arm64: lib: Use MOPS for memcpy() routines

Make memcpy(), memmove() and memset() use the Armv8.8 FEAT_MOPS
instructions when implemented on the CPU.

The CPY*/SET* instructions copy or set a block of memory of arbitrary
size and alignment. They can be interrupted by the CPU and the copying
resumed later. Their performance is expected to be close to the best
generic copy/set sequence of loads/stores for a given CPU. Using them in
the kernel's copy/set routines therefore avoids the need to periodically
rewrite the routines to optimize for new microarchitectures. It could
also lead to a performance improvement for some CPUs and systems.

With this change the kernel will always use the instructions if they are
implemented on the CPU (and have not been disabled by the arm64.nomops
command line parameter). When not implemented the usual routines will be
used (patched via alternatives). Note, we need to patch B/NOP instead of
the whole sequence to avoid executing a partially patched sequence in
case the compiler generates a mem*() call inside the alternatives
patching code.

Note that MOPS instructions have relaxed behavior on Device memory, but
it is expected that these routines are not generally used on MMIO.

Note: For memcpy(), this uses the CPY* instructions instead of CPYF*, as
CPY* allows overlaps between the source and destination buffers, and
despite contradicting the C standard, compilers require that memcpy()
work on exactly overlapping source and destination:
  https://gcc.gnu.org/onlinedocs/gcc/Standards.html#C-Language
  https://reviews.llvm.org/D86993

Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
Link: https://lore.kernel.org/r/20240930161051.3777828-5-kristina.martsenko@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

Author: kristina-martsenko

arch/arm64/Kconfig

@@ -2155,6 +2155,9 @@ config ARM64_EPAN
 	  if the cpu does not implement the feature.
 endmenu # "ARMv8.7 architectural features"
 
+config AS_HAS_MOPS
+	def_bool $(as-instr,.arch_extension mops)
+
 menu "ARMv8.9 architectural features"
 
 config ARM64_POE

arch/arm64/lib/memcpy.S

@@ -57,7 +57,7 @@
    The loop tail is handled by always copying 64 bytes from the end.
 */
 
-SYM_FUNC_START(__pi_memcpy)
+SYM_FUNC_START_LOCAL(__pi_memcpy_generic)
 	add	srcend, src, count
 	add	dstend, dstin, count
 	cmp	count, 128
@@ -238,7 +238,24 @@ L(copy64_from_start):
 	stp	B_l, B_h, [dstin, 16]
 	stp	C_l, C_h, [dstin]
 	ret
+SYM_FUNC_END(__pi_memcpy_generic)
+
+#ifdef CONFIG_AS_HAS_MOPS
+	.arch_extension mops
+SYM_FUNC_START(__pi_memcpy)
+alternative_if_not ARM64_HAS_MOPS
+	b	__pi_memcpy_generic
+alternative_else_nop_endif
+
+	mov	dst, dstin
+	cpyp	[dst]!, [src]!, count!
+	cpym	[dst]!, [src]!, count!
+	cpye	[dst]!, [src]!, count!
+	ret
 SYM_FUNC_END(__pi_memcpy)
+#else
+SYM_FUNC_ALIAS(__pi_memcpy, __pi_memcpy_generic)
+#endif
 
 SYM_FUNC_ALIAS(__memcpy, __pi_memcpy)
 EXPORT_SYMBOL(__memcpy)

arch/arm64/lib/memset.S

@@ -26,6 +26,7 @@
  */
 
 dstin		.req	x0
+val_x		.req	x1
 val		.req	w1
 count		.req	x2
 tmp1		.req	x3
@@ -42,7 +43,7 @@ dst		.req	x8
 tmp3w		.req	w9
 tmp3		.req	x9
 
-SYM_FUNC_START(__pi_memset)
+SYM_FUNC_START_LOCAL(__pi_memset_generic)
 	mov	dst, dstin	/* Preserve return value.  */
 	and	A_lw, val, #255
 	orr	A_lw, A_lw, A_lw, lsl #8
@@ -201,7 +202,24 @@ SYM_FUNC_START(__pi_memset)
 	ands	count, count, zva_bits_x
 	b.ne	.Ltail_maybe_long
 	ret
+SYM_FUNC_END(__pi_memset_generic)
+
+#ifdef CONFIG_AS_HAS_MOPS
+	.arch_extension mops
+SYM_FUNC_START(__pi_memset)
+alternative_if_not ARM64_HAS_MOPS
+	b	__pi_memset_generic
+alternative_else_nop_endif
+
+	mov	dst, dstin
+	setp	[dst]!, count!, val_x
+	setm	[dst]!, count!, val_x
+	sete	[dst]!, count!, val_x
+	ret
 SYM_FUNC_END(__pi_memset)
+#else
+SYM_FUNC_ALIAS(__pi_memset, __pi_memset_generic)
+#endif
 
 SYM_FUNC_ALIAS(__memset, __pi_memset)
 EXPORT_SYMBOL(__memset)