From: Muhammad Usama Anjum <usama.anjum@arm.com>
To: Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Andrii Nakryiko <andrii@kernel.org>,
Eduard Zingerman <eddyz87@gmail.com>,
Kumar Kartikeya Dwivedi <memxor@gmail.com>,
Martin KaFai Lau <martin.lau@linux.dev>,
Song Liu <song@kernel.org>,
Yonghong Song <yonghong.song@linux.dev>,
Jiri Olsa <jolsa@kernel.org>,
Emil Tsalapatis <emil@etsalapatis.com>,
Ihor Solodrai <ihor.solodrai@linux.dev>,
Andrew Morton <akpm@linux-foundation.org>,
David Hildenbrand <david@kernel.org>,
Lorenzo Stoakes <ljs@kernel.org>,
"Liam R. Howlett" <liam@infradead.org>,
Vlastimil Babka <vbabka@kernel.org>,
Mike Rapoport <rppt@kernel.org>,
Suren Baghdasaryan <surenb@google.com>,
Michal Hocko <mhocko@suse.com>,
linux-arm-kernel@lists.infradead.org (moderated list:ARM64 PORT
(AARCH64 ARCHITECTURE)), linux-kernel@vger.kernel.org (open list),
bpf@vger.kernel.org (open list:BPF [GENERAL] (Safe Dynamic
Programs and Tools)),
linux-mm@kvack.org (open list:MEMORY MANAGEMENT - CORE)
Cc: Muhammad Usama Anjum <usama.anjum@arm.com>
Subject: [PATCH 1/7] arm64: uaccess: Add batched kernel nofault accessors
Date: Mon, 24 Aug 2026 17:04:46 +0100 [thread overview]
Message-ID: <20260824160523.3907021-2-usama.anjum@arm.com> (raw)
In-Reply-To: <20260824160523.3907021-1-usama.anjum@arm.com>
With Hardware Tag-Based KASAN in asynchronous or asymmetric mode, arm64
sets and clears PSTATE.TCO around every kernel nofault load or store. A
loop pays that cost for every access even though tag checking can stay
disabled until the operation finishes.
Separate TCO management from the fault-tolerant access and add begin and
end hooks for callers that want to batch several accesses. Keep the
existing accessors self-contained, and provide aliases and no-op hooks
for architectures that do not need special handling.
A context switch re-enables tag checking, so a batched region must not
schedule. Continue to evaluate accessor arguments before overriding TCO,
as those expressions may block.
Signed-off-by: Muhammad Usama Anjum <usama.anjum@arm.com>
---
arch/arm64/include/asm/uaccess.h | 71 ++++++++++++++++++++++++--------
include/linux/uaccess.h | 16 +++++++
2 files changed, 69 insertions(+), 18 deletions(-)
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 9f5bd9c69c249..1a14eb2a51dce 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -270,28 +270,43 @@ do { \
#define get_user __get_user
/*
- * We must not call into the scheduler between __mte_enable_tco_async() and
- * __mte_disable_tco_async(). As `dst` and `src` may contain blocking
- * functions, we must evaluate these outside of the critical section.
+ * Nofault load without TCO management for use inside a
+ * __begin/__end_kernel_nofault_bare() region.
*/
-#define __get_kernel_nofault(dst, src, type, err_label) \
+#define __get_kernel_nofault_bare(dst, src, type, err_label) \
do { \
__typeof__(dst) __gkn_dst = (dst); \
__typeof__(src) __gkn_src = (src); \
do { \
__label__ __gkn_label; \
- \
- __mte_enable_tco_async(); \
__raw_get_mem("ldr", *((type *)(__gkn_dst)), \
(__force type *)(__gkn_src), __gkn_label, K); \
- __mte_disable_tco_async(); \
break; \
__gkn_label: \
- __mte_disable_tco_async(); \
goto err_label; \
} while (0); \
} while (0)
+/*
+ * We must not call into the scheduler between __mte_enable_tco_async() and
+ * __mte_disable_tco_async(). As dst and src may contain blocking functions,
+ * evaluate them before overriding TCO.
+ */
+#define __get_kernel_nofault(dst, src, type, err_label) \
+do { \
+ __label__ __gkn_tco_err; \
+ __typeof__(dst) __gkn_tco_dst = (dst); \
+ __typeof__(src) __gkn_tco_src = (src); \
+ __mte_enable_tco_async(); \
+ __get_kernel_nofault_bare(__gkn_tco_dst, __gkn_tco_src, type, \
+ __gkn_tco_err); \
+ __mte_disable_tco_async(); \
+ break; \
+__gkn_tco_err: \
+ __mte_disable_tco_async(); \
+ goto err_label; \
+} while (0)
+
#define __put_mem_asm(store, reg, x, addr, label, type) \
asm goto( \
"1: " store " " reg "0, [%1]\n" \
@@ -366,28 +381,48 @@ do { \
#define put_user __put_user
-/*
- * We must not call into the scheduler between __mte_enable_tco_async() and
- * __mte_disable_tco_async(). As `dst` and `src` may contain blocking
- * functions, we must evaluate these outside of the critical section.
- */
-#define __put_kernel_nofault(dst, src, type, err_label) \
+/* Nofault store without TCO management; see __get_kernel_nofault_bare. */
+#define __put_kernel_nofault_bare(dst, src, type, err_label) \
do { \
__typeof__(dst) __pkn_dst = (dst); \
__typeof__(src) __pkn_src = (src); \
\
do { \
__label__ __pkn_err; \
- __mte_enable_tco_async(); \
__raw_put_mem("str", *((type *)(__pkn_src)), \
(__force type *)(__pkn_dst), __pkn_err, K); \
- __mte_disable_tco_async(); \
break; \
__pkn_err: \
- __mte_disable_tco_async(); \
goto err_label; \
} while (0); \
-} while(0)
+} while (0)
+
+/*
+ * We must not call into the scheduler between __mte_enable_tco_async() and
+ * __mte_disable_tco_async(). As `dst` and `src` may contain blocking
+ * functions, we must evaluate these outside of the critical section.
+ */
+#define __put_kernel_nofault(dst, src, type, err_label) \
+do { \
+ __label__ __pkn_tco_err; \
+ __typeof__(dst) __pkn_tco_dst = (dst); \
+ __typeof__(src) __pkn_tco_src = (src); \
+ __mte_enable_tco_async(); \
+ __put_kernel_nofault_bare(__pkn_tco_dst, __pkn_tco_src, type, \
+ __pkn_tco_err); \
+ __mte_disable_tco_async(); \
+ break; \
+__pkn_tco_err: \
+ __mte_disable_tco_async(); \
+ goto err_label; \
+} while (0)
+
+/*
+ * A context switch re-enables tag checking, hence the no-scheduling
+ * requirement for a bare nofault region.
+ */
+#define __begin_kernel_nofault_bare() __mte_enable_tco_async()
+#define __end_kernel_nofault_bare() __mte_disable_tco_async()
extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n);
#define raw_copy_from_user(to, from, n) \
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index eddbbb65ccc4f..7ae1854673471 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -637,6 +637,22 @@ do { \
#endif /* !__get_kernel_nofault */
+/*
+ * Architectures may use the begin/end hooks to establish state shared by a
+ * sequence of bare nofault accesses. Every path out of the region must call
+ * the end hook. The region, including expressions passed to the bare
+ * accessors, must not call into the scheduler.
+ */
+#ifndef __get_kernel_nofault_bare
+#define __get_kernel_nofault_bare __get_kernel_nofault
+#define __put_kernel_nofault_bare __put_kernel_nofault
+#endif
+
+#ifndef __begin_kernel_nofault_bare
+#define __begin_kernel_nofault_bare() do {} while (0)
+#define __end_kernel_nofault_bare() do {} while (0)
+#endif
+
/**
* get_kernel_nofault(): safely attempt to read from a location
* @val: read into this variable
--
2.47.3
next prev parent reply other threads:[~2026-08-24 16:06 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-24 16:04 [PATCH 0/7] arm64: Batch PSTATE.TCO handling in kernel nofault loops Muhammad Usama Anjum
2026-08-24 16:04 ` Muhammad Usama Anjum [this message]
2026-08-24 17:02 ` [PATCH 1/7] arm64: uaccess: Add batched kernel nofault accessors bot+bpf-ci
2026-08-24 16:04 ` [PATCH 2/7] uaccess: Add scope guard for bare kernel nofault regions Muhammad Usama Anjum
2026-08-24 17:02 ` bot+bpf-ci
2026-08-24 16:04 ` [PATCH 3/7] maccess: Skip setup for zero-sized kernel nofault copies Muhammad Usama Anjum
2026-08-24 17:02 ` bot+bpf-ci
2026-08-24 16:04 ` [PATCH 4/7] maccess: Use a scoped guard for page faults Muhammad Usama Anjum
2026-08-24 17:02 ` bot+bpf-ci
2026-08-25 10:36 ` David Hildenbrand (Arm)
2026-08-25 12:07 ` Muhammad Usama Anjum
2026-08-24 16:04 ` [PATCH 4/7] maccess: Use a scoped guard to re-enable " Muhammad Usama Anjum
2026-08-24 16:04 ` [PATCH 5/7] maccess: Batch TCO handling in kernel nofault loops Muhammad Usama Anjum
2026-08-24 17:02 ` bot+bpf-ci
2026-08-24 16:04 ` [PATCH 6/7] bpf: Skip setup for zero-length string kfunc operations Muhammad Usama Anjum
2026-08-24 16:04 ` [PATCH 7/7] bpf: Batch TCO handling in string kfuncs Muhammad Usama Anjum
2026-08-24 17:02 ` bot+bpf-ci
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260824160523.3907021-2-usama.anjum@arm.com \
--to=usama.anjum@arm.com \
--cc=akpm@linux-foundation.org \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=catalin.marinas@arm.com \
--cc=daniel@iogearbox.net \
--cc=david@kernel.org \
--cc=eddyz87@gmail.com \
--cc=emil@etsalapatis.com \
--cc=ihor.solodrai@linux.dev \
--cc=jolsa@kernel.org \
--cc=liam@infradead.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=mark.rutland@arm.com \
--cc=martin.lau@linux.dev \
--cc=memxor@gmail.com \
--cc=mhocko@suse.com \
--cc=rppt@kernel.org \
--cc=song@kernel.org \
--cc=surenb@google.com \
--cc=vbabka@kernel.org \
--cc=will@kernel.org \
--cc=yonghong.song@linux.dev \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox