[glibc/nsz/mtag] malloc: Only support zeroing and not arbitrary memset with mtag

[glibc/nsz/mtag] malloc: Only support zeroing and not arbitrary memset with mtag

[Szabolcs Nagy]

https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=8ec6e98d17b23ddc04a3b3beba159835c17cf526

commit 8ec6e98d17b23ddc04a3b3beba159835c17cf526
Author: Szabolcs Nagy <szabolcs.nagy@arm.com>
Date:   Fri Jan 29 17:07:28 2021 +0000

    malloc: Only support zeroing and not arbitrary memset with mtag
    
    The memset api is suboptimal and does not provide much benefit. Memory
    tagging only needs a zeroing memset (and only for memory that's sized
    and aligned to multiples of the tag granule), so change the internal
    api and the target hooks accordingly.  This is to simplify the
    implementation of the target hook.
    
    Reviewed-by: DJ Delorie <dj@redhat.com>

Diff:
---
 malloc/malloc.c                                        | 17 ++++++++---------
 sysdeps/aarch64/Makefile                               |  2 +-
 .../{__mtag_memset_tag.S => __mtag_tag_zero_region.S}  | 18 +++++++-----------
 sysdeps/aarch64/libc-mtag.h                            |  4 ++--
 sysdeps/generic/libc-mtag.h                            |  6 +++---
 5 files changed, 21 insertions(+), 26 deletions(-)

diff --git a/malloc/malloc.c b/malloc/malloc.c
index 253a919ec5..01cf6e9325 100644
--- a/malloc/malloc.c
+++ b/malloc/malloc.c
@@ -413,12 +413,11 @@ void *(*__morecore)(ptrdiff_t) = __default_morecore;
    operations can continue to be used.  Support macros are used to do
    this:
 
-   void *tag_new_memset (void *ptr, int, val, size_t size)
+   void *tag_new_zero_region (void *ptr, size_t size)
 
-   Has the same interface as memset(), but additionally allocates a
-   new tag, colors the memory with that tag and returns a pointer that
-   is correctly colored for that location.  The non-tagging version
-   will simply call memset.
+   Allocates a new tag, colors the memory with that tag, zeros the
+   memory and returns a pointer that is correctly colored for that
+   location.  The non-tagging version will simply call memset with 0.
 
    void *tag_region (void *ptr, size_t size)
 
@@ -458,11 +457,11 @@ tag_region (void *ptr, size_t size)
 }
 
 static __always_inline void *
-tag_new_memset (void *ptr, int val, size_t size)
+tag_new_zero_region (void *ptr, size_t size)
 {
   if (__glibc_unlikely (mtag_enabled))
-    return __libc_mtag_memset_with_tag (__libc_mtag_new_tag (ptr), val, size);
-  return memset (ptr, val, size);
+    return __libc_mtag_tag_zero_region (__libc_mtag_new_tag (ptr), size);
+  return memset (ptr, 0, size);
 }
 
 /* Defined later.  */
@@ -3679,7 +3678,7 @@ __libc_calloc (size_t n, size_t elem_size)
      regardless of MORECORE_CLEARS, so we zero the whole block while
      doing so.  */
 #ifdef USE_MTAG
-  return tag_new_memset (mem, 0, CHUNK_AVAILABLE_SIZE (p) - CHUNK_HDR_SZ);
+  return tag_new_zero_region (mem, CHUNK_AVAILABLE_SIZE (p) - CHUNK_HDR_SZ);
 #else
   INTERNAL_SIZE_T csz = chunksize (p);
 
diff --git a/sysdeps/aarch64/Makefile b/sysdeps/aarch64/Makefile
index d3ab37a40a..259070cfad 100644
--- a/sysdeps/aarch64/Makefile
+++ b/sysdeps/aarch64/Makefile
@@ -41,7 +41,7 @@ endif
 ifeq ($(subdir),misc)
 sysdep_headers += sys/ifunc.h
 sysdep_routines += __mtag_address_get_tag \
-		   __mtag_memset_tag \
+		   __mtag_tag_zero_region \
 		   __mtag_new_tag \
 		   __mtag_tag_region
 
diff --git a/sysdeps/aarch64/__mtag_memset_tag.S b/sysdeps/aarch64/__mtag_tag_zero_region.S
similarity index 82%
rename from sysdeps/aarch64/__mtag_memset_tag.S
rename to sysdeps/aarch64/__mtag_tag_zero_region.S
index 3c202888a4..74d398bba5 100644
--- a/sysdeps/aarch64/__mtag_memset_tag.S
+++ b/sysdeps/aarch64/__mtag_tag_zero_region.S
@@ -20,9 +20,6 @@
 
 #ifdef USE_MTAG
 
-/* Use the same register names and assignments as memset.  */
-#include "memset-reg.h"
-
 	.arch armv8.5-a
 	.arch_extension memtag
 
@@ -31,16 +28,15 @@
 /* FIXME: This is a minimal implementation.  We could do much better than
    this for large values of COUNT.  */
 
-ENTRY(__libc_mtag_memset_with_tag)
+#define dstin x0
+#define count x1
+#define dst   x2
 
-	and	valw, valw, 255
-	orr	valw, valw, valw, lsl 8
-	orr	valw, valw, valw, lsl 16
-	orr	val, val, val, lsl 32
-	mov	dst, dstin
+ENTRY(__libc_mtag_tag_zero_region)
 
+	mov	dst, dstin
 L(loop):
-	stgp	val, val, [dst], #16
+	stzg	dst, [dst], #16
 	subs	count, count, 16
 	bne	L(loop)
 #if 0
@@ -49,5 +45,5 @@ L(loop):
 	ldg	dstin, [dstin] // Recover the tag created (might be untagged).
 #endif
 	ret
-END (__libc_mtag_memset_with_tag)
+END (__libc_mtag_tag_zero_region)
 #endif /* USE_MTAG */
diff --git a/sysdeps/aarch64/libc-mtag.h b/sysdeps/aarch64/libc-mtag.h
index 979cbb743e..f58402ccf9 100644
--- a/sysdeps/aarch64/libc-mtag.h
+++ b/sysdeps/aarch64/libc-mtag.h
@@ -39,8 +39,8 @@
    void *__libc_mtag_tag_region (const void *, size_t)  */
 void *__libc_mtag_tag_region (void *, size_t);
 
-/* Optimized equivalent to __libc_mtag_tag_region followed by memset.  */
-void *__libc_mtag_memset_with_tag (void *, int, size_t);
+/* Optimized equivalent to __libc_mtag_tag_region followed by memset to 0.  */
+void *__libc_mtag_tag_zero_region (void *, size_t);
 
 /* Convert address P to a pointer that is tagged correctly for that
    location.
diff --git a/sysdeps/generic/libc-mtag.h b/sysdeps/generic/libc-mtag.h
index e8fc236b6c..4743e873f1 100644
--- a/sysdeps/generic/libc-mtag.h
+++ b/sysdeps/generic/libc-mtag.h
@@ -44,12 +44,12 @@ __libc_mtag_tag_region (void *p, size_t n)
   return p;
 }
 
-/* Optimized equivalent to __libc_mtag_tag_region followed by memset.  */
+/* Optimized equivalent to __libc_mtag_tag_region followed by memset to 0.  */
 static inline void *
-__libc_mtag_memset_with_tag (void *p, int c, size_t n)
+__libc_mtag_tag_zero_region (void *p, size_t n)
 {
   __libc_mtag_link_error ();
-  return memset (p, c, n);
+  return memset (p, 0, n);
 }
 
 /* Convert address P to a pointer that is tagged correctly for that

[glibc/nsz/mtag] malloc: Only support zeroing and not arbitrary memset with mtag

[Szabolcs Nagy]

https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=35218b88e7b231309b144b07f43a4077cfd971cd

commit 35218b88e7b231309b144b07f43a4077cfd971cd
Author: Szabolcs Nagy <szabolcs.nagy@arm.com>
Date:   Fri Jan 29 17:07:28 2021 +0000

    malloc: Only support zeroing and not arbitrary memset with mtag
    
    The memset api is suboptimal and does not provide much benefit. Memory
    tagging only needs a zeroing memset (and only for memory that's sized
    and aligned to multiples of the tag granule), so change the internal
    api and the target hooks accordingly.  This is to simplify the
    implementation of the target hook.
    
    Reviewed-by: DJ Delorie <dj@redhat.com>

Diff:
---
 malloc/malloc.c                                        | 17 ++++++++---------
 sysdeps/aarch64/Makefile                               |  2 +-
 .../{__mtag_memset_tag.S => __mtag_tag_zero_region.S}  | 18 +++++++-----------
 sysdeps/aarch64/libc-mtag.h                            |  4 ++--
 sysdeps/generic/libc-mtag.h                            |  6 +++---
 5 files changed, 21 insertions(+), 26 deletions(-)

diff --git a/malloc/malloc.c b/malloc/malloc.c
index 253a919ec5..01cf6e9325 100644
--- a/malloc/malloc.c
+++ b/malloc/malloc.c
@@ -413,12 +413,11 @@ void *(*__morecore)(ptrdiff_t) = __default_morecore;
    operations can continue to be used.  Support macros are used to do
    this:
 
-   void *tag_new_memset (void *ptr, int, val, size_t size)
+   void *tag_new_zero_region (void *ptr, size_t size)
 
-   Has the same interface as memset(), but additionally allocates a
-   new tag, colors the memory with that tag and returns a pointer that
-   is correctly colored for that location.  The non-tagging version
-   will simply call memset.
+   Allocates a new tag, colors the memory with that tag, zeros the
+   memory and returns a pointer that is correctly colored for that
+   location.  The non-tagging version will simply call memset with 0.
 
    void *tag_region (void *ptr, size_t size)
 
@@ -458,11 +457,11 @@ tag_region (void *ptr, size_t size)
 }
 
 static __always_inline void *
-tag_new_memset (void *ptr, int val, size_t size)
+tag_new_zero_region (void *ptr, size_t size)
 {
   if (__glibc_unlikely (mtag_enabled))
-    return __libc_mtag_memset_with_tag (__libc_mtag_new_tag (ptr), val, size);
-  return memset (ptr, val, size);
+    return __libc_mtag_tag_zero_region (__libc_mtag_new_tag (ptr), size);
+  return memset (ptr, 0, size);
 }
 
 /* Defined later.  */
@@ -3679,7 +3678,7 @@ __libc_calloc (size_t n, size_t elem_size)
      regardless of MORECORE_CLEARS, so we zero the whole block while
      doing so.  */
 #ifdef USE_MTAG
-  return tag_new_memset (mem, 0, CHUNK_AVAILABLE_SIZE (p) - CHUNK_HDR_SZ);
+  return tag_new_zero_region (mem, CHUNK_AVAILABLE_SIZE (p) - CHUNK_HDR_SZ);
 #else
   INTERNAL_SIZE_T csz = chunksize (p);
 
diff --git a/sysdeps/aarch64/Makefile b/sysdeps/aarch64/Makefile
index d3ab37a40a..259070cfad 100644
--- a/sysdeps/aarch64/Makefile
+++ b/sysdeps/aarch64/Makefile
@@ -41,7 +41,7 @@ endif
 ifeq ($(subdir),misc)
 sysdep_headers += sys/ifunc.h
 sysdep_routines += __mtag_address_get_tag \
-		   __mtag_memset_tag \
+		   __mtag_tag_zero_region \
 		   __mtag_new_tag \
 		   __mtag_tag_region
 
diff --git a/sysdeps/aarch64/__mtag_memset_tag.S b/sysdeps/aarch64/__mtag_tag_zero_region.S
similarity index 82%
rename from sysdeps/aarch64/__mtag_memset_tag.S
rename to sysdeps/aarch64/__mtag_tag_zero_region.S
index 3c202888a4..74d398bba5 100644
--- a/sysdeps/aarch64/__mtag_memset_tag.S
+++ b/sysdeps/aarch64/__mtag_tag_zero_region.S
@@ -20,9 +20,6 @@
 
 #ifdef USE_MTAG
 
-/* Use the same register names and assignments as memset.  */
-#include "memset-reg.h"
-
 	.arch armv8.5-a
 	.arch_extension memtag
 
@@ -31,16 +28,15 @@
 /* FIXME: This is a minimal implementation.  We could do much better than
    this for large values of COUNT.  */
 
-ENTRY(__libc_mtag_memset_with_tag)
+#define dstin x0
+#define count x1
+#define dst   x2
 
-	and	valw, valw, 255
-	orr	valw, valw, valw, lsl 8
-	orr	valw, valw, valw, lsl 16
-	orr	val, val, val, lsl 32
-	mov	dst, dstin
+ENTRY(__libc_mtag_tag_zero_region)
 
+	mov	dst, dstin
 L(loop):
-	stgp	val, val, [dst], #16
+	stzg	dst, [dst], #16
 	subs	count, count, 16
 	bne	L(loop)
 #if 0
@@ -49,5 +45,5 @@ L(loop):
 	ldg	dstin, [dstin] // Recover the tag created (might be untagged).
 #endif
 	ret
-END (__libc_mtag_memset_with_tag)
+END (__libc_mtag_tag_zero_region)
 #endif /* USE_MTAG */
diff --git a/sysdeps/aarch64/libc-mtag.h b/sysdeps/aarch64/libc-mtag.h
index 979cbb743e..f58402ccf9 100644
--- a/sysdeps/aarch64/libc-mtag.h
+++ b/sysdeps/aarch64/libc-mtag.h
@@ -39,8 +39,8 @@
    void *__libc_mtag_tag_region (const void *, size_t)  */
 void *__libc_mtag_tag_region (void *, size_t);
 
-/* Optimized equivalent to __libc_mtag_tag_region followed by memset.  */
-void *__libc_mtag_memset_with_tag (void *, int, size_t);
+/* Optimized equivalent to __libc_mtag_tag_region followed by memset to 0.  */
+void *__libc_mtag_tag_zero_region (void *, size_t);
 
 /* Convert address P to a pointer that is tagged correctly for that
    location.
diff --git a/sysdeps/generic/libc-mtag.h b/sysdeps/generic/libc-mtag.h
index e8fc236b6c..4743e873f1 100644
--- a/sysdeps/generic/libc-mtag.h
+++ b/sysdeps/generic/libc-mtag.h
@@ -44,12 +44,12 @@ __libc_mtag_tag_region (void *p, size_t n)
   return p;
 }
 
-/* Optimized equivalent to __libc_mtag_tag_region followed by memset.  */
+/* Optimized equivalent to __libc_mtag_tag_region followed by memset to 0.  */
 static inline void *
-__libc_mtag_memset_with_tag (void *p, int c, size_t n)
+__libc_mtag_tag_zero_region (void *p, size_t n)
 {
   __libc_mtag_link_error ();
-  return memset (p, c, n);
+  return memset (p, 0, n);
 }
 
 /* Convert address P to a pointer that is tagged correctly for that

[glibc/nsz/mtag] malloc: Only support zeroing and not arbitrary memset with mtag

[Szabolcs Nagy]

https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=8ec6e98d17b23ddc04a3b3beba159835c17cf526

commit 8ec6e98d17b23ddc04a3b3beba159835c17cf526
Author: Szabolcs Nagy <szabolcs.nagy@arm.com>
Date:   Fri Jan 29 17:07:28 2021 +0000

    malloc: Only support zeroing and not arbitrary memset with mtag
    
    The memset api is suboptimal and does not provide much benefit. Memory
    tagging only needs a zeroing memset (and only for memory that's sized
    and aligned to multiples of the tag granule), so change the internal
    api and the target hooks accordingly.  This is to simplify the
    implementation of the target hook.
    
    Reviewed-by: DJ Delorie <dj@redhat.com>

Diff:
---
 malloc/malloc.c                                        | 17 ++++++++---------
 sysdeps/aarch64/Makefile                               |  2 +-
 .../{__mtag_memset_tag.S => __mtag_tag_zero_region.S}  | 18 +++++++-----------
 sysdeps/aarch64/libc-mtag.h                            |  4 ++--
 sysdeps/generic/libc-mtag.h                            |  6 +++---
 5 files changed, 21 insertions(+), 26 deletions(-)

diff --git a/malloc/malloc.c b/malloc/malloc.c
index 253a919ec5..01cf6e9325 100644
--- a/malloc/malloc.c
+++ b/malloc/malloc.c
@@ -413,12 +413,11 @@ void *(*__morecore)(ptrdiff_t) = __default_morecore;
    operations can continue to be used.  Support macros are used to do
    this:
 
-   void *tag_new_memset (void *ptr, int, val, size_t size)
+   void *tag_new_zero_region (void *ptr, size_t size)
 
-   Has the same interface as memset(), but additionally allocates a
-   new tag, colors the memory with that tag and returns a pointer that
-   is correctly colored for that location.  The non-tagging version
-   will simply call memset.
+   Allocates a new tag, colors the memory with that tag, zeros the
+   memory and returns a pointer that is correctly colored for that
+   location.  The non-tagging version will simply call memset with 0.
 
    void *tag_region (void *ptr, size_t size)
 
@@ -458,11 +457,11 @@ tag_region (void *ptr, size_t size)
 }
 
 static __always_inline void *
-tag_new_memset (void *ptr, int val, size_t size)
+tag_new_zero_region (void *ptr, size_t size)
 {
   if (__glibc_unlikely (mtag_enabled))
-    return __libc_mtag_memset_with_tag (__libc_mtag_new_tag (ptr), val, size);
-  return memset (ptr, val, size);
+    return __libc_mtag_tag_zero_region (__libc_mtag_new_tag (ptr), size);
+  return memset (ptr, 0, size);
 }
 
 /* Defined later.  */
@@ -3679,7 +3678,7 @@ __libc_calloc (size_t n, size_t elem_size)
      regardless of MORECORE_CLEARS, so we zero the whole block while
      doing so.  */
 #ifdef USE_MTAG
-  return tag_new_memset (mem, 0, CHUNK_AVAILABLE_SIZE (p) - CHUNK_HDR_SZ);
+  return tag_new_zero_region (mem, CHUNK_AVAILABLE_SIZE (p) - CHUNK_HDR_SZ);
 #else
   INTERNAL_SIZE_T csz = chunksize (p);
 
diff --git a/sysdeps/aarch64/Makefile b/sysdeps/aarch64/Makefile
index d3ab37a40a..259070cfad 100644
--- a/sysdeps/aarch64/Makefile
+++ b/sysdeps/aarch64/Makefile
@@ -41,7 +41,7 @@ endif
 ifeq ($(subdir),misc)
 sysdep_headers += sys/ifunc.h
 sysdep_routines += __mtag_address_get_tag \
-		   __mtag_memset_tag \
+		   __mtag_tag_zero_region \
 		   __mtag_new_tag \
 		   __mtag_tag_region
 
diff --git a/sysdeps/aarch64/__mtag_memset_tag.S b/sysdeps/aarch64/__mtag_tag_zero_region.S
similarity index 82%
rename from sysdeps/aarch64/__mtag_memset_tag.S
rename to sysdeps/aarch64/__mtag_tag_zero_region.S
index 3c202888a4..74d398bba5 100644
--- a/sysdeps/aarch64/__mtag_memset_tag.S
+++ b/sysdeps/aarch64/__mtag_tag_zero_region.S
@@ -20,9 +20,6 @@
 
 #ifdef USE_MTAG
 
-/* Use the same register names and assignments as memset.  */
-#include "memset-reg.h"
-
 	.arch armv8.5-a
 	.arch_extension memtag
 
@@ -31,16 +28,15 @@
 /* FIXME: This is a minimal implementation.  We could do much better than
    this for large values of COUNT.  */
 
-ENTRY(__libc_mtag_memset_with_tag)
+#define dstin x0
+#define count x1
+#define dst   x2
 
-	and	valw, valw, 255
-	orr	valw, valw, valw, lsl 8
-	orr	valw, valw, valw, lsl 16
-	orr	val, val, val, lsl 32
-	mov	dst, dstin
+ENTRY(__libc_mtag_tag_zero_region)
 
+	mov	dst, dstin
 L(loop):
-	stgp	val, val, [dst], #16
+	stzg	dst, [dst], #16
 	subs	count, count, 16
 	bne	L(loop)
 #if 0
@@ -49,5 +45,5 @@ L(loop):
 	ldg	dstin, [dstin] // Recover the tag created (might be untagged).
 #endif
 	ret
-END (__libc_mtag_memset_with_tag)
+END (__libc_mtag_tag_zero_region)
 #endif /* USE_MTAG */
diff --git a/sysdeps/aarch64/libc-mtag.h b/sysdeps/aarch64/libc-mtag.h
index 979cbb743e..f58402ccf9 100644
--- a/sysdeps/aarch64/libc-mtag.h
+++ b/sysdeps/aarch64/libc-mtag.h
@@ -39,8 +39,8 @@
    void *__libc_mtag_tag_region (const void *, size_t)  */
 void *__libc_mtag_tag_region (void *, size_t);
 
-/* Optimized equivalent to __libc_mtag_tag_region followed by memset.  */
-void *__libc_mtag_memset_with_tag (void *, int, size_t);
+/* Optimized equivalent to __libc_mtag_tag_region followed by memset to 0.  */
+void *__libc_mtag_tag_zero_region (void *, size_t);
 
 /* Convert address P to a pointer that is tagged correctly for that
    location.
diff --git a/sysdeps/generic/libc-mtag.h b/sysdeps/generic/libc-mtag.h
index e8fc236b6c..4743e873f1 100644
--- a/sysdeps/generic/libc-mtag.h
+++ b/sysdeps/generic/libc-mtag.h
@@ -44,12 +44,12 @@ __libc_mtag_tag_region (void *p, size_t n)
   return p;
 }
 
-/* Optimized equivalent to __libc_mtag_tag_region followed by memset.  */
+/* Optimized equivalent to __libc_mtag_tag_region followed by memset to 0.  */
 static inline void *
-__libc_mtag_memset_with_tag (void *p, int c, size_t n)
+__libc_mtag_tag_zero_region (void *p, size_t n)
 {
   __libc_mtag_link_error ();
-  return memset (p, c, n);
+  return memset (p, 0, n);
 }
 
 /* Convert address P to a pointer that is tagged correctly for that

[glibc/nsz/mtag] malloc: Only support zeroing and not arbitrary memset with mtag

[Szabolcs Nagy]

https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=fa350832ffe6117eb08ffc650326e722bbe61cf5

commit fa350832ffe6117eb08ffc650326e722bbe61cf5
Author: Szabolcs Nagy <szabolcs.nagy@arm.com>
Date:   Fri Jan 29 17:07:28 2021 +0000

    malloc: Only support zeroing and not arbitrary memset with mtag
    
    The memset api is suboptimal and does not provide much benefit. Memory
    tagging only needs a zeroing memset (and only for memory that's sized
    and aligned to multiples of the tag granule), so change the internal
    api and the target hooks accordingly.  This is to simplify the
    implementation of the target hook.

Diff:
---
 malloc/malloc.c                                        | 17 ++++++++---------
 sysdeps/aarch64/Makefile                               |  2 +-
 .../{__mtag_memset_tag.S => __mtag_tag_zero_region.S}  | 18 +++++++-----------
 sysdeps/aarch64/libc-mtag.h                            |  4 ++--
 sysdeps/generic/libc-mtag.h                            |  6 +++---
 5 files changed, 21 insertions(+), 26 deletions(-)

diff --git a/malloc/malloc.c b/malloc/malloc.c
index caf34843f7..9002d51d7b 100644
--- a/malloc/malloc.c
+++ b/malloc/malloc.c
@@ -413,12 +413,11 @@ void *(*__morecore)(ptrdiff_t) = __default_morecore;
    operations can continue to be used.  Support macros are used to do
    this:
 
-   void *tag_new_memset (void *ptr, int, val, size_t size)
+   void *tag_new_zero_region (void *ptr, size_t size)
 
-   Has the same interface as memset(), but additionally allocates a
-   new tag, colors the memory with that tag and returns a pointer that
-   is correctly colored for that location.  The non-tagging version
-   will simply call memset.
+   Allocates a new tag, colors the memory with that tag, zeros the
+   memory and returns a pointer that is correctly colored for that
+   location.  The non-tagging version will simply call memset with 0.
 
    void *tag_region (void *ptr, size_t size)
 
@@ -458,11 +457,11 @@ tag_region (void *ptr, size_t size)
 }
 
 static __always_inline void *
-tag_new_memset (void *ptr, int val, size_t size)
+tag_new_zero_region (void *ptr, size_t size)
 {
   if (__glibc_unlikely (mtag_enabled))
-    return __libc_mtag_memset_with_tag (__libc_mtag_new_tag (ptr), val, size);
-  return memset (ptr, val, size);
+    return __libc_mtag_tag_zero_region (__libc_mtag_new_tag (ptr), size);
+  return memset (ptr, 0, size);
 }
 
 /* Defined later.  */
@@ -3679,7 +3678,7 @@ __libc_calloc (size_t n, size_t elem_size)
      regardless of MORECORE_CLEARS, so we zero the whole block while
      doing so.  */
 #ifdef USE_MTAG
-  return tag_new_memset (mem, 0, CHUNK_AVAILABLE_SIZE (p) - CHUNK_HDR_SZ);
+  return tag_new_zero_region (mem, CHUNK_AVAILABLE_SIZE (p) - CHUNK_HDR_SZ);
 #else
   INTERNAL_SIZE_T csz = chunksize (p);
 
diff --git a/sysdeps/aarch64/Makefile b/sysdeps/aarch64/Makefile
index d3ab37a40a..259070cfad 100644
--- a/sysdeps/aarch64/Makefile
+++ b/sysdeps/aarch64/Makefile
@@ -41,7 +41,7 @@ endif
 ifeq ($(subdir),misc)
 sysdep_headers += sys/ifunc.h
 sysdep_routines += __mtag_address_get_tag \
-		   __mtag_memset_tag \
+		   __mtag_tag_zero_region \
 		   __mtag_new_tag \
 		   __mtag_tag_region
 
diff --git a/sysdeps/aarch64/__mtag_memset_tag.S b/sysdeps/aarch64/__mtag_tag_zero_region.S
similarity index 82%
rename from sysdeps/aarch64/__mtag_memset_tag.S
rename to sysdeps/aarch64/__mtag_tag_zero_region.S
index 3c202888a4..74d398bba5 100644
--- a/sysdeps/aarch64/__mtag_memset_tag.S
+++ b/sysdeps/aarch64/__mtag_tag_zero_region.S
@@ -20,9 +20,6 @@
 
 #ifdef USE_MTAG
 
-/* Use the same register names and assignments as memset.  */
-#include "memset-reg.h"
-
 	.arch armv8.5-a
 	.arch_extension memtag
 
@@ -31,16 +28,15 @@
 /* FIXME: This is a minimal implementation.  We could do much better than
    this for large values of COUNT.  */
 
-ENTRY(__libc_mtag_memset_with_tag)
+#define dstin x0
+#define count x1
+#define dst   x2
 
-	and	valw, valw, 255
-	orr	valw, valw, valw, lsl 8
-	orr	valw, valw, valw, lsl 16
-	orr	val, val, val, lsl 32
-	mov	dst, dstin
+ENTRY(__libc_mtag_tag_zero_region)
 
+	mov	dst, dstin
 L(loop):
-	stgp	val, val, [dst], #16
+	stzg	dst, [dst], #16
 	subs	count, count, 16
 	bne	L(loop)
 #if 0
@@ -49,5 +45,5 @@ L(loop):
 	ldg	dstin, [dstin] // Recover the tag created (might be untagged).
 #endif
 	ret
-END (__libc_mtag_memset_with_tag)
+END (__libc_mtag_tag_zero_region)
 #endif /* USE_MTAG */
diff --git a/sysdeps/aarch64/libc-mtag.h b/sysdeps/aarch64/libc-mtag.h
index 979cbb743e..f58402ccf9 100644
--- a/sysdeps/aarch64/libc-mtag.h
+++ b/sysdeps/aarch64/libc-mtag.h
@@ -39,8 +39,8 @@
    void *__libc_mtag_tag_region (const void *, size_t)  */
 void *__libc_mtag_tag_region (void *, size_t);
 
-/* Optimized equivalent to __libc_mtag_tag_region followed by memset.  */
-void *__libc_mtag_memset_with_tag (void *, int, size_t);
+/* Optimized equivalent to __libc_mtag_tag_region followed by memset to 0.  */
+void *__libc_mtag_tag_zero_region (void *, size_t);
 
 /* Convert address P to a pointer that is tagged correctly for that
    location.
diff --git a/sysdeps/generic/libc-mtag.h b/sysdeps/generic/libc-mtag.h
index e8fc236b6c..4743e873f1 100644
--- a/sysdeps/generic/libc-mtag.h
+++ b/sysdeps/generic/libc-mtag.h
@@ -44,12 +44,12 @@ __libc_mtag_tag_region (void *p, size_t n)
   return p;
 }
 
-/* Optimized equivalent to __libc_mtag_tag_region followed by memset.  */
+/* Optimized equivalent to __libc_mtag_tag_region followed by memset to 0.  */
 static inline void *
-__libc_mtag_memset_with_tag (void *p, int c, size_t n)
+__libc_mtag_tag_zero_region (void *p, size_t n)
 {
   __libc_mtag_link_error ();
-  return memset (p, c, n);
+  return memset (p, 0, n);
 }
 
 /* Convert address P to a pointer that is tagged correctly for that