From ffebbaedc8616cffe648202e364dce6a045d65a2 Mon Sep 17 00:00:00 2001
From: "Chang S. Bae" <chang.seok.bae@intel.com>
Date: Tue, 18 Sep 2018 16:08:58 -0700
Subject: x86/vdso: Introduce helper functions for CPU and node number

Clean up the CPU/node number related code a bit, to make it more apparent
how we are encoding/extracting the CPU and node fields from the
segment limit.

No change in functionality intended.

[ mingo: Wrote new changelog. ]

Suggested-by: Andy Lutomirski <luto@kernel.org>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Markus T Metzger <markus.t.metzger@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Shankar <ravi.v.shankar@intel.com>
Cc: Rik van Riel <riel@surriel.com>
Link: http://lkml.kernel.org/r/1537312139-5580-8-git-send-email-chang.seok.bae@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/segment.h | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

(limited to 'arch/x86/include/asm/segment.h')

diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index e3e788ea52e5..4d1f6cc62e13 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -224,6 +224,47 @@
 #define GDT_ENTRY_TLS_ENTRIES		3
 #define TLS_SIZE			(GDT_ENTRY_TLS_ENTRIES* 8)
 
+#ifdef CONFIG_X86_64
+
+/* Bit size and mask of CPU number stored in the per CPU data (and TSC_AUX) */
+#define VDSO_CPU_SIZE			12
+#define VDSO_CPU_MASK			0xfff
+
+#ifndef __ASSEMBLY__
+
+/* Helper functions to store/load CPU and node numbers */
+
+static inline unsigned long vdso_encode_cpu_node(int cpu, unsigned long node)
+{
+	return ((node << VDSO_CPU_SIZE) | cpu);
+}
+
+static inline void vdso_read_cpu_node(unsigned *cpu, unsigned *node)
+{
+	unsigned int p;
+
+	/*
+	 * Load CPU and node number from GDT.  LSL is faster than RDTSCP
+	 * and works on all CPUs.  This is volatile so that it orders
+	 * correctly with respect to barrier() and to keep GCC from cleverly
+	 * hoisting it out of the calling function.
+	 *
+	 * If RDPID is available, use it.
+	 */
+	alternative_io ("lsl %[seg],%[p]",
+			".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */
+			X86_FEATURE_RDPID,
+			[p] "=a" (p), [seg] "r" (__CPU_NUMBER_SEG));
+
+	if (cpu)
+		*cpu = (p & VDSO_CPU_MASK);
+	if (node)
+		*node = (p >> VDSO_CPU_SIZE);
+}
+
+#endif /* !__ASSEMBLY__ */
+#endif /* CONFIG_X86_64 */
+
 #ifdef __KERNEL__
 
 /*
-- 
cgit v1.2.3