linux-kernel - [PATCH v2 5/5] x86/percpu: Optimize raw_cpu

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20190613135653.623354057@infradead.org>
Date:   Thu, 13 Jun 2019 15:54:50 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     torvalds@...ux-foundation.org, mingo@...nel.org, bp@...en8.de,
        tglx@...utronix.de, luto@...nel.org, namit@...are.com,
        peterz@...radead.org
Cc:     linux-kernel@...r.kernel.org
Subject: [PATCH v2 5/5] x86/percpu: Optimize raw_cpu_xchg()

Since raw_cpu_xchg() doesn't need to be IRQ-safe, like
this_cpu_xchg(), we can use a simple load-store instead of the cmpxchg
loop.

Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
 arch/x86/include/asm/percpu.h |   20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -407,9 +407,21 @@ do {									\
 #define raw_cpu_or_1(pcp, val)		percpu_to_op(, "or", (pcp), val)
 #define raw_cpu_or_2(pcp, val)		percpu_to_op(, "or", (pcp), val)
 #define raw_cpu_or_4(pcp, val)		percpu_to_op(, "or", (pcp), val)
-#define raw_cpu_xchg_1(pcp, val)	percpu_xchg_op(, pcp, val)
-#define raw_cpu_xchg_2(pcp, val)	percpu_xchg_op(, pcp, val)
-#define raw_cpu_xchg_4(pcp, val)	percpu_xchg_op(, pcp, val)
+
+/*
+ * raw_cpu_xchg() can use a load-store since it is not required to be
+ * IRQ-safe.
+ */
+#define raw_percpu_xchg_op(var, nval)					\
+({									\
+	typeof(var) pxo_ret__ = raw_cpu_read(var);			\
+	raw_cpu_write(var, (nval));					\
+	pxo_ret__;							\
+})
+
+#define raw_cpu_xchg_1(pcp, val)	raw_percpu_xchg_op(pcp, val)
+#define raw_cpu_xchg_2(pcp, val)	raw_percpu_xchg_op(pcp, val)
+#define raw_cpu_xchg_4(pcp, val)	raw_percpu_xchg_op(pcp, val)
 
 #define this_cpu_read_1(pcp)		percpu_from_op(volatile, "mov", pcp)
 #define this_cpu_read_2(pcp)		percpu_from_op(volatile, "mov", pcp)
@@ -472,7 +484,7 @@ do {									\
 #define raw_cpu_and_8(pcp, val)			percpu_to_op(, "and", (pcp), val)
 #define raw_cpu_or_8(pcp, val)			percpu_to_op(, "or", (pcp), val)
 #define raw_cpu_add_return_8(pcp, val)		percpu_add_return_op(, pcp, val)
-#define raw_cpu_xchg_8(pcp, nval)		percpu_xchg_op(, pcp, nval)
+#define raw_cpu_xchg_8(pcp, nval)		raw_percpu_xchg_op(pcp, nval)
 #define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(, pcp, oval, nval)
 
 #define this_cpu_read_8(pcp)			percpu_from_op(volatile, "mov", pcp)