4 files changed, 45 insertions, 13 deletions

diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 95cd62d67371..2cf999e41d30 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -29,7 +29,7 @@
 	.endm
 
 	.macro ldrh1 reg, ptr, val
-	user_ldst 9998f, ldtrh, \reg, \ptr, \val
+	user_ldst 9997f, ldtrh, \reg, \ptr, \val
 	.endm
 
 	.macro strh1 reg, ptr, val
@@ -37,7 +37,7 @@
 	.endm
 
 	.macro ldr1 reg, ptr, val
-	user_ldst 9998f, ldtr, \reg, \ptr, \val
+	user_ldst 9997f, ldtr, \reg, \ptr, \val
 	.endm
 
 	.macro str1 reg, ptr, val
@@ -45,7 +45,7 @@
 	.endm
 
 	.macro ldp1 reg1, reg2, ptr, val
-	user_ldp 9998f, \reg1, \reg2, \ptr, \val
+	user_ldp 9997f, \reg1, \reg2, \ptr, \val
 	.endm
 
 	.macro stp1 reg1, reg2, ptr, val
@@ -53,8 +53,10 @@
 	.endm
 
 end	.req	x5
+srcin	.req	x15
 SYM_FUNC_START(__arch_copy_from_user)
 	add	end, x0, x2
+	mov	srcin, x1
 #include "copy_template.S"
 	mov	x0, #0				// Nothing to copy
 	ret
@@ -63,6 +65,11 @@ EXPORT_SYMBOL(__arch_copy_from_user)
 
 	.section .fixup,"ax"
 	.align	2
+9997:	cmp	dst, dstin
+	b.ne	9998f
+	// Before being absolutely sure we couldn't copy anything, try harder
+USER(9998f, ldtrb tmp1w, [srcin])
+	strb	tmp1w, [dst], #1
 9998:	sub	x0, end, dst			// bytes not copied
 	ret
 	.previous
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index 1f61cd0df062..dbea3799c3ef 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -30,33 +30,34 @@
 	.endm
 
 	.macro ldrh1 reg, ptr, val
-	user_ldst 9998f, ldtrh, \reg, \ptr, \val
+	user_ldst 9997f, ldtrh, \reg, \ptr, \val
 	.endm
 
 	.macro strh1 reg, ptr, val
-	user_ldst 9998f, sttrh, \reg, \ptr, \val
+	user_ldst 9997f, sttrh, \reg, \ptr, \val
 	.endm
 
 	.macro ldr1 reg, ptr, val
-	user_ldst 9998f, ldtr, \reg, \ptr, \val
+	user_ldst 9997f, ldtr, \reg, \ptr, \val
 	.endm
 
 	.macro str1 reg, ptr, val
-	user_ldst 9998f, sttr, \reg, \ptr, \val
+	user_ldst 9997f, sttr, \reg, \ptr, \val
 	.endm
 
 	.macro ldp1 reg1, reg2, ptr, val
-	user_ldp 9998f, \reg1, \reg2, \ptr, \val
+	user_ldp 9997f, \reg1, \reg2, \ptr, \val
 	.endm
 
 	.macro stp1 reg1, reg2, ptr, val
-	user_stp 9998f, \reg1, \reg2, \ptr, \val
+	user_stp 9997f, \reg1, \reg2, \ptr, \val
 	.endm
 
 end	.req	x5
-
+srcin	.req	x15
 SYM_FUNC_START(__arch_copy_in_user)
 	add	end, x0, x2
+	mov	srcin, x1
 #include "copy_template.S"
 	mov	x0, #0
 	ret
@@ -65,6 +66,12 @@ EXPORT_SYMBOL(__arch_copy_in_user)
 
 	.section .fixup,"ax"
 	.align	2
+9997:	cmp	dst, dstin
+	b.ne	9998f
+	// Before being absolutely sure we couldn't copy anything, try harder
+USER(9998f, ldtrb tmp1w, [srcin])
+USER(9998f, sttrb tmp1w, [dst])
+	add	dst, dst, #1
 9998:	sub	x0, end, dst			// bytes not copied
 	ret
 	.previous
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 043da90f5dd7..9f380eecf653 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -32,7 +32,7 @@
 	.endm
 
 	.macro strh1 reg, ptr, val
-	user_ldst 9998f, sttrh, \reg, \ptr, \val
+	user_ldst 9997f, sttrh, \reg, \ptr, \val
 	.endm
 
 	.macro ldr1 reg, ptr, val
@@ -40,7 +40,7 @@
 	.endm
 
 	.macro str1 reg, ptr, val
-	user_ldst 9998f, sttr, \reg, \ptr, \val
+	user_ldst 9997f, sttr, \reg, \ptr, \val
 	.endm
 
 	.macro ldp1 reg1, reg2, ptr, val
@@ -48,12 +48,14 @@
 	.endm
 
 	.macro stp1 reg1, reg2, ptr, val
-	user_stp 9998f, \reg1, \reg2, \ptr, \val
+	user_stp 9997f, \reg1, \reg2, \ptr, \val
 	.endm
 
 end	.req	x5
+srcin	.req	x15
 SYM_FUNC_START(__arch_copy_to_user)
 	add	end, x0, x2
+	mov	srcin, x1
 #include "copy_template.S"
 	mov	x0, #0
 	ret
@@ -62,6 +64,12 @@ EXPORT_SYMBOL(__arch_copy_to_user)
 
 	.section .fixup,"ax"
 	.align	2
+9997:	cmp	dst, dstin
+	b.ne	9998f
+	// Before being absolutely sure we couldn't copy anything, try harder
+	ldrb	tmp1w, [srcin]
+USER(9998f, sttrb tmp1w, [dst])
+	add	dst, dst, #1
 9998:	sub	x0, end, dst			// bytes not copied
 	ret
 	.previous
diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S
index 35fbdb7d6e1a..1648790e91b3 100644
--- a/arch/arm64/lib/strlen.S
+++ b/arch/arm64/lib/strlen.S
@@ -8,6 +8,7 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/mte-def.h>
 
 /* Assumptions:
  *
@@ -42,7 +43,16 @@
 #define REP8_7f 0x7f7f7f7f7f7f7f7f
 #define REP8_80 0x8080808080808080
 
+/*
+ * When KASAN_HW_TAGS is in use, memory is checked at MTE_GRANULE_SIZE
+ * (16-byte) granularity, and we must ensure that no access straddles this
+ * alignment boundary.
+ */
+#ifdef CONFIG_KASAN_HW_TAGS
+#define MIN_PAGE_SIZE MTE_GRANULE_SIZE
+#else
 #define MIN_PAGE_SIZE 4096
+#endif
 
 	/* Since strings are short on average, we check the first 16 bytes
 	   of the string for a NUL character.  In order to do an unaligned ldp