Merge branch 'for-next/mops' into for-next/core

* for-next/mops:
  : More FEAT_MOPS (memcpy instructions) uses - in-kernel routines
  arm64: mops: Document requirements for hypervisors
  arm64: lib: Use MOPS for copy_page() and clear_page()
  arm64: lib: Use MOPS for memcpy() routines
  arm64: mops: Document booting requirement for HCR_EL2.MCE2
  arm64: mops: Handle MOPS exceptions from EL1
  arm64: probes: Disable kprobes/uprobes on MOPS instructions

# Conflicts:
#	arch/arm64/kernel/entry-common.c

4 files changed, 63 insertions, 2 deletions

diff --git a/arch/arm64/lib/clear_page.S b/arch/arm64/lib/clear_page.S
index ebde40e7fa2b..bd6f7d5eb6eb 100644
--- a/arch/arm64/lib/clear_page.S
+++ b/arch/arm64/lib/clear_page.S
@@ -15,6 +15,19 @@
  *	x0 - dest
  */
 SYM_FUNC_START(__pi_clear_page)
+#ifdef CONFIG_AS_HAS_MOPS
+	.arch_extension mops
+alternative_if_not ARM64_HAS_MOPS
+	b	.Lno_mops
+alternative_else_nop_endif
+
+	mov	x1, #PAGE_SIZE
+	setpn	[x0]!, x1!, xzr
+	setmn	[x0]!, x1!, xzr
+	seten	[x0]!, x1!, xzr
+	ret
+.Lno_mops:
+#endif
 	mrs	x1, dczid_el0
 	tbnz	x1, #4, 2f	/* Branch if DC ZVA is prohibited */
 	and	w1, w1, #0xf
diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S
index 6a56d7cf309d..e6374e7e5511 100644
--- a/arch/arm64/lib/copy_page.S
+++ b/arch/arm64/lib/copy_page.S
@@ -18,6 +18,19 @@
  *	x1 - src
  */
 SYM_FUNC_START(__pi_copy_page)
+#ifdef CONFIG_AS_HAS_MOPS
+	.arch_extension mops
+alternative_if_not ARM64_HAS_MOPS
+	b	.Lno_mops
+alternative_else_nop_endif
+
+	mov	x2, #PAGE_SIZE
+	cpypwn	[x0]!, [x1]!, x2!
+	cpymwn	[x0]!, [x1]!, x2!
+	cpyewn	[x0]!, [x1]!, x2!
+	ret
+.Lno_mops:
+#endif
 	ldp	x2, x3, [x1]
 	ldp	x4, x5, [x1, #16]
 	ldp	x6, x7, [x1, #32]
diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S
index 4ab48d49c451..9b99106fb95f 100644
--- a/arch/arm64/lib/memcpy.S
+++ b/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)
diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S
index a5aebe82ad73..97157da65ec6 100644
--- a/arch/arm64/lib/memset.S
+++ b/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)