d698dd7df637..d040dcf4add4 100644
--- a/arch/riscv/kernel/hibernate-asm.S
+++ b/arch/riscv/kernel/hibernate-asm.S
@@ -21,7 +21,7 @@
  *
  * Always returns 0
  */
-ENTRY(__hibernate_cpu_resume)
+SYM_FUNC_START(__hibernate_cpu_resume)
 	/* switch to hibernated image's page table. */
 	csrw CSR_SATP, s0
 	sfence.vma
@@ -34,7 +34,7 @@ ENTRY(__hibernate_cpu_resume)
 	mv	a0, zero
 
 	ret
-END(__hibernate_cpu_resume)
+SYM_FUNC_END(__hibernate_cpu_resume)
 
 /*
  * Prepare to restore the image.
@@ -42,7 +42,7 @@ END(__hibernate_cpu_resume)
  * a1: satp of temporary page tables.
  * a2: cpu_resume.
  */
-ENTRY(hibernate_restore_image)
+SYM_FUNC_START(hibernate_restore_image)
 	mv	s0, a0
 	mv	s1, a1
 	mv	s2, a2
@@ -50,7 +50,7 @@ ENTRY(hibernate_restore_image)
 	REG_L	a1, relocated_restore_code
 
 	jr	a1
-END(hibernate_restore_image)
+SYM_FUNC_END(hibernate_restore_image)
 
 /*
  * The below code will be executed from a 'safe' page.
@@ -58,7 +58,7 @@ END(hibernate_restore_image)
  * back to the original memory location. Finally, it jumps to __hibernate_cpu_resume()
  * to restore the CPU context.
  */
-ENTRY(hibernate_core_restore_code)
+SYM_FUNC_START(hibernate_core_restore_code)
 	/* switch to temp page table. */
 	csrw satp, s1
 	sfence.vma
@@ -73,4 +73,4 @@ ENTRY(hibernate_core_restore_code)
 	bnez	s4, .Lcopy
 
 	jr	s2
-END(hibernate_core_restore_code)
+SYM_FUNC_END(hibernate_core_restore_code)
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index 669b8697aa38..58dd96a2a153 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -82,7 +82,7 @@
 	.endm
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
-ENTRY(ftrace_caller)
+SYM_FUNC_START(ftrace_caller)
 	SAVE_ABI
 
 	addi	a0, t0, -FENTRY_RA_OFFSET
@@ -91,8 +91,7 @@ ENTRY(ftrace_caller)
 	mv	a1, ra
 	mv	a3, sp
 
-ftrace_call:
-	.global ftrace_call
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -102,16 +101,15 @@ ftrace_call:
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	mv	a2, s0
 #endif
-ftrace_graph_call:
-	.global ftrace_graph_call
+SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 #endif
 	RESTORE_ABI
 	jr t0
-ENDPROC(ftrace_caller)
+SYM_FUNC_END(ftrace_caller)
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-ENTRY(ftrace_regs_caller)
+SYM_FUNC_START(ftrace_regs_caller)
 	SAVE_ALL
 
 	addi	a0, t0, -FENTRY_RA_OFFSET
@@ -120,8 +118,7 @@ ENTRY(ftrace_regs_caller)
 	mv	a1, ra
 	mv	a3, sp
 
-ftrace_regs_call:
-	.global ftrace_regs_call
+SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -131,12 +128,11 @@ ftrace_regs_call:
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	mv	a2, s0
 #endif
-ftrace_graph_regs_call:
-	.global ftrace_graph_regs_call
+SYM_INNER_LABEL(ftrace_graph_regs_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 #endif
 
 	RESTORE_ALL
 	jr t0
-ENDPROC(ftrace_regs_caller)
+SYM_FUNC_END(ftrace_regs_caller)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index 8818a8fa9ff3..b4dd9ed6849e 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -61,7 +61,7 @@ SYM_TYPED_FUNC_START(ftrace_stub_graph)
 	ret
 SYM_FUNC_END(ftrace_stub_graph)
 
-ENTRY(return_to_handler)
+SYM_FUNC_START(return_to_handler)
 /*
  * On implementing the frame point test, the ideal way is to compare the
  * s0 (frame pointer, if enabled) on entry and the sp (stack pointer) on return.
@@ -76,25 +76,25 @@ ENTRY(return_to_handler)
 	mv	a2, a0
 	RESTORE_RET_ABI_STATE
 	jalr	a2
-ENDPROC(return_to_handler)
+SYM_FUNC_END(return_to_handler)
 #endif
 
 #ifndef CONFIG_DYNAMIC_FTRACE
-ENTRY(MCOUNT_NAME)
+SYM_FUNC_START(MCOUNT_NAME)
 	la	t4, ftrace_stub
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	la	t0, ftrace_graph_return
 	REG_L	t1, 0(t0)
-	bne	t1, t4, do_ftrace_graph_caller
+	bne	t1, t4, .Ldo_ftrace_graph_caller
 
 	la	t3, ftrace_graph_entry
 	REG_L	t2, 0(t3)
 	la	t6, ftrace_graph_entry_stub
-	bne	t2, t6, do_ftrace_graph_caller
+	bne	t2, t6, .Ldo_ftrace_graph_caller
 #endif
 	la	t3, ftrace_trace_function
 	REG_L	t5, 0(t3)
-	bne	t5, t4, do_trace
+	bne	t5, t4, .Ldo_trace
 	ret
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -102,7 +102,7 @@ ENTRY(MCOUNT_NAME)
  * A pseudo representation for the function graph tracer:
  * prepare_to_return(&ra_to_caller_of_caller, ra_to_caller)
  */
-do_ftrace_graph_caller:
+.Ldo_ftrace_graph_caller:
 	addi	a0, s0, -SZREG
 	mv	a1, ra
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
@@ -118,7 +118,7 @@ do_ftrace_graph_caller:
  * A pseudo representation for the function tracer:
  * (*ftrace_trace_function)(ra_to_caller, ra_to_caller_of_caller)
  */
-do_trace:
+.Ldo_trace:
 	REG_L	a1, -SZREG(s0)
 	mv	a0, ra
 
@@ -126,6 +126,6 @@ do_trace:
 	jalr	t5
 	RESTORE_ABI_STATE
 	ret
-ENDPROC(MCOUNT_NAME)
+SYM_FUNC_END(MCOUNT_NAME)
 #endif
 EXPORT_SYMBOL(MCOUNT_NAME)
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 7c651d55fcbd..56a8c78e9e21 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -7,6 +7,9 @@
 #include <linux/elf.h>
 #include <linux/err.h>
 #include <linux/errno.h>
+#include <linux/hashtable.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
 #include <linux/moduleloader.h>
 #include <linux/vmalloc.h>
 #include <linux/sizes.h>
@@ -14,6 +17,38 @@
 #include <asm/alternative.h>
 #include <asm/sections.h>
 
+struct used_bucket {
+	struct list_head head;
+	struct hlist_head *bucket;
+};
+
+struct relocation_head {
+	struct hlist_node node;
+	struct list_head *rel_entry;
+	void *location;
+};
+
+struct relocation_entry {
+	struct list_head head;
+	Elf_Addr value;
+	unsigned int type;
+};
+
+struct relocation_handlers {
+	int (*reloc_handler)(struct module *me, void *location, Elf_Addr v);
+	int (*accumulate_handler)(struct module *me, void *location,
+				  long buffer);
+};
+
+unsigned int initialize_relocation_hashtable(unsigned int num_relocations);
+void process_accumulated_relocations(struct module *me);
+int add_relocation_to_accumulate(struct module *me, int type, void *location,
+				 unsigned int hashtable_bits, Elf_Addr v);
+
+struct hlist_head *relocation_hashtable;
+
+struct list_head used_buckets_list;
+
 /*
  * The auipc+jalr instruction pair can reach any PC-relative offset
  * in the range [-2^31 - 2^11, 2^31 - 2^11)
@@ -27,68 +62,90 @@ static bool riscv_insn_valid_32bit_offset(ptrdiff_t val)
 #endif
 }
 
-static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v)
+static int riscv_insn_rmw(void *location, u32 keep, u32 set)
+{
+	u16 *parcel = location;
+	u32 insn = (u32)le16_to_cpu(parcel[0]) | (u32)le16_to_cpu(parcel[1]) << 16;
+
+	insn &= keep;
+	insn |= set;
+
+	parcel[0] = cpu_to_le16(insn);
+	parcel[1] = cpu_to_le16(insn >> 16);
+	return 0;
+}
+
+static int riscv_insn_rvc_rmw(void *location, u16 keep, u16 set)
+{
+	u16 *parcel = location;
+	u16 insn = le16_to_cpu(*parcel);
+
+	insn &= keep;
+	insn |= set;
+
+	*parcel = cpu_to_le16(insn);
+	return 0;
+}
+
+static int apply_r_riscv_32_rela(struct module *me, void *location, Elf_Addr v)
 {
 	if (v != (u32)v) {
 		pr_err("%s: value %016llx out of range for 32-bit field\n",
 		       me->name, (long long)v);
 		return -EINVAL;
 	}
-	*location = v;
+	*(u32 *)location = v;
 	return 0;
 }
 
-static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v)
+static int apply_r_riscv_64_rela(struct module *me, void *location, Elf_Addr v)
 {
 	*(u64 *)location = v;
 	return 0;
 }
 
-static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
+static int apply_r_riscv_branch_rela(struct module *me, void *location,
 				     Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - location;
 	u32 imm12 = (offset & 0x1000) << (31 - 12);
 	u32 imm11 = (offset & 0x800) >> (11 - 7);
 	u32 imm10_5 = (offset & 0x7e0) << (30 - 10);
 	u32 imm4_1 = (offset & 0x1e) << (11 - 4);
 
-	*location = (*location & 0x1fff07f) | imm12 | imm11 | imm10_5 | imm4_1;
-	return 0;
+	return riscv_insn_rmw(location, 0x1fff07f, imm12 | imm11 | imm10_5 | imm4_1);
 }
 
-static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
+static int apply_r_riscv_jal_rela(struct module *me, void *location,
 				  Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - location;
 	u32 imm20 = (offset & 0x100000) << (31 - 20);
 	u32 imm19_12 = (offset & 0xff000);
 	u32 imm11 = (offset & 0x800) << (20 - 11);
 	u32 imm10_1 = (offset & 0x7fe) << (30 - 10);
 
-	*location = (*location & 0xfff) | imm20 | imm19_12 | imm11 | imm10_1;
-	return 0;
+	return riscv_insn_rmw(location, 0xfff, imm20 | imm19_12 | imm11 | imm10_1);
 }
 
-static int apply_r_riscv_rvc_branch_rela(struct module *me, u32 *location,
+static int apply_r_riscv_rvc_branch_rela(struct module *me, void *location,
 					 Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - location;
 	u16 imm8 = (offset & 0x100) << (12 - 8);
 	u16 imm7_6 = (offset & 0xc0) >> (6 - 5);
 	u16 imm5 = (offset & 0x20) >> (5 - 2);
 	u16 imm4_3 = (offset & 0x18) << (12 - 5);
 	u16 imm2_1 = (offset & 0x6) << (12 - 10);
 
-	*(u16 *)location = (*(u16 *)location & 0xe383) |
-		    imm8 | imm7_6 | imm5 | imm4_3 | imm2_1;
-	return 0;
+	return riscv_insn_rvc_rmw(location, 0xe383,
+			imm8 | imm7_6 | imm5 | imm4_3 | imm2_1);
 }
 
-static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location,
+static int apply_r_riscv_rvc_jump_rela(struct module *me, void *location,
 				       Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - location;
 	u16 imm11 = (offset & 0x800) << (12 - 11);
 	u16 imm10 = (offset & 0x400) >> (10 - 8);
 	u16 imm9_8 = (offset & 0x300) << (12 - 11);
@@ -98,16 +155,14 @@ static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location,
 	u16 imm4 = (offset & 0x10) << (12 - 5);
 	u16 imm3_1 = (offset & 0xe) << (12 - 10);
 
-	*(u16 *)location = (*(u16 *)location & 0xe003) |
-		    imm11 | imm10 | imm9_8 | imm7 | imm6 | imm5 | imm4 | imm3_1;
-	return 0;
+	return riscv_insn_rvc_rmw(location, 0xe003,
+			imm11 | imm10 | imm9_8 | imm7 | imm6 | imm5 | imm4 | imm3_1);
 }
 
-static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
+static int apply_r_riscv_pcrel_hi20_rela(struct module *me, void *location,
 					 Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
-	s32 hi20;
+	ptrdiff_t offset = (void *)v - location;
 
 	if (!riscv_insn_valid_32bit_offset(offset)) {
 		pr_err(
@@ -116,23 +171,20 @@ static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
 		return -EINVAL;
 	}
 
-	hi20 = (offset + 0x800) & 0xfffff000;
-	*location = (*location & 0xfff) | hi20;
-	return 0;
+	return riscv_insn_rmw(location, 0xfff, (offset + 0x800) & 0xfffff000);
 }
 
-static int apply_r_riscv_pcrel_lo12_i_rela(struct module *me, u32 *location,
+static int apply_r_riscv_pcrel_lo12_i_rela(struct module *me, void *location,
 					   Elf_Addr v)
 {
 	/*
 	 * v is the lo12 value to fill. It is calculated before calling this
 	 * handler.
 	 */
-	*location = (*location & 0xfffff) | ((v & 0xfff) << 20);
-	return 0;
+	return riscv_insn_rmw(location, 0xfffff, (v & 0xfff) << 20);
 }
 
-static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, u32 *location,
+static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, void *location,
 					   Elf_Addr v)
 {
 	/*
@@ -142,15 +194,12 @@ static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, u32 *location,
 	u32 imm11_5 = (v & 0xfe0) << (31 - 11);
 	u32 imm4_0 = (v & 0x1f) << (11 - 4);
 
-	*location = (*location & 0x1fff07f) | imm11_5 | imm4_0;
-	return 0;
+	return riscv_insn_rmw(location, 0x1fff07f, imm11_5 | imm4_0);
 }
 
-static int apply_r_riscv_hi20_rela(struct module *me, u32 *location,
+static int apply_r_riscv_hi20_rela(struct module *me, void *location,
 				   Elf_Addr v)
 {
-	s32 hi20;
-
 	if (IS_ENABLED(CONFIG_CMODEL_MEDLOW)) {
 		pr_err(
 		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
@@ -158,22 +207,20 @@ static int apply_r_riscv_hi20_rela(struct module *me, u32 *location,
 		return -EINVAL;
 	}
 
-	hi20 = ((s32)v + 0x800) & 0xfffff000;
-	*location = (*location & 0xfff) | hi20;
-	return 0;
+	return riscv_insn_rmw(location, 0xfff, ((s32)v + 0x800) & 0xfffff000);
 }
 
-static int apply_r_riscv_lo12_i_rela(struct module *me, u32 *location,
+static int apply_r_riscv_lo12_i_rela(struct module *me, void *location,
 				     Elf_Addr v)
 {
 	/* Skip medlow checking because of filtering by HI20 already */
 	s32 hi20 = ((s32)v + 0x800) & 0xfffff000;
 	s32 lo12 = ((s32)v - hi20);
-	*location = (*location & 0xfffff) | ((lo12 & 0xfff) << 20);
-	return 0;
+
+	return riscv_insn_rmw(location, 0xfffff, (lo12 & 0xfff) << 20);
 }
 
-static int apply_r_riscv_lo12_s_rela(struct module *me, u32 *location,
+static int apply_r_riscv_lo12_s_rela(struct module *me, void *location,
 				     Elf_Addr v)
 {
 	/* Skip medlow checking because of filtering by HI20 already */
@@ -181,20 +228,18 @@ static int apply_r_riscv_lo12_s_rela(struct module *me, u32 *location,
 	s32 lo12 = ((s32)v - hi20);
 	u32 imm11_5 = (lo12 & 0xfe0) << (31 - 11);
 	u32 imm4_0 = (lo12 & 0x1f) << (11 - 4);
-	*location = (*location & 0x1fff07f) | imm11_5 | imm4_0;
-	return 0;
+
+	return riscv_insn_rmw(location, 0x1fff07f, imm11_5 | imm4_0);
 }
 
-static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
+static int apply_r_riscv_got_hi20_rela(struct module *me, void *location,
 				       Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
-	s32 hi20;
+	ptrdiff_t offset = (void *)v - location;
 
 	/* Always emit the got entry */
 	if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) {
-		offset = module_emit_got_entry(me, v);
-		offset = (void *)offset - (void *)location;
+		offset = (void *)module_emit_got_entry(me, v) - location;
 	} else {
 		pr_err(
 		  "%s: can not generate the GOT entry for symbol = %016llx from PC = %p\n",
@@ -202,22 +247,19 @@ static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
 		return -EINVAL;
 	}
 
-	hi20 = (offset + 0x800) & 0xfffff000;
-	*location = (*location & 0xfff) | hi20;
-	return 0;
+	return riscv_insn_rmw(location, 0xfff, (offset + 0x800) & 0xfffff000);
 }
 
-static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
+static int apply_r_riscv_call_plt_rela(struct module *me, void *location,
 				       Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - location;
 	u32 hi20, lo12;
 
 	if (!riscv_insn_valid_32bit_offset(offset)) {
 		/* Only emit the plt entry if offset over 32-bit range */
 		if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) {
-			offset = module_emit_plt_entry(me, v);
-			offset = (void *)offset - (void *)location;
+			offset = (void *)module_emit_plt_entry(me, v) - location;
 		} else {
 			pr_err(
 			  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
@@ -228,15 +270,14 @@ static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
 
 	hi20 = (offset + 0x800) & 0xfffff000;
 	lo12 = (offset - hi20) & 0xfff;
-	*location = (*location & 0xfff) | hi20;
-	*(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20);
-	return 0;
+	riscv_insn_rmw(location, 0xfff, hi20);
+	return riscv_insn_rmw(location + 4, 0xfffff, lo12 << 20);
 }
 
-static int apply_r_riscv_call_rela(struct module *me, u32 *location,
+static int apply_r_riscv_call_rela(struct module *me, void *location,
 				   Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - location;
 	u32 hi20, lo12;
 
 	if (!riscv_insn_valid_32bit_offset(offset)) {
@@ -248,18 +289,17 @@ static int apply_r_riscv_call_rela(struct module *me, u32 *location,
 
 	hi20 = (offset + 0x800) & 0xfffff000;
 	lo12 = (offset - hi20) & 0xfff;
-	*location = (*location & 0xfff) | hi20;
-	*(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20);
-	return 0;
+	riscv_insn_rmw(location, 0xfff, hi20);
+	return riscv_insn_rmw(location + 4, 0xfffff, lo12 << 20);
 }
 
-static int apply_r_riscv_relax_rela(struct module *me, u32 *location,
+static int apply_r_riscv_relax_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	return 0;
 }
 
-static int apply_r_riscv_align_rela(struct module *me, u32 *location,
+static int apply_r_riscv_align_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	pr_err(
@@ -268,91 +308,446 @@ static int apply_r_riscv_align_rela(struct module *me, u32 *location,
 	return -EINVAL;
 }
 
-static int apply_r_riscv_add16_rela(struct module *me, u32 *location,
+static int apply_r_riscv_add8_rela(struct module *me, void *location, Elf_Addr v)
+{
+	*(u8 *)location += (u8)v;
+	return 0;
+}
+
+static int apply_r_riscv_add16_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	*(u16 *)location += (u16)v;
 	return 0;
 }
 
-static int apply_r_riscv_add32_rela(struct module *me, u32 *location,
+static int apply_r_riscv_add32_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	*(u32 *)location += (u32)v;
 	return 0;
 }
 
-static int apply_r_riscv_add64_rela(struct module *me, u32 *location,
+static int apply_r_riscv_add64_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	*(u64 *)location += (u64)v;
 	return 0;
 }
 
-static int apply_r_riscv_sub16_rela(struct module *me, u32 *location,
+static int apply_r_riscv_sub8_rela(struct module *me, void *location, Elf_Addr v)
+{
+	*(u8 *)location -= (u8)v;
+	return 0;
+}
+
+static int apply_r_riscv_sub16_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	*(u16 *)location -= (u16)v;
 	return 0;
 }
 
-static int apply_r_riscv_sub32_rela(struct module *me, u32 *location,
+static int apply_r_riscv_sub32_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	*(u32 *)location -= (u32)v;
 	return 0;
 }
 
-static int apply_r_riscv_sub64_rela(struct module *me, u32 *location,
+static int apply_r_riscv_sub64_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	*(u64 *)location -= (u64)v;
 	return 0;
 }
 
-static int (*reloc_handlers_rela[]) (struct module *me, u32 *location,
-				Elf_Addr v) = {
-	[R_RISCV_32]			= apply_r_riscv_32_rela,
-	[R_RISCV_64]			= apply_r_riscv_64_rela,
-	[R_RISCV_BRANCH]		= apply_r_riscv_branch_rela,
-	[R_RISCV_JAL]			= apply_r_riscv_jal_rela,
-	[R_RISCV_RVC_BRANCH]		= apply_r_riscv_rvc_branch_rela,
-	[R_RISCV_RVC_JUMP]		= apply_r_riscv_rvc_jump_rela,
-	[R_RISCV_PCREL_HI20]		= apply_r_riscv_pcrel_hi20_rela,
-	[R_RISCV_PCREL_LO12_I]		= apply_r_riscv_pcrel_lo12_i_rela,
-	[R_RISCV_PCREL_LO12_S]		= apply_r_riscv_pcrel_lo12_s_rela,
-	[R_RISCV_HI20]			= apply_r_riscv_hi20_rela,
-	[R_RISCV_LO12_I]		= apply_r_riscv_lo12_i_rela,
-	[R_RISCV_LO12_S]		= apply_r_riscv_lo12_s_rela,
-	[R_RISCV_GOT_HI20]		= apply_r_riscv_got_hi20_rela,
-	[R_RISCV_CALL_PLT]		= apply_r_riscv_call_plt_rela,
-	[R_RISCV_CALL]			= apply_r_riscv_call_rela,
-	[R_RISCV_RELAX]			= apply_r_riscv_relax_rela,
-	[R_RISCV_ALIGN]			= apply_r_riscv_align_rela,
-	[R_RISCV_ADD16]			= apply_r_riscv_add16_rela,
-	[R_RISCV_ADD32]			= apply_r_riscv_add32_rela,
-	[R_RISCV_ADD64]			= apply_r_riscv_add64_rela,
-	[R_RISCV_SUB16]			= apply_r_riscv_sub16_rela,
-	[R_RISCV_SUB32]			= apply_r_riscv_sub32_rela,
-	[R_RISCV_SUB64]			= apply_r_riscv_sub64_rela,
+static int dynamic_linking_not_supported(struct module *me, void *location,
+					 Elf_Addr v)
+{
+	pr_err("%s: Dynamic linking not supported in kernel modules PC = %p\n",
+	       me->name, location);
+	return -EINVAL;
+}
+
+static int tls_not_supported(struct module *me, void *location, Elf_Addr v)
+{
+	pr_err("%s: Thread local storage not supported in kernel modules PC = %p\n",
+	       me->name, location);
+	return -EINVAL;
+}
+
+static int apply_r_riscv_sub6_rela(struct module *me, void *location, Elf_Addr v)
+{
+	u8 *byte = location;
+	u8 value = v;
+
+	*byte = (*byte - (value & 0x3f)) & 0x3f;
+	return 0;
+}
+
+static int apply_r_riscv_set6_rela(struct module *me, void *location, Elf_Addr v)
+{
+	u8 *byte = location;
+	u8 value = v;
+
+	*byte = (*byte & 0xc0) | (value & 0x3f);
+	return 0;
+}
+
+static int apply_r_riscv_set8_rela(struct module *me, void *location, Elf_Addr v)
+{
+	*(u8 *)location = (u8)v;
+	return 0;
+}
+
+static int apply_r_riscv_set16_rela(struct module *me, void *location,
+				    Elf_Addr v)
+{
+	*(u16 *)location = (u16)v;
+	return 0;
+}
+
+static int apply_r_riscv_set32_rela(struct module *me, void *location,
+				    Elf_Addr v)
+{
+	*(u32 *)location = (u32)v;
+	return 0;
+}
+
+static int apply_r_riscv_32_pcrel_rela(struct module *me, void *location,
+				       Elf_Addr v)
+{
+	*(u32 *)location = v - (uintptr_t)location;
+	return 0;
+}
+
+static int apply_r_riscv_plt32_rela(struct module *me, void *location,
+				    Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - location;
+
+	if (!riscv_insn_valid_32bit_offset(offset)) {
+		/* Only emit the plt entry if offset over 32-bit range */
+		if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) {
+			offset = (void *)module_emit_plt_entry(me, v) - location;
+		} else {
+			pr_err("%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+			       me->name, (long long)v, location);
+			return -EINVAL;
+		}
+	}
+
+	*(u32 *)location = (u32)offset;
+	return 0;
+}
+
+static int apply_r_riscv_set_uleb128(struct module *me, void *location, Elf_Addr v)
+{
+	*(long *)location = v;
+	return 0;
+}
+
+static int apply_r_riscv_sub_uleb128(struct module *me, void *location, Elf_Addr v)
+{
+	*(long *)location -= v;
+	return 0;
+}
+
+static int apply_6_bit_accumulation(struct module *me, void *location, long buffer)
+{
+	u8 *byte = location;
+	u8 value = buffer;
+
+	if (buffer > 0x3f) {
+		pr_err("%s: value %ld out of range for 6-bit relocation.\n",
+		       me->name, buffer);
+		return -EINVAL;
+	}
+
+	*byte = (*byte & 0xc0) | (value & 0x3f);
+	return 0;
+}
+
+static int apply_8_bit_accumulation(struct module *me, void *location, long buffer)
+{
+	if (buffer > U8_MAX) {
+		pr_err("%s: value %ld out of range for 8-bit relocation.\n",
+		       me->name, buffer);
+		return -EINVAL;
+	}
+	*(u8 *)location = (u8)buffer;
+	return 0;
+}
+
+static int apply_16_bit_accumulation(struct module *me, void *location, long buffer)
+{
+	if (buffer > U16_MAX) {
+		pr_err("%s: value %ld out of range for 16-bit relocation.\n",
+		       me->name, buffer);
+		return -EINVAL;
+	}
+	*(u16 *)location = (u16)buffer;
+	return 0;
+}
+
+static int apply_32_bit_accumulation(struct module *me, void *location, long buffer)
+{
+	if (buffer > U32_MAX) {
+		pr_err("%s: value %ld out of range for 32-bit relocation.\n",
+		       me->name, buffer);
+		return -EINVAL;
+	}
+	*(u32 *)location = (u32)buffer;
+	return 0;
+}
+
+static int apply_64_bit_accumulation(struct module *me, void *location, long buffer)
+{
+	*(u64 *)location = (u64)buffer;
+	return 0;
+}
+
+static int apply_uleb128_accumulation(struct module *me, void *location, long buffer)
+{
+	/*
+	 * ULEB128 is a variable length encoding. Encode the buffer into
+	 * the ULEB128 data format.
+	 */
+	u8 *p = location;
+
+	while (buffer != 0) {
+		u8 value = buffer & 0x7f;
+
+		buffer >>= 7;
+		value |= (!!buffer) << 7;
+
+		*p++ = value;
+	}
+	return 0;
+}
+
+/*
+ * Relocations defined in the riscv-elf-psabi-doc.
+ * This handles static linking only.
+ */
+static const struct relocation_handlers reloc_handlers[] = {
+	[R_RISCV_32]		= { .reloc_handler = apply_r_riscv_32_rela },
+	[R_RISCV_64]		= { .reloc_handler = apply_r_riscv_64_rela },
+	[R_RISCV_RELATIVE]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_COPY]		= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_JUMP_SLOT]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_TLS_DTPMOD32]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_TLS_DTPMOD64]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_TLS_DTPREL32]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_TLS_DTPREL64]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_TLS_TPREL32]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_TLS_TPREL64]	= { .reloc_handler = dynamic_linking_not_supported },
+	/* 12-15 undefined */
+	[R_RISCV_BRANCH]	= { .reloc_handler = apply_r_riscv_branch_rela },
+	[R_RISCV_JAL]		= { .reloc_handler = apply_r_riscv_jal_rela },
+	[R_RISCV_CALL]		= { .reloc_handler = apply_r_riscv_call_rela },
+	[R_RISCV_CALL_PLT]	= { .reloc_handler = apply_r_riscv_call_plt_rela },
+	[R_RISCV_GOT_HI20]	= { .reloc_handler = apply_r_riscv_got_hi20_rela },
+	[R_RISCV_TLS_GOT_HI20]	= { .reloc_handler = tls_not_supported },
+	[R_RISCV_TLS_GD_HI20]	= { .reloc_handler = tls_not_supported },
+	[R_RISCV_PCREL_HI20]	= { .reloc_handler = apply_r_riscv_pcrel_hi20_rela },
+	[R_RISCV_PCREL_LO12_I]	= { .reloc_handler = apply_r_riscv_pcrel_lo12_i_rela },
+	[R_RISCV_PCREL_LO12_S]	= { .reloc_handler = apply_r_riscv_pcrel_lo12_s_rela },
+	[R_RISCV_HI20]		= { .reloc_handler = apply_r_riscv_hi20_rela },
+	[R_RISCV_LO12_I]	= { .reloc_handler = apply_r_riscv_lo12_i_rela },
+	[R_RISCV_LO12_S]	= { .reloc_handler = apply_r_riscv_lo12_s_rela },
+	[R_RISCV_TPREL_HI20]	= { .reloc_handler = tls_not_supported },
+	[R_RISCV_TPREL_LO12_I]	= { .reloc_handler = tls_not_supported },
+	[R_RISCV_TPREL_LO12_S]	= { .reloc_handler = tls_not_supported },
+	[R_RISCV_TPREL_ADD]	= { .reloc_handler = tls_not_supported },
+	[R_RISCV_ADD8]		= { .reloc_handler = apply_r_riscv_add8_rela,
+				    .accumulate_handler = apply_8_bit_accumulation },
+	[R_RISCV_ADD16]		= { .reloc_handler = apply_r_riscv_add16_rela,
+				    .accumulate_handler = apply_16_bit_accumulation },
+	[R_RISCV_ADD32]		= { .reloc_handler = apply_r_riscv_add32_rela,
+				    .accumulate_handler = apply_32_bit_accumulation },
+	[R_RISCV_ADD64]		= { .reloc_handler = apply_r_riscv_add64_rela,
+				    .accumulate_handler = apply_64_bit_accumulation },
+	[R_RISCV_SUB8]		= { .reloc_handler = apply_r_riscv_sub8_rela,
+				    .accumulate_handler = apply_8_bit_accumulation },
+	[R_RISCV_SUB16]		= { .reloc_handler = apply_r_riscv_sub16_rela,
+				    .accumulate_handler = apply_16_bit_accumulation },
+	[R_RISCV_SUB32]		= { .reloc_handler = apply_r_riscv_sub32_rela,
+				    .accumulate_handler = apply_32_bit_accumulation },
+	[R_RISCV_SUB64]		= { .reloc_handler = apply_r_riscv_sub64_rela,
+				    .accumulate_handler = apply_64_bit_accumulation },
+	/* 41-42 reserved for future standard use */
+	[R_RISCV_ALIGN]		= { .reloc_handler = apply_r_riscv_align_rela },
+	[R_RISCV_RVC_BRANCH]	= { .reloc_handler = apply_r_riscv_rvc_branch_rela },
+	[R_RISCV_RVC_JUMP]	= { .reloc_handler = apply_r_riscv_rvc_jump_rela },
+	/* 46-50 reserved for future standard use */
+	[R_RISCV_RELAX]		= { .reloc_handler = apply_r_riscv_relax_rela },
+	[R_RISCV_SUB6]		= { .reloc_handler = apply_r_riscv_sub6_rela,
+				    .accumulate_handler = apply_6_bit_accumulation },
+	[R_RISCV_SET6]		= { .reloc_handler = apply_r_riscv_set6_rela,
+				    .accumulate_handler = apply_6_bit_accumulation },
+	[R_RISCV_SET8]		= { .reloc_handler = apply_r_riscv_set8_rela,
+				    .accumulate_handler = apply_8_bit_accumulation },
+	[R_RISCV_SET16]		= { .reloc_handler = apply_r_riscv_set16_rela,
+				    .accumulate_handler = apply_16_bit_accumulation },
+	[R_RISCV_SET32]		= { .reloc_handler = apply_r_riscv_set32_rela,
+				    .accumulate_handler = apply_32_bit_accumulation },
+	[R_RISCV_32_PCREL]	= { .reloc_handler = apply_r_riscv_32_pcrel_rela },
+	[R_RISCV_IRELATIVE]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_PLT32]		= { .reloc_handler = apply_r_riscv_plt32_rela },
+	[R_RISCV_SET_ULEB128]	= { .reloc_handler = apply_r_riscv_set_uleb128,
+				    .accumulate_handler = apply_uleb128_accumulation },
+	[R_RISCV_SUB_ULEB128]	= { .reloc_handler = apply_r_riscv_sub_uleb128,
+				    .accumulate_handler = apply_uleb128_accumulation },
+	/* 62-191 reserved for future standard use */
+	/* 192-255 nonstandard ABI extensions  */
 };
 
+void process_accumulated_relocations(struct module *me)
+{
+	/*
+	 * Only ADD/SUB/SET/ULEB128 should end up here.
+	 *
+	 * Each bucket may have more than one relocation location. All
+	 * relocations for a location are stored in a list in a bucket.
+	 *
+	 * Relocations are applied to a temp variable before being stored to the
+	 * provided location to check for overflow. This also allows ULEB128 to
+	 * properly decide how many entries are needed before storing to
+	 * location. The final value is stored into location using the handler
+	 * for the last relocation to an address.
+	 *
+	 * Three layers of indexing:
+	 *	- Each of the buckets in use
+	 *	- Groups of relocations in each bucket by location address
+	 *	- Each relocation entry for a location address
+	 */
+	struct used_bucket *bucket_iter;
+	struct relocation_head *rel_head_iter;
+	struct relocation_entry *rel_entry_iter;
+	int curr_type;
+	void *location;
+	long buffer;
+
+	list_for_each_entry(bucket_iter, &used_buckets_list, head) {
+		hlist_for_each_entry(rel_head_iter, bucket_iter->bucket, node) {
+			buffer = 0;
+			location = rel_head_iter->location;
+			list_for_each_entry(rel_entry_iter,
+					    rel_head_iter->rel_entry, head) {
+				curr_type = rel_entry_iter->type;
+				reloc_handlers[curr_type].reloc_handler(
+					me, &buffer, rel_entry_iter->value);
+				kfree(rel_entry_iter);
+			}
+			reloc_handlers[curr_type].accumulate_handler(
+				me, location, buffer);
+			kfree(rel_head_iter);
+		}
+		kfree(bucket_iter);
+	}
+
+	kfree(relocation_hashtable);
+}
+
+int add_relocation_to_accumulate(struct module *me, int type, void *location,
+				 unsigned int hashtable_bits, Elf_Addr v)
+{
+	struct relocation_entry *entry;
+	struct relocation_head *rel_head;
+	struct hlist_head *current_head;
+	struct used_bucket *bucket;
+	unsigned long hash;
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	INIT_LIST_HEAD(&entry->head);
+	entry->type = type;
+	entry->value = v;
+
+	hash = hash_min((uintptr_t)location, hashtable_bits);
+
+	current_head = &relocation_hashtable[hash];
+
+	/* Find matching location (if any) */
+	bool found = false;
+	struct relocation_head *rel_head_iter;
+
+	hlist_for_each_entry(rel_head_iter, current_head, node) {
+		if (rel_head_iter->location == location) {
+			found = true;
+			rel_head = rel_head_iter;
+			break;
+		}
+	}
+
+	if (!found) {
+		rel_head = kmalloc(sizeof(*rel_head), GFP_KERNEL);
+		rel_head->rel_entry =
+			kmalloc(sizeof(struct list_head), GFP_KERNEL);
+		INIT_LIST_HEAD(rel_head->rel_entry);
+		rel_head->location = location;
+		INIT_HLIST_NODE(&rel_head->node);
+		if (!current_head->first) {
+			bucket =
+				kmalloc(sizeof(struct used_bucket), GFP_KERNEL);
+			INIT_LIST_HEAD(&bucket->head);
+			bucket->bucket = current_head;
+			list_add(&bucket->head, &used_buckets_list);
+		}
+		hlist_add_head(&rel_head->node, current_head);
+	}
+
+	/* Add relocation to head of discovered rel_head */
+	list_add_tail(&entry->head, rel_head->rel_entry);
+
+	return 0;
+}
+
+unsigned int 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);
+	unsigned int hashtable_bits = ilog2(hashtable_size);
+
+	/*
+	 * Double size of hashtable if num_relocations * 1.25 is greater than
+	 * hashtable_size.
+	 */
+	int should_double_size = ((num_relocations + (num_relocations >> 2)) > (hashtable_size));
+
+	hashtable_bits += should_double_size;
+
+	hashtable_size <<= should_double_size;
+
+	relocation_hashtable = kmalloc_array(hashtable_size,
+					     sizeof(*relocation_hashtable),
+					     GFP_KERNEL);
+	__hash_init(relocation_hashtable, hashtable_size);
+
+	INIT_LIST_HEAD(&used_buckets_list);
+
+	return hashtable_bits;
+}
+
 int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 		       unsigned int symindex, unsigned int relsec,
 		       struct module *me)
 {
 	Elf_Rela *rel = (void *) sechdrs[relsec].sh_addr;
-	int (*handler)(struct module *me, u32 *location, Elf_Addr v);
+	int (*handler)(struct module *me, void *location, Elf_Addr v);
 	Elf_Sym *sym;
-	u32 *location;
+	void *location;
 	unsigned int i, type;
 	Elf_Addr v;
 	int res;
+	unsigned int num_relocations = sechdrs[relsec].sh_size / sizeof(*rel);
+	unsigned int hashtable_bits = initialize_relocation_hashtable(num_relocations);
 
 	pr_debug("Applying relocate section %u to %u\n", relsec,
 	       sechdrs[relsec].sh_info);
 
-	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
+	for (i = 0; i < num_relocations; i++) {
 		/* This is where to make the change */
 		location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
 			+ rel[i].r_offset;
@@ -370,8 +765,8 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 
 		type = ELF_RISCV_R_TYPE(rel[i].r_info);
 
-		if (type < ARRAY_SIZE(reloc_handlers_rela))
-			handler = reloc_handlers_rela[type];
+		if (type < ARRAY_SIZE(reloc_handlers))
+			handler = reloc_handlers[type].reloc_handler;
 		else
 			handler = NULL;
 
@@ -427,11 +822,16 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 			}
 		}
 
-		res = handler(me, location, v);
+		if (reloc_handlers[type].accumulate_handler)
+			res = add_relocation_to_accumulate(me, type, location, hashtable_bits, v);
+		else
+			res = handler(me, location, v);
 		if (res)
 			return res;
 	}
 
+	process_accumulated_relocations(me);
+
 	return 0;
 }
 
diff --git a/arch/riscv/kernel/probes/rethook_trampoline.S b/arch/riscv/kernel/probes/rethook_trampoline.S
index 21bac92a170a..f2cd83d9b0f0 100644
--- a/arch/riscv/kernel/probes/rethook_trampoline.S
+++ b/arch/riscv/kernel/probes/rethook_trampoline.S
@@ -75,7 +75,7 @@
 	REG_L x31, PT_T6(sp)
 	.endm
 
-ENTRY(arch_rethook_trampoline)
+SYM_CODE_START(arch_rethook_trampoline)
 	addi sp, sp, -(PT_SIZE_ON_STACK)
 	save_all_base_regs
 
@@ -90,4 +90,4 @@ ENTRY(arch_rethook_trampoline)
 	addi sp, sp, PT_SIZE_ON_STACK
 
 	ret
-ENDPROC(arch_rethook_trampoline)
+SYM_CODE_END(arch_rethook_trampoline)
diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c
index d3099d67816d..6c166029079c 100644
--- a/arch/riscv/kernel/probes/simulate-insn.c
+++ b/arch/riscv/kernel/probes/simulate-insn.c
@@ -24,7 +24,7 @@ static inline bool rv_insn_reg_set_val(struct pt_regs *regs, u32 index,
 				       unsigned long val)
 {
 	if (index == 0)
-		return false;
+		return true;
 	else if (index <= 31)
 		*((unsigned long *)regs + index) = val;
 	else
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
index 194f166b2cc4..4b3dc8beaf77 100644
--- a/arch/riscv/kernel/probes/uprobes.c
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -3,6 +3,7 @@
 #include <linux/highmem.h>
 #include <linux/ptrace.h>
 #include <linux/uprobes.h>
+#include <asm/insn.h>
 
 #include "decode-insn.h"
 
@@ -17,6 +18,11 @@ bool is_swbp_insn(uprobe_opcode_t *insn)
 #endif
 }
 
+bool is_trap_insn(uprobe_opcode_t *insn)
+{
+	return riscv_insn_is_ebreak(*insn) || riscv_insn_is_c_ebreak(*insn);
+}
+
 unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
 {
 	return instruction_pointer(regs);
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index e32d737e039f..4f21d970a129 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -25,6 +25,7 @@
 #include <asm/thread_info.h>
 #include <asm/cpuidle.h>
 #include <asm/vector.h>
+#include <asm/cpufeature.h>
 
 register unsigned long gp_in_global __asm__("gp");
 
@@ -41,6 +42,23 @@ void arch_cpu_idle(void)
 	cpu_do_idle();
 }
 
+int set_unalign_ctl(struct task_struct *tsk, unsigned int val)
+{
+	if (!unaligned_ctl_available())
+		return -EINVAL;
+
+	tsk->thread.align_ctl = val;
+	return 0;
+}
+
+int get_unalign_ctl(struct task_struct *tsk, unsigned long adr)
+{
+	if (!unaligned_ctl_available())
+		return -EINVAL;
+
+	return put_user(tsk->thread.align_ctl, (unsigned long __user *)adr);
+}
+
 void __show_regs(struct pt_regs *regs)
 {
 	show_regs_print_info(KERN_DEFAULT);
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index c672c8ba9a2a..5a62ed1da453 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -11,6 +11,7 @@
 #include <linux/reboot.h>
 #include <asm/sbi.h>
 #include <asm/smp.h>
+#include <asm/tlbflush.h>
 
 /* default SBI version is 0.1 */
 unsigned long sbi_spec_version __ro_after_init = SBI_SPEC_VERSION_DEFAULT;
@@ -377,31 +378,14 @@ int sbi_remote_fence_i(const struct cpumask *cpu_mask)
 EXPORT_SYMBOL(sbi_remote_fence_i);
 
 /**
- * sbi_remote_sfence_vma() - Execute SFENCE.VMA instructions on given remote
- *			     harts for the specified virtual address range.
- * @cpu_mask: A cpu mask containing all the target harts.
- * @start: Start of the virtual address
- * @size: Total size of the virtual address range.
- *
- * Return: 0 on success, appropriate linux error code otherwise.
- */
-int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
-			   unsigned long start,
-			   unsigned long size)
-{
-	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
-			    cpu_mask, start, size, 0, 0);
-}
-EXPORT_SYMBOL(sbi_remote_sfence_vma);
-
-/**
  * sbi_remote_sfence_vma_asid() - Execute SFENCE.VMA instructions on given
- * remote harts for a virtual address range belonging to a specific ASID.
+ * remote harts for a virtual address range belonging to a specific ASID or not.
  *
  * @cpu_mask: A cpu mask containing all the target harts.
  * @start: Start of the virtual address
  * @size: Total size of the virtual address range.
- * @asid: The value of address space identifier (ASID).
+ * @asid: The value of address space identifier (ASID), or FLUSH_TLB_NO_ASID
+ * for flushing all address spaces.
  *
  * Return: 0 on success, appropriate linux error code otherwise.
  */
@@ -410,8 +394,12 @@ int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
 				unsigned long size,
 				unsigned long asid)
 {
-	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
-			    cpu_mask, start, size, asid, 0);
+	if (asid == FLUSH_TLB_NO_ASID)
+		return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
+				    cpu_mask, start, size, 0, 0);
+	else
+		return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
+				    cpu_mask, start, size, asid, 0);
 }
 EXPORT_SYMBOL(sbi_remote_sfence_vma_asid);
 
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 21a4d0e111bc..88b6220b2608 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -384,30 +384,6 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	sigset_t *oldset = sigmask_to_save();
 	int ret;
 
-	/* Are we from a system call? */
-	if (regs->cause == EXC_SYSCALL) {
-		/* Avoid additional syscall restarting via ret_from_exception */
-		regs->cause = -1UL;
-		/* If so, check system call restarting.. */
-		switch (regs->a0) {
-		case -ERESTART_RESTARTBLOCK:
-		case -ERESTARTNOHAND:
-			regs->a0 = -EINTR;
-			break;
-
-		case -ERESTARTSYS:
-			if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
-				regs->a0 = -EINTR;
-				break;
-			}
-			fallthrough;
-		case -ERESTARTNOINTR:
-                        regs->a0 = regs->orig_a0;
-			regs->epc -= 0x4;
-			break;
-		}
-	}
-
 	rseq_signal_deliver(ksig, regs);
 
 	/* Set up the stack frame */
@@ -421,36 +397,67 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 
 void arch_do_signal_or_restart(struct pt_regs *regs)
 {
+	unsigned long continue_addr = 0, restart_addr = 0;
+	int retval = 0;
 	struct ksignal ksig;
+	bool syscall = (regs->cause == EXC_SYSCALL);
 
-	if (get_signal(&ksig)) {
-		/* Actually deliver the signal */
-		handle_signal(&ksig, regs);
-		return;
-	}
+	/* If we were from a system call, check for system call restarting */
+	if (syscall) {
+		continue_addr = regs->epc;
+		restart_addr = continue_addr - 4;
+		retval = regs->a0;
 
-	/* Did we come from a system call? */
-	if (regs->cause == EXC_SYSCALL) {
 		/* Avoid additional syscall restarting via ret_from_exception */
 		regs->cause = -1UL;
 
-		/* Restart the system call - no handlers present */
-		switch (regs->a0) {
+		/*
+		 * Prepare for system call restart. We do this here so that a
+		 * debugger will see the already changed PC.
+		 */
+		switch (retval) {
 		case -ERESTARTNOHAND:
 		case -ERESTARTSYS:
 		case -ERESTARTNOINTR:
-                        regs->a0 = regs->orig_a0;
-			regs->epc -= 0x4;
-			break;
 		case -ERESTART_RESTARTBLOCK:
-                        regs->a0 = regs->orig_a0;
-			regs->a7 = __NR_restart_syscall;
-			regs->epc -= 0x4;
+			regs->a0 = regs->orig_a0;
+			regs->epc = restart_addr;
 			break;
 		}
 	}
 
 	/*
+	 * Get the signal to deliver. When running under ptrace, at this point
+	 * the debugger may change all of our registers.
+	 */
+	if (get_signal(&ksig)) {
+		/*
+		 * Depending on the signal settings, we may need to revert the
+		 * decision to restart the system call, but skip this if a
+		 * debugger has chosen to restart at a different PC.
+		 */
+		if (regs->epc == restart_addr &&
+		    (retval == -ERESTARTNOHAND ||
+		     retval == -ERESTART_RESTARTBLOCK ||
+		     (retval == -ERESTARTSYS &&
+		      !(ksig.ka.sa.sa_flags & SA_RESTART)))) {
+			regs->a0 = -EINTR;
+			regs->epc = continue_addr;
+		}
+
+		/* Actually deliver the signal */
+		handle_signal(&ksig, regs);
+		return;
+	}
+
+	/*
+	 * Handle restarting a different system call. As above, if a debugger
+	 * has chosen to restart at a different PC, ignore the restart.
+	 */
+	if (syscall && regs->epc == restart_addr && retval == -ERESTART_RESTARTBLOCK)
+		regs->a7 = __NR_restart_syscall;
+
+	/*
 	 * If there is no signal to deliver, we just put the saved
 	 * sigmask back.
 	 */
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index d1b0a6fc3adf..d162bf339beb 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -248,7 +248,6 @@ asmlinkage __visible void smp_callin(void)
 
 	numa_add_cpu(curr_cpuid);
 	set_cpu_online(curr_cpuid, 1);
-	check_unaligned_access(curr_cpuid);
 
 	if (has_vector()) {
 		if (riscv_v_setup_vsize())
diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S
index d5cf8b575777..2d54f309c140 100644
--- a/arch/riscv/kernel/suspend_entry.S
+++ b/arch/riscv/kernel/suspend_entry.S
@@ -16,7 +16,7 @@
 	.altmacro
 	.option norelax
 
-ENTRY(__cpu_suspend_enter)
+SYM_FUNC_START(__cpu_suspend_enter)
 	/* Save registers (except A0 and T0-T6) */
 	REG_S	ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0)
 	REG_S	sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0)
@@ -57,7 +57,7 @@ ENTRY(__cpu_suspend_enter)
 
 	/* Return to C code */
 	ret
-END(__cpu_suspend_enter)
+SYM_FUNC_END(__cpu_suspend_enter)
 
 SYM_TYPED_FUNC_START(__cpu_resume_enter)
 	/* Load the global pointer */
diff --git a/arch/riscv/kernel/tests/Kconfig.debug b/arch/riscv/kernel/tests/Kconfig.debug
new file mode 100644
index 000000000000..5dba64e8e977
--- /dev/null
+++ b/arch/riscv/kernel/tests/Kconfig.debug
@@ -0,0 +1,35 @@
+# SPDX-License-Identifier: GPL-2.0-only
+menu "arch/riscv/kernel Testing and Coverage"
+
+config AS_HAS_ULEB128
+	def_bool $(as-instr,.reloc label$(comma) R_RISCV_SET_ULEB128$(comma) 127\n.reloc label$(comma) R_RISCV_SUB_ULEB128$(comma) 127\nlabel:\n.word 0)
+
+menuconfig RUNTIME_KERNEL_TESTING_MENU
+       bool "arch/riscv/kernel runtime Testing"
+       def_bool y
+       help
+         Enable riscv kernel runtime testing.
+
+if RUNTIME_KERNEL_TESTING_MENU
+
+config RISCV_MODULE_LINKING_KUNIT
+       bool "KUnit test riscv module linking at runtime" if !KUNIT_ALL_TESTS
+       depends on KUNIT
+       default KUNIT_ALL_TESTS
+       help
+         Enable this option to test riscv module linking at boot. This will
+	 enable a module called "test_module_linking".
+
+         KUnit tests run during boot and output the results to the debug log
+         in TAP format (http://testanything.org/). Only useful for kernel devs
+         running the KUnit test harness, and not intended for inclusion into a
+         production build.
+
+         For more information on KUnit and unit tests in general please refer
+         to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+         If unsure, say N.
+
+endif # RUNTIME_TESTING_MENU
+
+endmenu # "arch/riscv/kernel runtime Testing"
diff --git a/arch/riscv/kernel/tests/Makefile b/arch/riscv/kernel/tests/Makefile
new file mode 100644
index 000000000000..7d6c76cffe20
--- /dev/null
+++ b/arch/riscv/kernel/tests/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_RISCV_MODULE_LINKING_KUNIT)	+= module_test/
diff --git a/arch/riscv/kernel/tests/module_test/Makefile b/arch/riscv/kernel/tests/module_test/Makefile
new file mode 100644
index 000000000000..d7a6fd8943de
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/Makefile
@@ -0,0 +1,15 @@
+obj-m += test_module_linking.o
+
+test_sub := test_sub6.o test_sub8.o test_sub16.o test_sub32.o test_sub64.o
+
+test_set := test_set6.o test_set8.o test_set16.o test_set32.o
+
+test_module_linking-objs += $(test_sub)
+
+test_module_linking-objs += $(test_set)
+
+ifeq ($(CONFIG_AS_HAS_ULEB128),y)
+test_module_linking-objs += test_uleb128.o
+endif
+
+test_module_linking-objs += test_module_linking_main.o
diff --git a/arch/riscv/kernel/tests/module_test/test_module_linking_main.c b/arch/riscv/kernel/tests/module_test/test_module_linking_main.c
new file mode 100644
index 000000000000..8df5fa5b834e
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_module_linking_main.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <kunit/test.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Test module linking");
+
+extern int test_set32(void);
+extern int test_set16(void);
+extern int test_set8(void);
+extern int test_set6(void);
+extern long test_sub64(void);
+extern int test_sub32(void);
+extern int test_sub16(void);
+extern int test_sub8(void);
+extern int test_sub6(void);
+
+#ifdef CONFIG_AS_HAS_ULEB128
+extern int test_uleb_basic(void);
+extern int test_uleb_large(void);
+#endif
+
+#define CHECK_EQ(lhs, rhs) KUNIT_ASSERT_EQ(test, lhs, rhs)
+
+void run_test_set(struct kunit *test);
+void run_test_sub(struct kunit *test);
+void run_test_uleb(struct kunit *test);
+
+void run_test_set(struct kunit *test)
+{
+	int val32 = test_set32();
+	int val16 = test_set16();
+	int val8 = test_set8();
+	int val6 = test_set6();
+
+	CHECK_EQ(val32, 0);
+	CHECK_EQ(val16, 0);
+	CHECK_EQ(val8, 0);
+	CHECK_EQ(val6, 0);
+}
+
+void run_test_sub(struct kunit *test)
+{
+	int val64 = test_sub64();
+	int val32 = test_sub32();
+	int val16 = test_sub16();
+	int val8 = test_sub8();
+	int val6 = test_sub6();
+
+	CHECK_EQ(val64, 0);
+	CHECK_EQ(val32, 0);
+	CHECK_EQ(val16, 0);
+	CHECK_EQ(val8, 0);
+	CHECK_EQ(val6, 0);
+}
+
+#ifdef CONFIG_AS_HAS_ULEB128
+void run_test_uleb(struct kunit *test)
+{
+	int val_uleb = test_uleb_basic();
+	int val_uleb2 = test_uleb_large();
+
+	CHECK_EQ(val_uleb, 0);
+	CHECK_EQ(val_uleb2, 0);
+}
+#endif
+
+static struct kunit_case __refdata riscv_module_linking_test_cases[] = {
+	KUNIT_CASE(run_test_set),
+	KUNIT_CASE(run_test_sub),
+#ifdef CONFIG_AS_HAS_ULEB128
+	KUNIT_CASE(run_test_uleb),
+#endif
+	{}
+};
+
+static struct kunit_suite riscv_module_linking_test_suite = {
+	.name = "riscv_checksum",
+	.test_cases = riscv_module_linking_test_cases,
+};
+
+kunit_test_suites(&riscv_module_linking_test_suite);
diff --git a/arch/riscv/kernel/tests/module_test/test_set16.S b/arch/riscv/kernel/tests/module_test/test_set16.S
new file mode 100644
index 000000000000..2be0e441a12e
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_set16.S
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_set16
+test_set16:
+	lw	a0, set16
+	la	t0, set16
+#ifdef CONFIG_32BIT
+	slli	t0, t0, 16
+	srli	t0, t0, 16
+#else
+	slli	t0, t0, 48
+	srli	t0, t0, 48
+#endif
+	sub	a0, a0, t0
+	ret
+.data
+set16:
+	.reloc set16, R_RISCV_SET16, set16
+	.word 0
diff --git a/arch/riscv/kernel/tests/module_test/test_set32.S b/arch/riscv/kernel/tests/module_test/test_set32.S
new file mode 100644
index 000000000000..de0444537e67
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_set32.S
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_set32
+test_set32:
+	lw	a0, set32
+	la	t0, set32
+#ifndef CONFIG_32BIT
+	slli	t0, t0, 32
+	srli	t0, t0, 32
+#endif
+	sub	a0, a0, t0
+	ret
+.data
+set32:
+	.reloc set32, R_RISCV_SET32, set32
+	.word 0
diff --git a/arch/riscv/kernel/tests/module_test/test_set6.S b/arch/riscv/kernel/tests/module_test/test_set6.S
new file mode 100644
index 000000000000..c39ce4c219eb
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_set6.S
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_set6
+test_set6:
+	lw	a0, set6
+	la	t0, set6
+#ifdef CONFIG_32BIT
+	slli	t0, t0, 26
+	srli	t0, t0, 26
+#else
+	slli	t0, t0, 58
+	srli	t0, t0, 58
+#endif
+	sub	a0, a0, t0
+	ret
+.data
+set6:
+	.reloc set6, R_RISCV_SET6, set6
+	.word 0
diff --git a/arch/riscv/kernel/tests/module_test/test_set8.S b/arch/riscv/kernel/tests/module_test/test_set8.S
new file mode 100644
index 000000000000..a656173f6f99
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_set8.S
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_set8
+test_set8:
+	lw	a0, set8
+	la	t0, set8
+#ifdef CONFIG_32BIT
+	slli	t0, t0, 24
+	srli	t0, t0, 24
+#else
+	slli	t0, t0, 56
+	srli	t0, t0, 56
+#endif
+	sub	a0, a0, t0
+	ret
+.data
+set8:
+	.reloc set8, R_RISCV_SET8, set8
+	.word 0
diff --git a/arch/riscv/kernel/tests/module_test/test_sub16.S b/arch/riscv/kernel/tests/module_test/test_sub16.S
new file mode 100644
index 000000000000..80f731d599ba
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_sub16.S
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_sub16
+test_sub16:
+	lh	a0, sub16
+	addi	a0, a0, -32
+	ret
+first:
+	.space 32
+second:
+
+.data
+sub16:
+	.reloc		sub16, R_RISCV_ADD16, second
+	.reloc		sub16, R_RISCV_SUB16, first
+	.half		0
diff --git a/arch/riscv/kernel/tests/module_test/test_sub32.S b/arch/riscv/kernel/tests/module_test/test_sub32.S
new file mode 100644
index 000000000000..a341686e12df
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_sub32.S
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_sub32
+test_sub32:
+	lw	a0, sub32
+	addi	a0, a0, -32
+	ret
+first:
+	.space 32
+second:
+
+.data
+sub32:
+	.reloc		sub32, R_RISCV_ADD32, second
+	.reloc		sub32, R_RISCV_SUB32, first
+	.word		0
diff --git a/arch/riscv/kernel/tests/module_test/test_sub6.S b/arch/riscv/kernel/tests/module_test/test_sub6.S
new file mode 100644
index 000000000000..e8b61c1ec527
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_sub6.S
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_sub6
+test_sub6:
+	lb	a0, sub6
+	addi	a0, a0, -32
+	ret
+first:
+	.space 32
+second:
+
+.data
+sub6:
+	.reloc		sub6, R_RISCV_SET6, second
+	.reloc		sub6, R_RISCV_SUB6, first
+	.byte		0
diff --git a/arch/riscv/kernel/tests/module_test/test_sub64.S b/arch/riscv/kernel/tests/module_test/test_sub64.S
new file mode 100644
index 000000000000..a59e8afa88fd
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_sub64.S
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_sub64
+test_sub64:
+#ifdef CONFIG_32BIT
+	lw	a0, sub64
+#else
+	ld	a0, sub64
+#endif
+	addi	a0, a0, -32
+	ret
+first:
+	.space 32
+second:
+
+.data
+sub64:
+	.reloc		sub64, R_RISCV_ADD64, second
+	.reloc		sub64, R_RISCV_SUB64, first
+	.word		0
+	.word		0
diff --git a/arch/riscv/kernel/tests/module_test/test_sub8.S b/arch/riscv/kernel/tests/module_test/test_sub8.S
new file mode 100644
index 000000000000..ac5d0ec98de3
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_sub8.S
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_sub8
+test_sub8:
+	lb	a0, sub8
+	addi	a0, a0, -32
+	ret
+first:
+	.space 32
+second:
+
+.data
+sub8:
+	.reloc		sub8, R_RISCV_ADD8, second
+	.reloc		sub8, R_RISCV_SUB8, first
+	.byte		0
diff --git a/arch/riscv/kernel/tests/module_test/test_uleb128.S b/arch/riscv/kernel/tests/module_test/test_uleb128.S
new file mode 100644
index 000000000000..90f22049d553
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_uleb128.S
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_uleb_basic
+test_uleb_basic:
+	ld	a0, second
+	addi	a0, a0, -127
+	ret
+
+.global test_uleb_large
+test_uleb_large:
+	ld	a0, fourth
+	addi	a0, a0, -0x07e8
+	ret
+
+.data
+first:
+	.space 127
+second:
+	.reloc second, R_RISCV_SET_ULEB128, second
+	.reloc second, R_RISCV_SUB_ULEB128, first
+	.dword 0
+third:
+	.space 1000
+fourth:
+	.reloc fourth, R_RISCV_SET_ULEB128, fourth
+	.reloc fourth, R_RISCV_SUB_ULEB128, third
+	.dword 0
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index c9d698518bae..a1b9be3c4332 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -36,7 +36,21 @@ int show_unhandled_signals = 1;
 
 static DEFINE_SPINLOCK(die_lock);
 
-static void dump_kernel_instr(const char *loglvl, struct pt_regs *regs)
+static int copy_code(struct pt_regs *regs, u16 *val, const u16 *insns)
+{
+	const void __user *uaddr = (__force const void __user *)insns;
+
+	if (!user_mode(regs))
+		return get_kernel_nofault(*val, insns);
+
+	/* The user space code from other tasks cannot be accessed. */
+	if (regs != task_pt_regs(current))
+		return -EPERM;
+
+	return copy_from_user_nofault(val, uaddr, sizeof(*val));
+}
+
+static void dump_instr(const char *loglvl, struct pt_regs *regs)
 {
 	char str[sizeof("0000 ") * 12 + 2 + 1], *p = str;
 	const u16 *insns = (u16 *)instruction_pointer(regs);
@@ -45,7 +59,7 @@ static void dump_kernel_instr(const char *loglvl, struct pt_regs *regs)
 	int i;
 
 	for (i = -10; i < 2; i++) {
-		bad = get_kernel_nofault(val, &insns[i]);
+		bad = copy_code(regs, &val, &insns[i]);
 		if (!bad) {
 			p += sprintf(p, i == 0 ? "(%04hx) " : "%04hx ", val);
 		} else {
@@ -74,7 +88,7 @@ void die(struct pt_regs *regs, const char *str)
 	print_modules();
 	if (regs) {
 		show_regs(regs);
-		dump_kernel_instr(KERN_EMERG, regs);
+		dump_instr(KERN_EMERG, regs);
 	}
 
 	cause = regs ? regs->cause : -1;
@@ -107,6 +121,7 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr)
 		print_vma_addr(KERN_CONT " in ", instruction_pointer(regs));
 		pr_cont("\n");
 		__show_regs(regs);
+		dump_instr(KERN_EMERG, regs);
 	}
 
 	force_sig_fault(signo, code, (void __user *)addr);
@@ -181,14 +196,6 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re
 
 DO_ERROR_INFO(do_trap_load_fault,
 	SIGSEGV, SEGV_ACCERR, "load access fault");
-#ifndef CONFIG_RISCV_M_MODE
-DO_ERROR_INFO(do_trap_load_misaligned,
-	SIGBUS, BUS_ADRALN, "Oops - load address misaligned");
-DO_ERROR_INFO(do_trap_store_misaligned,
-	SIGBUS, BUS_ADRALN, "Oops - store (or AMO) address misaligned");
-#else
-int handle_misaligned_load(struct pt_regs *regs);
-int handle_misaligned_store(struct pt_regs *regs);
 
 asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs)
 {
@@ -231,7 +238,6 @@ asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs
 		irqentry_nmi_exit(regs, state);
 	}
 }
-#endif
 DO_ERROR_INFO(do_trap_store_fault,
 	SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
 DO_ERROR_INFO(do_trap_ecall_s,
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 378f5b151443..5eba37147caa 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -6,12 +6,16 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/perf_event.h>
 #include <linux/irq.h>
 #include <linux/stringify.h>
 
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/csr.h>
+#include <asm/entry-common.h>
+#include <asm/hwprobe.h>
+#include <asm/cpufeature.h>
 
 #define INSN_MATCH_LB			0x3
 #define INSN_MASK_LB			0x707f
@@ -151,53 +155,134 @@
 #define PRECISION_S 0
 #define PRECISION_D 1
 
-#define DECLARE_UNPRIVILEGED_LOAD_FUNCTION(type, insn)			\
-static inline type load_##type(const type *addr)			\
-{									\
-	type val;							\
-	asm (#insn " %0, %1"						\
-	: "=&r" (val) : "m" (*addr));					\
-	return val;							\
+#ifdef CONFIG_FPU
+
+#define FP_GET_RD(insn)		(insn >> 7 & 0x1F)
+
+extern void put_f32_reg(unsigned long fp_reg, unsigned long value);
+
+static int set_f32_rd(unsigned long insn, struct pt_regs *regs,
+		      unsigned long val)
+{
+	unsigned long fp_reg = FP_GET_RD(insn);
+
+	put_f32_reg(fp_reg, val);
+	regs->status |= SR_FS_DIRTY;
+
+	return 0;
 }
 
-#define DECLARE_UNPRIVILEGED_STORE_FUNCTION(type, insn)			\
-static inline void store_##type(type *addr, type val)			\
-{									\
-	asm volatile (#insn " %0, %1\n"					\
-	: : "r" (val), "m" (*addr));					\
+extern void put_f64_reg(unsigned long fp_reg, unsigned long value);
+
+static int set_f64_rd(unsigned long insn, struct pt_regs *regs, u64 val)
+{
+	unsigned long fp_reg = FP_GET_RD(insn);
+	unsigned long value;
+
+#if __riscv_xlen == 32
+	value = (unsigned long) &val;
+#else
+	value = val;
+#endif
+	put_f64_reg(fp_reg, value);
+	regs->status |= SR_FS_DIRTY;
+
+	return 0;
 }
 
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u8, lbu)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u16, lhu)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s8, lb)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s16, lh)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s32, lw)
-DECLARE_UNPRIVILEGED_STORE_FUNCTION(u8, sb)
-DECLARE_UNPRIVILEGED_STORE_FUNCTION(u16, sh)
-DECLARE_UNPRIVILEGED_STORE_FUNCTION(u32, sw)
-#if defined(CONFIG_64BIT)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lwu)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u64, ld)
-DECLARE_UNPRIVILEGED_STORE_FUNCTION(u64, sd)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, ld)
+#if __riscv_xlen == 32
+extern void get_f64_reg(unsigned long fp_reg, u64 *value);
+
+static u64 get_f64_rs(unsigned long insn, u8 fp_reg_offset,
+		      struct pt_regs *regs)
+{
+	unsigned long fp_reg = (insn >> fp_reg_offset) & 0x1F;
+	u64 val;
+
+	get_f64_reg(fp_reg, &val);
+	regs->status |= SR_FS_DIRTY;
+
+	return val;
+}
 #else
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lw)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, lw)
 
-static inline u64 load_u64(const u64 *addr)
+extern unsigned long get_f64_reg(unsigned long fp_reg);
+
+static unsigned long get_f64_rs(unsigned long insn, u8 fp_reg_offset,
+				struct pt_regs *regs)
 {
-	return load_u32((u32 *)addr)
-		+ ((u64)load_u32((u32 *)addr + 1) << 32);
+	unsigned long fp_reg = (insn >> fp_reg_offset) & 0x1F;
+	unsigned long val;
+
+	val = get_f64_reg(fp_reg);
+	regs->status |= SR_FS_DIRTY;
+
+	return val;
 }
 
-static inline void store_u64(u64 *addr, u64 val)
+#endif
+
+extern unsigned long get_f32_reg(unsigned long fp_reg);
+
+static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset,
+				struct pt_regs *regs)
 {
-	store_u32((u32 *)addr, val);
-	store_u32((u32 *)addr + 1, val >> 32);
+	unsigned long fp_reg = (insn >> fp_reg_offset) & 0x1F;
+	unsigned long val;
+
+	val = get_f32_reg(fp_reg);
+	regs->status |= SR_FS_DIRTY;
+
+	return val;
 }
+
+#else /* CONFIG_FPU */
+static void set_f32_rd(unsigned long insn, struct pt_regs *regs,
+		       unsigned long val) {}
+
+static void set_f64_rd(unsigned long insn, struct pt_regs *regs, u64 val) {}
+
+static unsigned long get_f64_rs(unsigned long insn, u8 fp_reg_offset,
+				struct pt_regs *regs)
+{
+	return 0;
+}
+
+static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset,
+				struct pt_regs *regs)
+{
+	return 0;
+}
+
 #endif
 
-static inline ulong get_insn(ulong mepc)
+#define GET_F64_RS2(insn, regs) (get_f64_rs(insn, 20, regs))
+#define GET_F64_RS2C(insn, regs) (get_f64_rs(insn, 2, regs))
+#define GET_F64_RS2S(insn, regs) (get_f64_rs(RVC_RS2S(insn), 0, regs))
+
+#define GET_F32_RS2(insn, regs) (get_f32_rs(insn, 20, regs))
+#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;
@@ -226,23 +311,119 @@ static inline ulong get_insn(ulong mepc)
 	: [addr] "r" (__mepc), [rvc_mask] "r" (rvc_mask),
 	  [xlen_minus_16] "i" (XLEN_MINUS_16));
 
-	return val;
+	*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, 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, addr);
+	} else {
+		*addr = val;
+		return 0;
+	}
 }
 
+#define __read_insn(regs, insn, insn_addr)		\
+({							\
+	int __ret;					\
+							\
+	if (user_mode(regs)) {				\
+		__ret = __get_user(insn, insn_addr);	\
+	} else {					\
+		insn = *insn_addr;			\
+		__ret = 0;				\
+	}						\
+							\
+	__ret;						\
+})
+
+static inline int get_insn(struct pt_regs *regs, ulong epc, ulong *r_insn)
+{
+	ulong insn = 0;
+
+	if (epc & 0x2) {
+		ulong tmp = 0;
+		u16 __user *insn_addr = (u16 __user *)epc;
+
+		if (__read_insn(regs, insn, insn_addr))
+			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
+		 * below with the upper 16 bits half.
+		 */
+		insn &= GENMASK(15, 0);
+		if ((insn & __INSN_LENGTH_MASK) != __INSN_LENGTH_32) {
+			*r_insn = insn;
+			return 0;
+		}
+		insn_addr++;
+		if (__read_insn(regs, tmp, insn_addr))
+			return -EFAULT;
+		*r_insn = (tmp << 16) | insn;
+
+		return 0;
+	} else {
+		u32 __user *insn_addr = (u32 __user *)epc;
+
+		if (__read_insn(regs, insn, insn_addr))
+			return -EFAULT;
+		if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) {
+			*r_insn = insn;
+			return 0;
+		}
+		insn &= GENMASK(15, 0);
+		*r_insn = insn;
+
+		return 0;
+	}
+}
+#endif
+
 union reg_data {
 	u8 data_bytes[8];
 	ulong data_ulong;
 	u64 data_u64;
 };
 
+static bool unaligned_ctl __read_mostly;
+
+/* sysctl hooks */
+int unaligned_enabled __read_mostly = 1;	/* Enabled by default */
+
 int handle_misaligned_load(struct pt_regs *regs)
 {
 	union reg_data val;
 	unsigned long epc = regs->epc;
-	unsigned long insn = get_insn(epc);
-	unsigned long addr = csr_read(mtval);
+	unsigned long insn;
+	unsigned long addr = regs->badaddr;
 	int i, fp = 0, shift = 0, len = 0;
 
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
+
+	*this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_EMULATED;
+
+	if (!unaligned_enabled)
+		return -1;
+
+	if (user_mode(regs) && (current->thread.align_ctl & PR_UNALIGN_SIGBUS))
+		return -1;
+
+	if (get_insn(regs, epc, &insn))
+		return -1;
+
 	regs->epc = 0;
 
 	if ((insn & INSN_MASK_LW) == INSN_MATCH_LW) {
@@ -305,13 +486,21 @@ int handle_misaligned_load(struct pt_regs *regs)
 		return -1;
 	}
 
+	if (!IS_ENABLED(CONFIG_FPU) && fp)
+		return -EOPNOTSUPP;
+
 	val.data_u64 = 0;
-	for (i = 0; i < len; i++)
-		val.data_bytes[i] = load_u8((void *)(addr + i));
+	for (i = 0; i < len; i++) {
+		if (load_u8(regs, (void *)(addr + i), &val.data_bytes[i]))
+			return -1;
+	}
 
-	if (fp)
-		return -1;
-	SET_RD(insn, regs, val.data_ulong << shift >> shift);
+	if (!fp)
+		SET_RD(insn, regs, val.data_ulong << shift >> shift);
+	else if (len == 8)
+		set_f64_rd(insn, regs, val.data_u64);
+	else
+		set_f32_rd(insn, regs, val.data_ulong);
 
 	regs->epc = epc + INSN_LEN(insn);
 
@@ -322,9 +511,20 @@ int handle_misaligned_store(struct pt_regs *regs)
 {
 	union reg_data val;
 	unsigned long epc = regs->epc;
-	unsigned long insn = get_insn(epc);
-	unsigned long addr = csr_read(mtval);
-	int i, len = 0;
+	unsigned long insn;
+	unsigned long addr = regs->badaddr;
+	int i, len = 0, fp = 0;
+
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
+
+	if (!unaligned_enabled)
+		return -1;
+
+	if (user_mode(regs) && (current->thread.align_ctl & PR_UNALIGN_SIGBUS))
+		return -1;
+
+	if (get_insn(regs, epc, &insn))
+		return -1;
 
 	regs->epc = 0;
 
@@ -336,6 +536,14 @@ int handle_misaligned_store(struct pt_regs *regs)
 	} else if ((insn & INSN_MASK_SD) == INSN_MATCH_SD) {
 		len = 8;
 #endif
+	} else if ((insn & INSN_MASK_FSD) == INSN_MATCH_FSD) {
+		fp = 1;
+		len = 8;
+		val.data_u64 = GET_F64_RS2(insn, regs);
+	} else if ((insn & INSN_MASK_FSW) == INSN_MATCH_FSW) {
+		fp = 1;
+		len = 4;
+		val.data_ulong = GET_F32_RS2(insn, regs);
 	} else if ((insn & INSN_MASK_SH) == INSN_MATCH_SH) {
 		len = 2;
 #if defined(CONFIG_64BIT)
@@ -354,15 +562,88 @@ int handle_misaligned_store(struct pt_regs *regs)
 		   ((insn >> SH_RD) & 0x1f)) {
 		len = 4;
 		val.data_ulong = GET_RS2C(insn, regs);
+	} else if ((insn & INSN_MASK_C_FSD) == INSN_MATCH_C_FSD) {
+		fp = 1;
+		len = 8;
+		val.data_u64 = GET_F64_RS2S(insn, regs);
+	} else if ((insn & INSN_MASK_C_FSDSP) == INSN_MATCH_C_FSDSP) {
+		fp = 1;
+		len = 8;
+		val.data_u64 = GET_F64_RS2C(insn, regs);
+#if !defined(CONFIG_64BIT)
+	} else if ((insn & INSN_MASK_C_FSW) == INSN_MATCH_C_FSW) {
+		fp = 1;
+		len = 4;
+		val.data_ulong = GET_F32_RS2S(insn, regs);
+	} else if ((insn & INSN_MASK_C_FSWSP) == INSN_MATCH_C_FSWSP) {
+		fp = 1;
+		len = 4;
+		val.data_ulong = GET_F32_RS2C(insn, regs);
+#endif
 	} else {
 		regs->epc = epc;
 		return -1;
 	}
 
-	for (i = 0; i < len; i++)
-		store_u8((void *)(addr + i), val.data_bytes[i]);
+	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]))
+			return -1;
+	}
 
 	regs->epc = epc + INSN_LEN(insn);
 
 	return 0;
 }
+
+bool check_unaligned_access_emulated(int cpu)
+{
+	long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu);
+	unsigned long tmp_var, tmp_val;
+	bool misaligned_emu_detected;
+
+	*mas_ptr = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+
+	__asm__ __volatile__ (
+		"       "REG_L" %[tmp], 1(%[ptr])\n"
+		: [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory");
+
+	misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_EMULATED);
+	/*
+	 * If unaligned_ctl is already set, this means that we detected that all
+	 * CPUS uses emulated misaligned access at boot time. If that changed
+	 * when hotplugging the new cpu, this is something we don't handle.
+	 */
+	if (unlikely(unaligned_ctl && !misaligned_emu_detected)) {
+		pr_crit("CPU misaligned accesses non homogeneous (expected all emulated)\n");
+		while (true)
+			cpu_relax();
+	}
+
+	return misaligned_emu_detected;
+}
+
+void unaligned_emulation_finish(void)
+{
+	int cpu;
+
+	/*
+	 * We can only support PR_UNALIGN controls if all CPUs have misaligned
+	 * accesses emulated since tasks requesting such control can run on any
+	 * CPU.
+	 */
+	for_each_present_cpu(cpu) {
+		if (per_cpu(misaligned_access_speed, cpu) !=
+					RISCV_HWPROBE_MISALIGNED_EMULATED) {
+			return;
+		}
+	}
+	unaligned_ctl = true;
+}
+
+bool unaligned_ctl_available(void)
+{
+	return unaligned_ctl;
+}
diff --git a/arch/riscv/kernel/vdso/flush_icache.S b/arch/riscv/kernel/vdso/flush_icache.S
index 82f97d67c23e..8f884227e8bc 100644
--- a/arch/riscv/kernel/vdso/flush_icache.S
+++ b/arch/riscv/kernel/vdso/flush_icache.S
@@ -8,7 +8,7 @@
 
 	.text
 /* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */
-ENTRY(__vdso_flush_icache)
+SYM_FUNC_START(__vdso_flush_icache)
 	.cfi_startproc
 #ifdef CONFIG_SMP
 	li a7, __NR_riscv_flush_icache
@@ -19,4 +19,4 @@ ENTRY(__vdso_flush_icache)
 #endif
 	ret
 	.cfi_endproc
-ENDPROC(__vdso_flush_icache)
+SYM_FUNC_END(__vdso_flush_icache)
diff --git a/arch/riscv/kernel/vdso/getcpu.S b/arch/riscv/kernel/vdso/getcpu.S
index bb0c05e2ffba..9c1bd531907f 100644
--- a/arch/riscv/kernel/vdso/getcpu.S
+++ b/arch/riscv/kernel/vdso/getcpu.S
@@ -8,11 +8,11 @@
 
 	.text
 /* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */
-ENTRY(__vdso_getcpu)
+SYM_FUNC_START(__vdso_getcpu)
 	.cfi_startproc
 	/* For now, just do the syscall. */
 	li a7, __NR_getcpu
 	ecall
 	ret
 	.cfi_endproc
-ENDPROC(__vdso_getcpu)
+SYM_FUNC_END(__vdso_getcpu)
diff --git a/arch/riscv/kernel/vdso/rt_sigreturn.S b/arch/riscv/kernel/vdso/rt_sigreturn.S
index 10438c7c626a..3dc022aa8931 100644
--- a/arch/riscv/kernel/vdso/rt_sigreturn.S
+++ b/arch/riscv/kernel/vdso/rt_sigreturn.S
@@ -7,10 +7,10 @@
 #include <asm/unistd.h>
 
 	.text
-ENTRY(__vdso_rt_sigreturn)
+SYM_FUNC_START(__vdso_rt_sigreturn)
 	.cfi_startproc
 	.cfi_signal_frame
 	li a7, __NR_rt_sigreturn
 	ecall
 	.cfi_endproc
-ENDPROC(__vdso_rt_sigreturn)
+SYM_FUNC_END(__vdso_rt_sigreturn)
diff --git a/arch/riscv/kernel/vdso/sys_hwprobe.S b/arch/riscv/kernel/vdso/sys_hwprobe.S
index 4e704146c77a..77e57f830521 100644
--- a/arch/riscv/kernel/vdso/sys_hwprobe.S
+++ b/arch/riscv/kernel/vdso/sys_hwprobe.S
@@ -5,11 +5,11 @@
 #include <asm/unistd.h>
 
 .text
-ENTRY(riscv_hwprobe)
+SYM_FUNC_START(riscv_hwprobe)
 	.cfi_startproc
 	li a7, __NR_riscv_hwprobe
 	ecall
 	ret
 
 	.cfi_endproc
-ENDPROC(riscv_hwprobe)
+SYM_FUNC_END(riscv_hwprobe)
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index 82ce64900f3d..cbe2a179331d 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -23,35 +23,31 @@ SECTIONS
 	.gnu.version_d	: { *(.gnu.version_d) }
 	.gnu.version_r	: { *(.gnu.version_r) }
 
-	.note		: { *(.note.*) }		:text	:note
 	.dynamic	: { *(.dynamic) }		:text	:dynamic
 
+	.rodata		: {
+		*(.rodata .rodata.* .gnu.linkonce.r.*)
+		*(.got.plt) *(.got)
+		*(.data .data.* .gnu.linkonce.d.*)
+		*(.dynbss)
+		*(.bss .bss.* .gnu.linkonce.b.*)
+	}
+
+	.note		: { *(.note.*) }		:text	:note
+
 	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
 	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
 
-	.rodata		: { *(.rodata .rodata.* .gnu.linkonce.r.*) }
-
 	/*
-	 * This linker script is used both with -r and with -shared.
-	 * For the layouts to match, we need to skip more than enough
-	 * space for the dynamic symbol table, etc. If this amount is
-	 * insufficient, ld -shared will error; simply increase it here.
+	 * Text is well-separated from actual data: there's plenty of
+	 * stuff that isn't used at runtime in between.
 	 */
-	. = 0x800;
+	. = ALIGN(16);
 	.text		: { *(.text .text.*) }		:text
 
 	. = ALIGN(4);
 	.alternative : {
-		__alt_start = .;
 		*(.alternative)
-		__alt_end = .;
-	}
-
-	.data		: {
-		*(.got.plt) *(.got)
-		*(.data .data.* .gnu.linkonce.d.*)
-		*(.dynbss)
-		*(.bss .bss.* .gnu.linkonce.b.*)
 	}
 }
 
diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c
index 74bb27440527..a944294f6f23 100644
--- a/arch/riscv/kvm/aia.c
+++ b/arch/riscv/kvm/aia.c
@@ -14,7 +14,7 @@
 #include <linux/kvm_host.h>
 #include <linux/percpu.h>
 #include <linux/spinlock.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/kvm_aia_imsic.h>
 
 struct aia_hgei_control {
diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c
index 48ae0d4b3932..225a435d9c9a 100644
--- a/arch/riscv/kvm/main.c
+++ b/arch/riscv/kvm/main.c
@@ -11,7 +11,7 @@
 #include <linux/module.h>
 #include <linux/kvm_host.h>
 #include <asm/csr.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/sbi.h>
 
 long kvm_arch_dev_ioctl(struct file *filp,
diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c
index 44bc324aeeb0..23c0e82b5103 100644
--- a/arch/riscv/kvm/tlb.c
+++ b/arch/riscv/kvm/tlb.c
@@ -12,7 +12,7 @@
 #include <linux/kvm_host.h>
 #include <asm/cacheflush.h>
 #include <asm/csr.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/insn-def.h>
 
 #define has_svinval()	riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL)
diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c
index 08ba48a395aa..030904d82b58 100644
--- a/arch/riscv/kvm/vcpu_fp.c
+++ b/arch/riscv/kvm/vcpu_fp.c
@@ -11,7 +11,7 @@
 #include <linux/err.h>
 #include <linux/kvm_host.h>
 #include <linux/uaccess.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 
 #ifdef CONFIG_FPU
 void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu)
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index c6ebce6126b5..f8c9fa0c03c5 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -13,7 +13,7 @@
 #include <linux/uaccess.h>
 #include <linux/kvm_host.h>
 #include <asm/cacheflush.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/kvm_vcpu_vector.h>
 #include <asm/vector.h>
 
diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c
index b430cbb69521..b339a2682f25 100644
--- a/arch/riscv/kvm/vcpu_vector.c
+++ b/arch/riscv/kvm/vcpu_vector.c
@@ -11,7 +11,7 @@
 #include <linux/err.h>
 #include <linux/kvm_host.h>
 #include <linux/uaccess.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/kvm_vcpu_vector.h>
 #include <asm/vector.h>
 
diff --git a/arch/riscv/lib/clear_page.S b/arch/riscv/lib/clear_page.S
index d7a256eb53f4..b22de1231144 100644
--- a/arch/riscv/lib/clear_page.S
+++ b/arch/riscv/lib/clear_page.S
@@ -29,41 +29,41 @@ SYM_FUNC_START(clear_page)
 	lw	a1, riscv_cboz_block_size
 	add	a2, a0, a2
 .Lzero_loop:
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
 	CBOZ_ALT(11, "bltu a0, a2, .Lzero_loop; ret", "nop; nop")
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
 	CBOZ_ALT(10, "bltu a0, a2, .Lzero_loop; ret", "nop; nop")
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
 	CBOZ_ALT(9, "bltu a0, a2, .Lzero_loop; ret", "nop; nop")
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
 	CBOZ_ALT(8, "bltu a0, a2, .Lzero_loop; ret", "nop; nop")
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
 	bltu	a0, a2, .Lzero_loop
 	ret
diff --git a/arch/riscv/lib/memcpy.S b/arch/riscv/lib/memcpy.S
index 1a40d01a9543..44e009ec5fef 100644
--- a/arch/riscv/lib/memcpy.S
+++ b/arch/riscv/lib/memcpy.S
@@ -7,8 +7,7 @@
 #include <asm/asm.h>
 
 /* void *memcpy(void *, const void *, size_t) */
-ENTRY(__memcpy)
-WEAK(memcpy)
+SYM_FUNC_START(__memcpy)
 	move t6, a0  /* Preserve return value */
 
 	/* Defer to byte-oriented copy for small sizes */
@@ -105,6 +104,7 @@ WEAK(memcpy)
 	bltu a1, a3, 5b
 6:
 	ret
-END(__memcpy)
+SYM_FUNC_END(__memcpy)
+SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy)
 SYM_FUNC_ALIAS(__pi_memcpy, __memcpy)
 SYM_FUNC_ALIAS(__pi___memcpy, __memcpy)
diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S
index 838ff2022fe3..cb3e2e7ef0ba 100644
--- a/arch/riscv/lib/memmove.S
+++ b/arch/riscv/lib/memmove.S
@@ -7,7 +7,6 @@
 #include <asm/asm.h>
 
 SYM_FUNC_START(__memmove)
-SYM_FUNC_START_WEAK(memmove)
 	/*
 	 * Returns
 	 *   a0 - dest
@@ -26,8 +25,8 @@ SYM_FUNC_START_WEAK(memmove)
 	 */
 
 	/* Return if nothing to do */
-	beq a0, a1, return_from_memmove
-	beqz a2, return_from_memmove
+	beq a0, a1, .Lreturn_from_memmove
+	beqz a2, .Lreturn_from_memmove
 
 	/*
 	 * Register Uses
@@ -60,7 +59,7 @@ SYM_FUNC_START_WEAK(memmove)
 	 * small enough not to bother.
 	 */
 	andi t0, a2, -(2 * SZREG)
-	beqz t0, byte_copy
+	beqz t0, .Lbyte_copy
 
 	/*
 	 * Now solve for t5 and t6.
@@ -87,14 +86,14 @@ SYM_FUNC_START_WEAK(memmove)
 	 */
 	xor  t0, a0, a1
 	andi t1, t0, (SZREG - 1)
-	beqz t1, coaligned_copy
+	beqz t1, .Lcoaligned_copy
 	/* Fall through to misaligned fixup copy */
 
-misaligned_fixup_copy:
-	bltu a1, a0, misaligned_fixup_copy_reverse
+.Lmisaligned_fixup_copy:
+	bltu a1, a0, .Lmisaligned_fixup_copy_reverse
 
-misaligned_fixup_copy_forward:
-	jal  t0, byte_copy_until_aligned_forward
+.Lmisaligned_fixup_copy_forward:
+	jal  t0, .Lbyte_copy_until_aligned_forward
 
 	andi a5, a1, (SZREG - 1) /* Find the alignment offset of src (a1) */
 	slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */
@@ -153,10 +152,10 @@ misaligned_fixup_copy_forward:
 	mv    t3, t6 /* Fix the dest pointer in case the loop was broken */
 
 	add  a1, t3, a5 /* Restore the src pointer */
-	j byte_copy_forward /* Copy any remaining bytes */
+	j .Lbyte_copy_forward /* Copy any remaining bytes */
 
-misaligned_fixup_copy_reverse:
-	jal  t0, byte_copy_until_aligned_reverse
+.Lmisaligned_fixup_copy_reverse:
+	jal  t0, .Lbyte_copy_until_aligned_reverse
 
 	andi a5, a4, (SZREG - 1) /* Find the alignment offset of src (a4) */
 	slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */
@@ -215,18 +214,18 @@ misaligned_fixup_copy_reverse:
 	mv    t4, t5 /* Fix the dest pointer in case the loop was broken */
 
 	add  a4, t4, a5 /* Restore the src pointer */
-	j byte_copy_reverse /* Copy any remaining bytes */
+	j .Lbyte_copy_reverse /* Copy any remaining bytes */
 
 /*
  * Simple copy loops for SZREG co-aligned memory locations.
  * These also make calls to do byte copies for any unaligned
  * data at their terminations.
  */
-coaligned_copy:
-	bltu a1, a0, coaligned_copy_reverse
+.Lcoaligned_copy:
+	bltu a1, a0, .Lcoaligned_copy_reverse
 
-coaligned_copy_forward:
-	jal t0, byte_copy_until_aligned_forward
+.Lcoaligned_copy_forward:
+	jal t0, .Lbyte_copy_until_aligned_forward
 
 	1:
 	REG_L t1, ( 0 * SZREG)(a1)
@@ -235,10 +234,10 @@ coaligned_copy_forward:
 	REG_S t1, (-1 * SZREG)(t3)
 	bne   t3, t6, 1b
 
-	j byte_copy_forward /* Copy any remaining bytes */
+	j .Lbyte_copy_forward /* Copy any remaining bytes */
 
-coaligned_copy_reverse:
-	jal t0, byte_copy_until_aligned_reverse
+.Lcoaligned_copy_reverse:
+	jal t0, .Lbyte_copy_until_aligned_reverse
 
 	1:
 	REG_L t1, (-1 * SZREG)(a4)
@@ -247,7 +246,7 @@ coaligned_copy_reverse:
 	REG_S t1, ( 0 * SZREG)(t4)
 	bne   t4, t5, 1b
 
-	j byte_copy_reverse /* Copy any remaining bytes */
+	j .Lbyte_copy_reverse /* Copy any remaining bytes */
 
 /*
  * These are basically sub-functions within the function.  They
@@ -258,7 +257,7 @@ coaligned_copy_reverse:
  * up from where they were left and we avoid code duplication
  * without any overhead except the call in and return jumps.
  */
-byte_copy_until_aligned_forward:
+.Lbyte_copy_until_aligned_forward:
 	beq  t3, t5, 2f
 	1:
 	lb   t1,  0(a1)
@@ -269,7 +268,7 @@ byte_copy_until_aligned_forward:
 	2:
 	jalr zero, 0x0(t0) /* Return to multibyte copy loop */
 
-byte_copy_until_aligned_reverse:
+.Lbyte_copy_until_aligned_reverse:
 	beq  t4, t6, 2f
 	1:
 	lb   t1, -1(a4)
@@ -285,10 +284,10 @@ byte_copy_until_aligned_reverse:
  * These will byte copy until they reach the end of data to copy.
  * At that point, they will call to return from memmove.
  */
-byte_copy:
-	bltu a1, a0, byte_copy_reverse
+.Lbyte_copy:
+	bltu a1, a0, .Lbyte_copy_reverse
 
-byte_copy_forward:
+.Lbyte_copy_forward:
 	beq  t3, t4, 2f
 	1:
 	lb   t1,  0(a1)
@@ -299,7 +298,7 @@ byte_copy_forward:
 	2:
 	ret
 
-byte_copy_reverse:
+.Lbyte_copy_reverse:
 	beq  t4, t3, 2f
 	1:
 	lb   t1, -1(a4)
@@ -309,10 +308,10 @@ byte_copy_reverse:
 	bne  t4, t3, 1b
 	2:
 
-return_from_memmove:
+.Lreturn_from_memmove:
 	ret
 
-SYM_FUNC_END(memmove)
 SYM_FUNC_END(__memmove)
+SYM_FUNC_ALIAS_WEAK(memmove, __memmove)
 SYM_FUNC_ALIAS(__pi_memmove, __memmove)
 SYM_FUNC_ALIAS(__pi___memmove, __memmove)
diff --git a/arch/riscv/lib/memset.S b/arch/riscv/lib/memset.S
index 34c5360c6705..35f358e70bdb 100644
--- a/arch/riscv/lib/memset.S
+++ b/arch/riscv/lib/memset.S
@@ -8,8 +8,7 @@
 #include <asm/asm.h>
 
 /* void *memset(void *, int, size_t) */
-ENTRY(__memset)
-WEAK(memset)
+SYM_FUNC_START(__memset)
 	move t0, a0  /* Preserve return value */
 
 	/* Defer to byte-oriented fill for small sizes */
@@ -110,4 +109,5 @@ WEAK(memset)
 	bltu t0, a3, 5b
 6:
 	ret
-END(__memset)
+SYM_FUNC_END(__memset)
+SYM_FUNC_ALIAS_WEAK(memset, __memset)
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index 09b47ebacf2e..3ab438f30d13 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -10,8 +10,7 @@
 	_asm_extable	100b, \lbl
 	.endm
 
-ENTRY(__asm_copy_to_user)
-ENTRY(__asm_copy_from_user)
+SYM_FUNC_START(__asm_copy_to_user)
 
 	/* Enable access to user memory */
 	li t6, SR_SUM
@@ -181,13 +180,13 @@ ENTRY(__asm_copy_from_user)
 	csrc CSR_STATUS, t6
 	sub a0, t5, a0
 	ret
-ENDPROC(__asm_copy_to_user)
-ENDPROC(__asm_copy_from_user)
+SYM_FUNC_END(__asm_copy_to_user)
 EXPORT_SYMBOL(__asm_copy_to_user)
+SYM_FUNC_ALIAS(__asm_copy_from_user, __asm_copy_to_user)
 EXPORT_SYMBOL(__asm_copy_from_user)
 
 
-ENTRY(__clear_user)
+SYM_FUNC_START(__clear_user)
 
 	/* Enable access to user memory */
 	li t6, SR_SUM
@@ -233,5 +232,5 @@ ENTRY(__clear_user)
 	csrc CSR_STATUS, t6
 	sub a0, a3, a0
 	ret
-ENDPROC(__clear_user)
+SYM_FUNC_END(__clear_user)
 EXPORT_SYMBOL(__clear_user)
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index 9c454f90fd3d..3a4dfc8babcf 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -36,3 +36,4 @@ endif
 
 obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
 obj-$(CONFIG_RISCV_DMA_NONCOHERENT) += dma-noncoherent.o
+obj-$(CONFIG_RISCV_NONSTANDARD_CACHE_OPS) += cache-ops.o
diff --git a/arch/riscv/mm/cache-ops.c b/arch/riscv/mm/cache-ops.c
new file mode 100644
index 000000000000..a993ad11d0ec
--- /dev/null
+++ b/arch/riscv/mm/cache-ops.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <asm/dma-noncoherent.h>
+
+struct riscv_nonstd_cache_ops noncoherent_cache_ops __ro_after_init;
+
+void
+riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops)
+{
+	if (!ops)
+		return;
+	noncoherent_cache_ops = *ops;
+}
+EXPORT_SYMBOL_GPL(riscv_noncoherent_register_cache_ops);
diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index b76e7e192eb1..4e4e469b8dd6 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -15,12 +15,6 @@ static bool noncoherent_supported __ro_after_init;
 int dma_cache_alignment __ro_after_init = ARCH_DMA_MINALIGN;
 EXPORT_SYMBOL_GPL(dma_cache_alignment);
 
-struct riscv_nonstd_cache_ops noncoherent_cache_ops __ro_after_init = {
-	.wback = NULL,
-	.inv = NULL,
-	.wback_inv = NULL,
-};
-
 static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size)
 {
 	void *vaddr = phys_to_virt(paddr);
@@ -31,7 +25,7 @@ static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size)
 		return;
 	}
 #endif
-	ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+	ALT_CMO_OP(CLEAN, vaddr, size, riscv_cbom_block_size);
 }
 
 static inline void arch_dma_cache_inv(phys_addr_t paddr, size_t size)
@@ -45,7 +39,7 @@ static inline void arch_dma_cache_inv(phys_addr_t paddr, size_t size)
 	}
 #endif
 
-	ALT_CMO_OP(inval, vaddr, size, riscv_cbom_block_size);
+	ALT_CMO_OP(INVAL, vaddr, size, riscv_cbom_block_size);
 }
 
 static inline void arch_dma_cache_wback_inv(phys_addr_t paddr, size_t size)
@@ -59,7 +53,7 @@ static inline void arch_dma_cache_wback_inv(phys_addr_t paddr, size_t size)
 	}
 #endif
 
-	ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
+	ALT_CMO_OP(FLUSH, vaddr, size, riscv_cbom_block_size);
 }
 
 static inline bool arch_sync_dma_clean_before_fromdevice(void)
@@ -131,7 +125,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 	}
 #endif
 
-	ALT_CMO_OP(flush, flush_addr, size, riscv_cbom_block_size);
+	ALT_CMO_OP(FLUSH, flush_addr, size, riscv_cbom_block_size);
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
@@ -162,12 +156,3 @@ void __init riscv_set_dma_cache_alignment(void)
 	if (!noncoherent_supported)
 		dma_cache_alignment = 1;
 }
-
-void riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops)
-{
-	if (!ops)
-		return;
-
-	noncoherent_cache_ops = *ops;
-}
-EXPORT_SYMBOL_GPL(riscv_noncoherent_register_cache_ops);
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index b128ed3c5a37..2e011cbddf3a 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -666,16 +666,16 @@ void __init create_pgd_mapping(pgd_t *pgdp,
 static uintptr_t __init best_map_size(phys_addr_t pa, uintptr_t va,
 				      phys_addr_t size)
 {
-	if (!(pa & (PGDIR_SIZE - 1)) && !(va & (PGDIR_SIZE - 1)) && size >= PGDIR_SIZE)
-		return PGDIR_SIZE;
-
-	if (!(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE)
+	if (pgtable_l5_enabled &&
+	    !(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE)
 		return P4D_SIZE;
 
-	if (!(pa & (PUD_SIZE - 1)) && !(va & (PUD_SIZE - 1)) && size >= PUD_SIZE)
+	if (pgtable_l4_enabled &&
+	    !(pa & (PUD_SIZE - 1)) && !(va & (PUD_SIZE - 1)) && size >= PUD_SIZE)
 		return PUD_SIZE;
 
-	if (!(pa & (PMD_SIZE - 1)) && !(va & (PMD_SIZE - 1)) && size >= PMD_SIZE)
+	if (IS_ENABLED(CONFIG_64BIT) &&
+	    !(pa & (PMD_SIZE - 1)) && !(va & (PMD_SIZE - 1)) && size >= PMD_SIZE)
 		return PMD_SIZE;
 
 	return PAGE_SIZE;
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index 161d0b34c2cb..fc5fc4f785c4 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -5,6 +5,7 @@
 
 #include <linux/pagewalk.h>
 #include <linux/pgtable.h>
+#include <linux/vmalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/bitops.h>
 #include <asm/set_memory.h>
@@ -25,19 +26,6 @@ static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk)
 	return new_val;
 }
 
-static int pageattr_pgd_entry(pgd_t *pgd, unsigned long addr,
-			      unsigned long next, struct mm_walk *walk)
-{
-	pgd_t val = READ_ONCE(*pgd);
-
-	if (pgd_leaf(val)) {
-		val = __pgd(set_pageattr_masks(pgd_val(val), walk));
-		set_pgd(pgd, val);
-	}
-
-	return 0;
-}
-
 static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
@@ -96,7 +84,6 @@ static int pageattr_pte_hole(unsigned long addr, unsigned long next,
 }
 
 static const struct mm_walk_ops pageattr_ops = {
-	.pgd_entry = pageattr_pgd_entry,
 	.p4d_entry = pageattr_p4d_entry,
 	.pud_entry = pageattr_pud_entry,
 	.pmd_entry = pageattr_pmd_entry,
@@ -105,12 +92,181 @@ static const struct mm_walk_ops pageattr_ops = {
 	.walk_lock = PGWALK_RDLOCK,
 };
 
+#ifdef CONFIG_64BIT
+static int __split_linear_mapping_pmd(pud_t *pudp,
+				      unsigned long vaddr, unsigned long end)
+{
+	pmd_t *pmdp;
+	unsigned long next;
+
+	pmdp = pmd_offset(pudp, vaddr);
+
+	do {
+		next = pmd_addr_end(vaddr, end);
+
+		if (next - vaddr >= PMD_SIZE &&
+		    vaddr <= (vaddr & PMD_MASK) && end >= next)
+			continue;
+
+		if (pmd_leaf(*pmdp)) {
+			struct page *pte_page;
+			unsigned long pfn = _pmd_pfn(*pmdp);
+			pgprot_t prot = __pgprot(pmd_val(*pmdp) & ~_PAGE_PFN_MASK);
+			pte_t *ptep_new;
+			int i;
+
+			pte_page = alloc_page(GFP_KERNEL);
+			if (!pte_page)
+				return -ENOMEM;
+
+			ptep_new = (pte_t *)page_address(pte_page);
+			for (i = 0; i < PTRS_PER_PTE; ++i, ++ptep_new)
+				set_pte(ptep_new, pfn_pte(pfn + i, prot));
+
+			smp_wmb();
+
+			set_pmd(pmdp, pfn_pmd(page_to_pfn(pte_page), PAGE_TABLE));
+		}
+	} while (pmdp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_pud(p4d_t *p4dp,
+				      unsigned long vaddr, unsigned long end)
+{
+	pud_t *pudp;
+	unsigned long next;
+	int ret;
+
+	pudp = pud_offset(p4dp, vaddr);
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (next - vaddr >= PUD_SIZE &&
+		    vaddr <= (vaddr & PUD_MASK) && end >= next)
+			continue;
+
+		if (pud_leaf(*pudp)) {
+			struct page *pmd_page;
+			unsigned long pfn = _pud_pfn(*pudp);
+			pgprot_t prot = __pgprot(pud_val(*pudp) & ~_PAGE_PFN_MASK);
+			pmd_t *pmdp_new;
+			int i;
+
+			pmd_page = alloc_page(GFP_KERNEL);
+			if (!pmd_page)
+				return -ENOMEM;
+
+			pmdp_new = (pmd_t *)page_address(pmd_page);
+			for (i = 0; i < PTRS_PER_PMD; ++i, ++pmdp_new)
+				set_pmd(pmdp_new,
+					pfn_pmd(pfn + ((i * PMD_SIZE) >> PAGE_SHIFT), prot));
+
+			smp_wmb();
+
+			set_pud(pudp, pfn_pud(page_to_pfn(pmd_page), PAGE_TABLE));
+		}
+
+		ret = __split_linear_mapping_pmd(pudp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (pudp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_p4d(pgd_t *pgdp,
+				      unsigned long vaddr, unsigned long end)
+{
+	p4d_t *p4dp;
+	unsigned long next;
+	int ret;
+
+	p4dp = p4d_offset(pgdp, vaddr);
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+
+		/*
+		 * If [vaddr; end] contains [vaddr & P4D_MASK; next], we don't
+		 * need to split, we'll change the protections on the whole P4D.
+		 */
+		if (next - vaddr >= P4D_SIZE &&
+		    vaddr <= (vaddr & P4D_MASK) && end >= next)
+			continue;
+
+		if (p4d_leaf(*p4dp)) {
+			struct page *pud_page;
+			unsigned long pfn = _p4d_pfn(*p4dp);
+			pgprot_t prot = __pgprot(p4d_val(*p4dp) & ~_PAGE_PFN_MASK);
+			pud_t *pudp_new;
+			int i;
+
+			pud_page = alloc_page(GFP_KERNEL);
+			if (!pud_page)
+				return -ENOMEM;
+
+			/*
+			 * Fill the pud level with leaf puds that have the same
+			 * protections as the leaf p4d.
+			 */
+			pudp_new = (pud_t *)page_address(pud_page);
+			for (i = 0; i < PTRS_PER_PUD; ++i, ++pudp_new)
+				set_pud(pudp_new,
+					pfn_pud(pfn + ((i * PUD_SIZE) >> PAGE_SHIFT), prot));
+
+			/*
+			 * Make sure the pud filling is not reordered with the
+			 * p4d store which could result in seeing a partially
+			 * filled pud level.
+			 */
+			smp_wmb();
+
+			set_p4d(p4dp, pfn_p4d(page_to_pfn(pud_page), PAGE_TABLE));
+		}
+
+		ret = __split_linear_mapping_pud(p4dp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (p4dp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_pgd(pgd_t *pgdp,
+				      unsigned long vaddr,
+				      unsigned long end)
+{
+	unsigned long next;
+	int ret;
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+		/* We never use PGD mappings for the linear mapping */
+		ret = __split_linear_mapping_p4d(pgdp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (pgdp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int split_linear_mapping(unsigned long start, unsigned long end)
+{
+	return __split_linear_mapping_pgd(pgd_offset_k(start), start, end);
+}
+#endif	/* CONFIG_64BIT */
+
 static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 			pgprot_t clear_mask)
 {
 	int ret;
 	unsigned long start = addr;
 	unsigned long end = start + PAGE_SIZE * numpages;
+	unsigned long __maybe_unused lm_start;
+	unsigned long __maybe_unused lm_end;
 	struct pageattr_masks masks = {
 		.set_mask = set_mask,
 		.clear_mask = clear_mask
@@ -120,11 +276,67 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 		return 0;
 
 	mmap_write_lock(&init_mm);
+
+#ifdef CONFIG_64BIT
+	/*
+	 * We are about to change the permissions of a kernel mapping, we must
+	 * apply the same changes to its linear mapping alias, which may imply
+	 * splitting a huge mapping.
+	 */
+
+	if (is_vmalloc_or_module_addr((void *)start)) {
+		struct vm_struct *area = NULL;
+		int i, page_start;
+
+		area = find_vm_area((void *)start);
+		page_start = (start - (unsigned long)area->addr) >> PAGE_SHIFT;
+
+		for (i = page_start; i < page_start + numpages; ++i) {
+			lm_start = (unsigned long)page_address(area->pages[i]);
+			lm_end = lm_start + PAGE_SIZE;
+
+			ret = split_linear_mapping(lm_start, lm_end);
+			if (ret)
+				goto unlock;
+
+			ret = walk_page_range_novma(&init_mm, lm_start, lm_end,
+						    &pageattr_ops, NULL, &masks);
+			if (ret)
+				goto unlock;
+		}
+	} else if (is_kernel_mapping(start) || is_linear_mapping(start)) {
+		lm_start = (unsigned long)lm_alias(start);
+		lm_end = (unsigned long)lm_alias(end);
+
+		ret = split_linear_mapping(lm_start, lm_end);
+		if (ret)
+			goto unlock;
+
+		ret = walk_page_range_novma(&init_mm, lm_start, lm_end,
+					    &pageattr_ops, NULL, &masks);
+		if (ret)
+			goto unlock;
+	}
+
 	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
 				     &masks);
+
+unlock:
+	mmap_write_unlock(&init_mm);
+
+	/*
+	 * We can't use flush_tlb_kernel_range() here as we may have split a
+	 * hugepage that is larger than that, so let's flush everything.
+	 */
+	flush_tlb_all();
+#else
+	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
+				     &masks);
+
 	mmap_write_unlock(&init_mm);
 
 	flush_tlb_kernel_range(start, end);
+#endif
 
 	return ret;
 }
@@ -159,36 +371,14 @@ int set_memory_nx(unsigned long addr, int numpages)
 
 int set_direct_map_invalid_noflush(struct page *page)
 {
-	int ret;
-	unsigned long start = (unsigned long)page_address(page);
-	unsigned long end = start + PAGE_SIZE;
-	struct pageattr_masks masks = {
-		.set_mask = __pgprot(0),
-		.clear_mask = __pgprot(_PAGE_PRESENT)
-	};
-
-	mmap_read_lock(&init_mm);
-	ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
-	mmap_read_unlock(&init_mm);
-
-	return ret;
+	return __set_memory((unsigned long)page_address(page), 1,
+			    __pgprot(0), __pgprot(_PAGE_PRESENT));
 }
 
 int set_direct_map_default_noflush(struct page *page)
 {
-	int ret;
-	unsigned long start = (unsigned long)page_address(page);
-	unsigned long end = start + PAGE_SIZE;
-	struct pageattr_masks masks = {
-		.set_mask = PAGE_KERNEL,
-		.clear_mask = __pgprot(0)
-	};
-
-	mmap_read_lock(&init_mm);
-	ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
-	mmap_read_unlock(&init_mm);
-
-	return ret;
+	return __set_memory((unsigned long)page_address(page), 1,
+			    PAGE_KERNEL, __pgprot(0));
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
diff --git a/arch/riscv/mm/pmem.c b/arch/riscv/mm/pmem.c
index c5fc5ec96f6d..370a422ede11 100644
--- a/arch/riscv/mm/pmem.c
+++ b/arch/riscv/mm/pmem.c
@@ -17,7 +17,7 @@ void arch_wb_cache_pmem(void *addr, size_t size)
 		return;
 	}
 #endif
-	ALT_CMO_OP(clean, addr, size, riscv_cbom_block_size);
+	ALT_CMO_OP(CLEAN, addr, size, riscv_cbom_block_size);
 }
 EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
 
@@ -29,6 +29,6 @@ void arch_invalidate_pmem(void *addr, size_t size)
 		return;
 	}
 #endif
-	ALT_CMO_OP(inval, addr, size, riscv_cbom_block_size);
+	ALT_CMO_OP(INVAL, addr, size, riscv_cbom_block_size);
 }
 EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c
index e9090b38f811..657c27bc07a7 100644
--- a/arch/riscv/mm/ptdump.c
+++ b/arch/riscv/mm/ptdump.c
@@ -129,55 +129,55 @@ static struct ptd_mm_info efi_ptd_info = {
 /* Page Table Entry */
 struct prot_bits {
 	u64 mask;
-	u64 val;
 	const char *set;
 	const char *clear;
 };
 
 static const struct prot_bits pte_bits[] = {
 	{
+#ifdef CONFIG_64BIT
+		.mask = _PAGE_NAPOT,
+		.set = "N",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_MTMASK_SVPBMT,
+		.set = "MT(%s)",
+		.clear = "  ..  ",
+	}, {
+#endif
 		.mask = _PAGE_SOFT,
-		.val = _PAGE_SOFT,
-		.set = "RSW",
-		.clear = "   ",
+		.set = "RSW(%d)",
+		.clear = "  ..  ",
 	}, {
 		.mask = _PAGE_DIRTY,
-		.val = _PAGE_DIRTY,
 		.set = "D",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_ACCESSED,
-		.val = _PAGE_ACCESSED,
 		.set = "A",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_GLOBAL,
-		.val = _PAGE_GLOBAL,
 		.set = "G",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_USER,
-		.val = _PAGE_USER,
 		.set = "U",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_EXEC,
-		.val = _PAGE_EXEC,
 		.set = "X",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_WRITE,
-		.val = _PAGE_WRITE,
 		.set = "W",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_READ,
-		.val = _PAGE_READ,
 		.set = "R",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_PRESENT,
-		.val = _PAGE_PRESENT,
 		.set = "V",
 		.clear = ".",
 	}
@@ -208,15 +208,30 @@ static void dump_prot(struct pg_state *st)
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(pte_bits); i++) {
-		const char *s;
+		char s[7];
+		unsigned long val;
 
-		if ((st->current_prot & pte_bits[i].mask) == pte_bits[i].val)
-			s = pte_bits[i].set;
-		else
-			s = pte_bits[i].clear;
+		val = st->current_prot & pte_bits[i].mask;
+		if (val) {
+			if (pte_bits[i].mask == _PAGE_SOFT)
+				sprintf(s, pte_bits[i].set, val >> 8);
+#ifdef CONFIG_64BIT
+			else if (pte_bits[i].mask == _PAGE_MTMASK_SVPBMT) {
+				if (val == _PAGE_NOCACHE_SVPBMT)
+					sprintf(s, pte_bits[i].set, "NC");
+				else if (val == _PAGE_IO_SVPBMT)
+					sprintf(s, pte_bits[i].set, "IO");
+				else
+					sprintf(s, pte_bits[i].set, "??");
+			}
+#endif
+			else
+				sprintf(s, "%s", pte_bits[i].set);
+		} else {
+			sprintf(s, "%s", pte_bits[i].clear);
+		}
 
-		if (s)
-			pt_dump_seq_printf(st->seq, " %s", s);
+		pt_dump_seq_printf(st->seq, " %s", s);
 	}
 }
 
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 77be59aadc73..e6659d7368b3 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -3,33 +3,56 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
+#include <linux/hugetlb.h>
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
 
 static inline void local_flush_tlb_all_asid(unsigned long asid)
 {
-	__asm__ __volatile__ ("sfence.vma x0, %0"
-			:
-			: "r" (asid)
-			: "memory");
+	if (asid != FLUSH_TLB_NO_ASID)
+		__asm__ __volatile__ ("sfence.vma x0, %0"
+				:
+				: "r" (asid)
+				: "memory");
+	else
+		local_flush_tlb_all();
 }
 
 static inline void local_flush_tlb_page_asid(unsigned long addr,
 		unsigned long asid)
 {
-	__asm__ __volatile__ ("sfence.vma %0, %1"
-			:
-			: "r" (addr), "r" (asid)
-			: "memory");
+	if (asid != FLUSH_TLB_NO_ASID)
+		__asm__ __volatile__ ("sfence.vma %0, %1"
+				:
+				: "r" (addr), "r" (asid)
+				: "memory");
+	else
+		local_flush_tlb_page(addr);
 }
 
-static inline void local_flush_tlb_range(unsigned long start,
-		unsigned long size, unsigned long stride)
+/*
+ * Flush entire TLB if number of entries to be flushed is greater
+ * than the threshold below.
+ */
+static unsigned long tlb_flush_all_threshold __read_mostly = 64;
+
+static void local_flush_tlb_range_threshold_asid(unsigned long start,
+						 unsigned long size,
+						 unsigned long stride,
+						 unsigned long asid)
 {
-	if (size <= stride)
-		local_flush_tlb_page(start);
-	else
-		local_flush_tlb_all();
+	unsigned long nr_ptes_in_range = DIV_ROUND_UP(size, stride);
+	int i;
+
+	if (nr_ptes_in_range > tlb_flush_all_threshold) {
+		local_flush_tlb_all_asid(asid);
+		return;
+	}
+
+	for (i = 0; i < nr_ptes_in_range; ++i) {
+		local_flush_tlb_page_asid(start, asid);
+		start += stride;
+	}
 }
 
 static inline void local_flush_tlb_range_asid(unsigned long start,
@@ -37,8 +60,10 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
 {
 	if (size <= stride)
 		local_flush_tlb_page_asid(start, asid);
-	else
+	else if (size == FLUSH_TLB_MAX_SIZE)
 		local_flush_tlb_all_asid(asid);
+	else
+		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
 }
 
 static void __ipi_flush_tlb_all(void *info)
@@ -51,7 +76,7 @@ void flush_tlb_all(void)
 	if (riscv_use_ipi_for_rfence())
 		on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
 	else
-		sbi_remote_sfence_vma(NULL, 0, -1);
+		sbi_remote_sfence_vma_asid(NULL, 0, FLUSH_TLB_MAX_SIZE, FLUSH_TLB_NO_ASID);
 }
 
 struct flush_tlb_range_data {
@@ -68,68 +93,62 @@ static void __ipi_flush_tlb_range_asid(void *info)
 	local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
 }
 
-static void __ipi_flush_tlb_range(void *info)
-{
-	struct flush_tlb_range_data *d = info;
-
-	local_flush_tlb_range(d->start, d->size, d->stride);
-}
-
 static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
 			      unsigned long size, unsigned long stride)
 {
 	struct flush_tlb_range_data ftd;
-	struct cpumask *cmask = mm_cpumask(mm);
-	unsigned int cpuid;
+	const struct cpumask *cmask;
+	unsigned long asid = FLUSH_TLB_NO_ASID;
 	bool broadcast;
 
-	if (cpumask_empty(cmask))
-		return;
+	if (mm) {
+		unsigned int cpuid;
 
-	cpuid = get_cpu();
-	/* check if the tlbflush needs to be sent to other CPUs */
-	broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
-	if (static_branch_unlikely(&use_asid_allocator)) {
-		unsigned long asid = atomic_long_read(&mm->context.id) & asid_mask;
-
-		if (broadcast) {
-			if (riscv_use_ipi_for_rfence()) {
-				ftd.asid = asid;
-				ftd.start = start;
-				ftd.size = size;
-				ftd.stride = stride;
-				on_each_cpu_mask(cmask,
-						 __ipi_flush_tlb_range_asid,
-						 &ftd, 1);
-			} else
-				sbi_remote_sfence_vma_asid(cmask,
-							   start, size, asid);
-		} else {
-			local_flush_tlb_range_asid(start, size, stride, asid);
-		}
+		cmask = mm_cpumask(mm);
+		if (cpumask_empty(cmask))
+			return;
+
+		cpuid = get_cpu();
+		/* check if the tlbflush needs to be sent to other CPUs */
+		broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
+
+		if (static_branch_unlikely(&use_asid_allocator))
+			asid = atomic_long_read(&mm->context.id) & asid_mask;
 	} else {
-		if (broadcast) {
-			if (riscv_use_ipi_for_rfence()) {
-				ftd.asid = 0;
-				ftd.start = start;
-				ftd.size = size;
-				ftd.stride = stride;
-				on_each_cpu_mask(cmask,
-						 __ipi_flush_tlb_range,
-						 &ftd, 1);
-			} else
-				sbi_remote_sfence_vma(cmask, start, size);
-		} else {
-			local_flush_tlb_range(start, size, stride);
-		}
+		cmask = cpu_online_mask;
+		broadcast = true;
 	}
 
-	put_cpu();
+	if (broadcast) {
+		if (riscv_use_ipi_for_rfence()) {
+			ftd.asid = asid;
+			ftd.start = start;
+			ftd.size = size;
+			ftd.stride = stride;
+			on_each_cpu_mask(cmask,
+					 __ipi_flush_tlb_range_asid,
+					 &ftd, 1);
+		} else
+			sbi_remote_sfence_vma_asid(cmask,
+						   start, size, asid);
+	} else {
+		local_flush_tlb_range_asid(start, size, stride, asid);
+	}
+
+	if (mm)
+		put_cpu();
 }
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	__flush_tlb_range(mm, 0, -1, PAGE_SIZE);
+	__flush_tlb_range(mm, 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+}
+
+void flush_tlb_mm_range(struct mm_struct *mm,
+			unsigned long start, unsigned long end,
+			unsigned int page_size)
+{
+	__flush_tlb_range(mm, start, end - start, page_size);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
@@ -140,8 +159,40 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end)
 {
-	__flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE);
+	unsigned long stride_size;
+
+	if (!is_vm_hugetlb_page(vma)) {
+		stride_size = PAGE_SIZE;
+	} else {
+		stride_size = huge_page_size(hstate_vma(vma));
+
+		/*
+		 * As stated in the privileged specification, every PTE in a
+		 * NAPOT region must be invalidated, so reset the stride in that
+		 * case.
+		 */
+		if (has_svnapot()) {
+			if (stride_size >= PGDIR_SIZE)
+				stride_size = PGDIR_SIZE;
+			else if (stride_size >= P4D_SIZE)
+				stride_size = P4D_SIZE;
+			else if (stride_size >= PUD_SIZE)
+				stride_size = PUD_SIZE;
+			else if (stride_size >= PMD_SIZE)
+				stride_size = PMD_SIZE;
+			else
+				stride_size = PAGE_SIZE;
+		}
+	}
+
+	__flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
+}
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	__flush_tlb_range(NULL, start, end - start, PAGE_SIZE);
 }
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end)
diff --git a/arch/riscv/purgatory/entry.S b/arch/riscv/purgatory/entry.S
index 0194f4554130..5bcf3af903da 100644
--- a/arch/riscv/purgatory/entry.S
+++ b/arch/riscv/purgatory/entry.S
@@ -7,15 +7,11 @@
  * Author: Li Zhengyu (lizhengyu3@huawei.com)
  *
  */
-
-.macro	size, sym:req
-	.size \sym, . - \sym
-.endm
+#include <linux/linkage.h>
 
 .text
 
-.globl purgatory_start
-purgatory_start:
+SYM_CODE_START(purgatory_start)
 
 	lla	sp, .Lstack
 	mv	s0, a0	/* The hartid of the current hart */
@@ -28,8 +24,7 @@ purgatory_start:
 	mv	a1, s1
 	ld	a2, riscv_kernel_entry
 	jr	a2
-
-size purgatory_start
+SYM_CODE_END(purgatory_start)
 
 .align 4
 	.rept	256
@@ -39,9 +34,6 @@ size purgatory_start
 
 .data
 
-.globl riscv_kernel_entry
-riscv_kernel_entry:
-	.quad	0
-size riscv_kernel_entry
+SYM_DATA(riscv_kernel_entry, .quad 0)
 
 .end