Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   "Chang S. Bae" <chang.seok.bae@intel.com>
To:     Andy Lutomirski <luto@kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@kernel.org>,
        "H . Peter Anvin" <hpa@zytor.com>, Andi Kleen <ak@linux.intel.com>
Cc:     Markus T Metzger <markus.t.metzger@intel.com>,
        Ravi Shankar <ravi.v.shankar@intel.com>,
        "Chang S . Bae" <chang.seok.bae@intel.com>,
        LKML <linux-kernel@vger.kernel.org>,
        Dave Hansen <dave.hansen@linux.intel.com>
Subject: [PATCH v5 08/13] x86/fsgsbase/64: Introduce the FIND_PERCPU_BASE macro
Date:   Fri,  1 Feb 2019 12:53:14 -0800
Message-Id: <20190201205319.15995-10-chang.seok.bae@intel.com>
In-Reply-To: <20190201205319.15995-1-chang.seok.bae@intel.com>
References: <20190201205319.15995-1-chang.seok.bae@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

GSBASE is used to find per-CPU data in the kernel. But when it is unknown,
the per-CPU base can be found from the per_cpu_offset table with a CPU NR.
The CPU NR is extracted from the limit field of the CPUNODE entry in GDT,
or by the RDPID instruction.

Also, add the GAS-compatible RDPID macro.

The new macro will be used on a following patch.

Suggested-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/include/asm/fsgsbase.h | 46 +++++++++++++++++++++++++++++++++
 arch/x86/include/asm/inst.h     | 15 +++++++++++
 2 files changed, 61 insertions(+)

diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h
index aefd53767a5d..eecca2250748 100644
--- a/arch/x86/include/asm/fsgsbase.h
+++ b/arch/x86/include/asm/fsgsbase.h
@@ -78,6 +78,52 @@ extern void x86_gsbase_write_cpu_inactive(unsigned long gsbase);
 
 #endif /* CONFIG_X86_64 */
 
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_X86_64
+
+#include <asm/inst.h>
+
+#if CONFIG_SMP
+
+/*
+ * CPU/node NR is loaded from the limit (size) field of a special segment
+ * descriptor entry in GDT.
+ */
+.macro LOAD_CPU_AND_NODE_SEG_LIMIT reg:req
+	movq	$__CPUNODE_SEG, \reg
+	lsl	\reg, \reg
+.endm
+
+/*
+ * Fetch the per-CPU GSBASE value for this processor and put it in @reg.
+ * We normally use %gs for accessing per-CPU data, but we are setting up
+ * %gs here and obviously can not use %gs itself to access per-CPU data.
+ */
+.macro FIND_PERCPU_BASE reg:req
+	/*
+	 * The CPU/node NR is initialized earlier, directly in cpu_init().
+	 * The CPU NR is extracted from it.
+	 */
+	ALTERNATIVE \
+		"LOAD_CPU_AND_NODE_SEG_LIMIT \reg", \
+		"RDPID	\reg", \
+		X86_FEATURE_RDPID
+	andq	$VDSO_CPUNODE_MASK, \reg
+	movq	__per_cpu_offset(, \reg, 8), \reg
+.endm
+
+#else
+
+.macro FIND_PERCPU_BASE reg:req
+	/* Tracking the base offset value */
+	movq	pcpu_unit_offsets(%rip), \reg
+.endm
+
+#endif /* CONFIG_SMP */
+
+#endif /* CONFIG_X86_64 */
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_FSGSBASE_H */
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index f5a796da07f8..d063841a17e3 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -306,6 +306,21 @@
 	.endif
 	MODRM 0xc0 movq_r64_xmm_opd1 movq_r64_xmm_opd2
 	.endm
+
+.macro RDPID opd
+	REG_TYPE rdpid_opd_type \opd
+	.if rdpid_opd_type == REG_TYPE_R64
+	R64_NUM rdpid_opd \opd
+	.else
+	R32_NUM rdpid_opd \opd
+	.endif
+	.byte 0xf3
+	.if rdpid_opd > 7
+	PFX_REX rdpid_opd 0
+	.endif
+	.byte 0x0f, 0xc7
+	MODRM 0xc0 rdpid_opd 0x7
+.endm
 #endif
 
 #endif
-- 
2.19.1