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()
  ...

Documentation/arch/riscv/uabi.rst

@@ -42,6 +42,26 @@ An example string following the order is::
 
    rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux
 
+"isa" and "hart isa" lines in /proc/cpuinfo
+-------------------------------------------
+
+The "isa" line in /proc/cpuinfo describes the lowest common denominator of
+RISC-V ISA extensions recognized by the kernel and implemented on all harts. The
+"hart isa" line, in contrast, describes the set of extensions recognized by the
+kernel on the particular hart being described, even if those extensions may not
+be present on all harts in the system.
+
+In both lines, the presence of an extension guarantees only that the hardware
+has the described capability. Additional kernel support or policy changes may be
+required before an extension's capability is fully usable by userspace programs.
+Similarly, for S-mode extensions, presence in one of these lines does not
+guarantee that the kernel is taking advantage of the extension, or that the
+feature will be visible in guest VMs managed by this kernel.
+
+Inversely, the absence of an extension in these lines does not necessarily mean
+the hardware does not support that feature. The running kernel may not recognize
+the extension, or may have deliberately removed it from the listing.
+
 Misaligned accesses
 -------------------
 

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"

arch/riscv/Kconfig.debug

@@ -0,0 +1 @@
+source "arch/riscv/kernel/tests/Kconfig.debug"

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

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

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>
 

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

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.

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 */

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)			\

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 */

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))
 

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)

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
 
 /*

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)
 {

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 */

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,

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>

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 */

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 */