Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:3 as permitted sender) client-ip=2620:137:e000::3:3;
From:   Uros Bizjak <ubizjak@gmail.com>
To:     x86@kernel.org, linux-kernel@vger.kernel.org
Cc:     Uros Bizjak <ubizjak@gmail.com>, Nadav Amit <namit@vmware.com>,
        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 tip] x86/percpu: Use C for arch_raw_cpu_ptr()
Date:   Mon,  9 Oct 2023 22:29:33 +0200
Message-ID: <20231009203132.82773-1-ubizjak@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Implementing arch_raw_cpu_ptr() in C, allows the compiler to perform
better optimizations, such as setting an appropriate base to compute
the address instead of an add instruction.

E.g.: address calcuation in amd_pmu_enable_virt() improves from:

    48 c7 c0 00 00 00 00 	mov    $0x0,%rax
	87b7: R_X86_64_32S	cpu_hw_events

    65 48 03 05 00 00 00 	add    %gs:0x0(%rip),%rax
    00
	87bf: R_X86_64_PC32	this_cpu_off-0x4

    48 c7 80 28 13 00 00 	movq   $0x0,0x1328(%rax)
    00 00 00 00

to:

    65 48 8b 05 00 00 00 	mov    %gs:0x0(%rip),%rax
    00
	8798: R_X86_64_PC32	this_cpu_off-0x4
    48 c7 80 00 00 00 00 	movq   $0x0,0x0(%rax)
    00 00 00 00
	87a6: R_X86_64_32S	cpu_hw_events+0x1328

Co-developed-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
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/x86/include/asm/percpu.h | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 60ea7755c0fe..aa48c061abd9 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -39,16 +39,23 @@
 
 #define __percpu_prefix		""
 
+/*
+ * Efficient implementation for cases in which the compiler supports
+ * named address spaces.  Allows the compiler to perform additional
+ * optimizations that can save more instructions.
+ */
+#define arch_raw_cpu_ptr(ptr)					\
+({								\
+	unsigned long tcp_ptr__;				\
+	tcp_ptr__ = __raw_cpu_read(, this_cpu_off) + (unsigned long)(ptr); \
+	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;		\
+})
+
 #else /* CONFIG_CC_HAS_NAMED_AS */
 
 #define __percpu_seg_override
 #define __percpu_prefix		"%%"__stringify(__percpu_seg)":"
 
-#endif /* CONFIG_CC_HAS_NAMED_AS */
-
-#define __force_percpu_prefix	"%%"__stringify(__percpu_seg)":"
-#define __my_cpu_offset		this_cpu_read(this_cpu_off)
-
 /*
  * Compared to the generic __my_cpu_offset version, the following
  * saves one instruction and avoids clobbering a temp register.
@@ -61,6 +68,12 @@
 	     : "m" (__my_cpu_var(this_cpu_off)), "0" (ptr));	\
 	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;		\
 })
+
+#endif /* CONFIG_CC_HAS_NAMED_AS */
+
+#define __force_percpu_prefix	"%%"__stringify(__percpu_seg)":"
+#define __my_cpu_offset		this_cpu_read(this_cpu_off)
+
 #else /* CONFIG_SMP */
 #define __percpu_seg_override
 #define __percpu_prefix		""
-- 
2.41.0