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()
  ...

Author: torvalds

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>