Merge tag 'loongarch-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch updates from Huacai Chen:

 - Better backtraces for humanization

 - Relay BCE exceptions to userland as SIGSEGV

 - Provide kernel fpu functions

 - Optimize memory ops (memset/memcpy/memmove)

 - Optimize checksum and crc32(c) calculation

 - Add ARCH_HAS_FORTIFY_SOURCE selection

 - Add function error injection support

 - Add ftrace with direct call support

 - Add basic perf tools support

* tag 'loongarch-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson: (24 commits)
  tools/perf: Add basic support for LoongArch
  LoongArch: ftrace: Add direct call trampoline samples support
  LoongArch: ftrace: Add direct call support
  LoongArch: ftrace: Implement ftrace_find_callable_addr() to simplify code
  LoongArch: ftrace: Fix build error if DYNAMIC_FTRACE_WITH_REGS is not set
  LoongArch: ftrace: Abstract DYNAMIC_FTRACE_WITH_ARGS accesses
  LoongArch: Add support for function error injection
  LoongArch: Add ARCH_HAS_FORTIFY_SOURCE selection
  LoongArch: crypto: Add crc32 and crc32c hw acceleration
  LoongArch: Add checksum optimization for 64-bit system
  LoongArch: Optimize memory ops (memset/memcpy/memmove)
  LoongArch: Provide kernel fpu functions
  LoongArch: Relay BCE exceptions to userland as SIGSEGV with si_code=SEGV_BNDERR
  LoongArch: Tweak the BADV and CPUCFG.PRID lines in show_regs()
  LoongArch: Humanize the ESTAT line when showing registers
  LoongArch: Humanize the ECFG line when showing registers
  LoongArch: Humanize the EUEN line when showing registers
  LoongArch: Humanize the PRMD line when showing registers
  LoongArch: Humanize the CRMD line when showing registers
  LoongArch: Fix format of CSR lines during show_regs()
  ...

1 files changed, 68 insertions, 52 deletions

diff --git a/arch/loongarch/lib/memmove.S b/arch/loongarch/lib/memmove.S
index b796c3d6da05..45b725ba7867 100644
--- a/arch/loongarch/lib/memmove.S
+++ b/arch/loongarch/lib/memmove.S
@@ -11,23 +11,9 @@
 #include <asm/regdef.h>
 
 SYM_FUNC_START(memmove)
-	blt	a0, a1, 1f	/* dst < src, memcpy */
-	blt	a1, a0, 3f	/* src < dst, rmemcpy */
+	blt	a0, a1, memcpy	/* dst < src, memcpy */
+	blt	a1, a0, rmemcpy	/* src < dst, rmemcpy */
 	jr	ra		/* dst == src, return */
-
-	/* if (src - dst) < 64, copy 1 byte at a time */
-1:	ori	a3, zero, 64
-	sub.d	t0, a1, a0
-	blt	t0, a3, 2f
-	b	memcpy
-2:	b	__memcpy_generic
-
-	/* if (dst - src) < 64, copy 1 byte at a time */
-3:	ori	a3, zero, 64
-	sub.d	t0, a0, a1
-	blt	t0, a3, 4f
-	b	rmemcpy
-4:	b	__rmemcpy_generic
 SYM_FUNC_END(memmove)
 _ASM_NOKPROBE(memmove)
 
@@ -76,50 +62,80 @@ _ASM_NOKPROBE(__rmemcpy_generic)
  * a2: n
  */
 SYM_FUNC_START(__rmemcpy_fast)
-	move	a3, a0
-	beqz	a2, 3f
+	sltui	t0, a2, 9
+	bnez	t0, __memcpy_small
 
-	add.d	a0, a0, a2
-	add.d	a1, a1, a2
+	add.d	a3, a1, a2
+	add.d	a2, a0, a2
+	ld.d	a6, a1, 0
+	ld.d	a7, a3, -8
+
+	/* align up destination address */
+	andi	t1, a2, 7
+	sub.d	a3, a3, t1
+	sub.d	a5, a2, t1
 
-	ori	a4, zero, 64
-	blt	a2, a4, 2f
+	addi.d	a4, a1, 64
+	bgeu	a4, a3, .Llt64
 
 	/* copy 64 bytes at a time */
-1:	ld.d	t0, a1, -8
-	ld.d	t1, a1, -16
-	ld.d	t2, a1, -24
-	ld.d	t3, a1, -32
-	ld.d	t4, a1, -40
-	ld.d	t5, a1, -48
-	ld.d	t6, a1, -56
-	ld.d	t7, a1, -64
-	st.d	t0, a0, -8
-	st.d	t1, a0, -16
-	st.d	t2, a0, -24
-	st.d	t3, a0, -32
-	st.d	t4, a0, -40
-	st.d	t5, a0, -48
-	st.d	t6, a0, -56
-	st.d	t7, a0, -64
-
-	addi.d	a0, a0, -64
-	addi.d	a1, a1, -64
-	addi.d	a2, a2, -64
-	bge	a2, a4, 1b
-
-	beqz	a2, 3f
+.Lloop64:
+	ld.d	t0, a3, -8
+	ld.d	t1, a3, -16
+	ld.d	t2, a3, -24
+	ld.d	t3, a3, -32
+	ld.d	t4, a3, -40
+	ld.d	t5, a3, -48
+	ld.d	t6, a3, -56
+	ld.d	t7, a3, -64
+	addi.d	a3, a3, -64
+	st.d	t0, a5, -8
+	st.d	t1, a5, -16
+	st.d	t2, a5, -24
+	st.d	t3, a5, -32
+	st.d	t4, a5, -40
+	st.d	t5, a5, -48
+	st.d	t6, a5, -56
+	st.d	t7, a5, -64
+	addi.d	a5, a5, -64
+	bltu	a4, a3, .Lloop64
 
 	/* copy the remaining bytes */
-2:	ld.b	t0, a1, -1
-	st.b	t0, a0, -1
-	addi.d	a0, a0, -1
-	addi.d	a1, a1, -1
-	addi.d	a2, a2, -1
-	bgt	a2, zero, 2b
+.Llt64:
+	addi.d	a4, a1, 32
+	bgeu	a4, a3, .Llt32
+	ld.d	t0, a3, -8
+	ld.d	t1, a3, -16
+	ld.d	t2, a3, -24
+	ld.d	t3, a3, -32
+	addi.d	a3, a3, -32
+	st.d	t0, a5, -8
+	st.d	t1, a5, -16
+	st.d	t2, a5, -24
+	st.d	t3, a5, -32
+	addi.d	a5, a5, -32
+
+.Llt32:
+	addi.d	a4, a1, 16
+	bgeu	a4, a3, .Llt16
+	ld.d	t0, a3, -8
+	ld.d	t1, a3, -16
+	addi.d	a3, a3, -16
+	st.d	t0, a5, -8
+	st.d	t1, a5, -16
+	addi.d	a5, a5, -16
+
+.Llt16:
+	addi.d	a4, a1, 8
+	bgeu	a4, a3, .Llt8
+	ld.d	t0, a3, -8
+	st.d	t0, a5, -8
+
+.Llt8:
+	st.d	a6, a0, 0
+	st.d	a7, a2, -8
 
 	/* return */
-3:	move	a0, a3
 	jr	ra
 SYM_FUNC_END(__rmemcpy_fast)
 _ASM_NOKPROBE(__rmemcpy_fast)