Received-SPF: pass (google.com: domain of linux-kernel+bounces-129994-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
From: Uros Bizjak <ubizjak@gmail.com>
To: x86@kernel.org,
	linux-kernel@vger.kernel.org
Cc: Uros Bizjak <ubizjak@gmail.com>,
	Ingo Molnar <mingo@kernel.org>,
	Andy Lutomirski <luto@kernel.org>,
	Brian Gerst <brgerst@gmail.com>,
	Denys Vlasenko <dvlasenk@redhat.com>,
	"H . Peter Anvin" <hpa@zytor.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Josh Poimboeuf <jpoimboe@redhat.com>
Subject: [PATCH] x86/percpu: Fix and improve x86_this_cpu_test_bit() and friends
Date: Wed,  3 Apr 2024 16:46:32 +0200
Message-ID: <20240403144648.3885-1-ubizjak@gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Fix x86_this_cpu_variable_test_bit(), which is implemented with
wrong asm template, where argument 2 (count argument) is considered
as percpu variable. However, x86_this_cpu_test_bit() is currently
used exclusively with constant bit number argument, so the called
x86_this_cpu_variable_test_bit() function is never instantiated.
The fix introduces named assembler operands to prevent this kind
of errors.

Also rewrite the whole family of x86_this_cpu_test_bit() functions
as macros, so standard __my_cpu_var() and raw_cpu_read() macros
can be used on percpu variables. This approach considerably
simplifies implementation of functions and also introduces standard
checks on accessed percpu variables.

No functional changes intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
---
 arch/um/include/asm/cpufeature.h  |  3 +-
 arch/x86/include/asm/cpufeature.h |  3 +-
 arch/x86/include/asm/percpu.h     | 51 +++++++++++++------------------
 3 files changed, 24 insertions(+), 33 deletions(-)

diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h
index 66fe06db872f..1eb8b834fbec 100644
--- a/arch/um/include/asm/cpufeature.h
+++ b/arch/um/include/asm/cpufeature.h
@@ -38,8 +38,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 
 #define this_cpu_has(bit)						\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
-	 x86_this_cpu_test_bit(bit,					\
-		(unsigned long __percpu *)&cpu_info.x86_capability))
+	 x86_this_cpu_test_bit(bit, cpu_info.x86_capability))
 
 /*
  * This macro is for detection of features which need kernel
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index f95e1c8b7c01..7d527467ab9c 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -127,8 +127,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 
 #define this_cpu_has(bit)						\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
-	 x86_this_cpu_test_bit(bit,					\
-		(unsigned long __percpu *)&cpu_info.x86_capability))
+	 x86_this_cpu_test_bit(bit, cpu_info.x86_capability))
 
 /*
  * This macro is for detection of features which need kernel
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 20696df5d567..d6ff0db32209 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -96,7 +96,7 @@
 #endif /* CONFIG_SMP */
 
 #define __my_cpu_type(var)	typeof(var) __percpu_seg_override
-#define __my_cpu_ptr(ptr)	(__my_cpu_type(*ptr)*)(__force uintptr_t)(ptr)
+#define __my_cpu_ptr(ptr)	(__my_cpu_type(*(ptr))*)(__force uintptr_t)(ptr)
 #define __my_cpu_var(var)	(*__my_cpu_ptr(&(var)))
 #define __percpu_arg(x)		__percpu_prefix "%" #x
 #define __force_percpu_arg(x)	__force_percpu_prefix "%" #x
@@ -568,36 +568,29 @@ do {									\
 #define this_cpu_read_stable_8(pcp)    ({ BUILD_BUG(); (typeof(pcp))0; })
 #endif
 
-static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,
-                        const unsigned long __percpu *addr)
-{
-	unsigned long __percpu *a =
-		(unsigned long __percpu *)addr + nr / BITS_PER_LONG;
-
-#ifdef CONFIG_X86_64
-	return ((1UL << (nr % BITS_PER_LONG)) & raw_cpu_read_8(*a)) != 0;
-#else
-	return ((1UL << (nr % BITS_PER_LONG)) & raw_cpu_read_4(*a)) != 0;
-#endif
-}
-
-static inline bool x86_this_cpu_variable_test_bit(int nr,
-                        const unsigned long __percpu *addr)
-{
-	bool oldbit;
-
-	asm volatile("btl "__percpu_arg(2)",%1"
-			CC_SET(c)
-			: CC_OUT(c) (oldbit)
-			: "m" (*__my_cpu_ptr((unsigned long __percpu *)(addr))), "Ir" (nr));
+#define x86_this_cpu_constant_test_bit(_nr, _var)			\
+({									\
+	unsigned long __percpu *addr__ =				\
+		(unsigned long __percpu *)&(_var) + ((_nr) / BITS_PER_LONG); \
+	!!((1UL << ((_nr) % BITS_PER_LONG)) & raw_cpu_read(*addr__));	\
+})
 
-	return oldbit;
-}
+#define x86_this_cpu_variable_test_bit(_nr, _var)		\
+({								\
+	bool oldbit;						\
+								\
+	asm volatile("btl %[nr], " __percpu_arg([var])		\
+		     CC_SET(c)					\
+		     : CC_OUT(c) (oldbit)			\
+		     : [var] "m" (__my_cpu_var(_var)),		\
+		       [nr] "rI" (_nr));			\
+	oldbit;							\
+})
 
-#define x86_this_cpu_test_bit(nr, addr)			\
-	(__builtin_constant_p((nr))			\
-	 ? x86_this_cpu_constant_test_bit((nr), (addr))	\
-	 : x86_this_cpu_variable_test_bit((nr), (addr)))
+#define x86_this_cpu_test_bit(_nr, _var)			\
+	(__builtin_constant_p(_nr)				\
+	 ? x86_this_cpu_constant_test_bit(_nr, _var)		\
+	 : x86_this_cpu_variable_test_bit(_nr, _var))
 
 
 #include <asm-generic/percpu.h>
-- 
2.42.0