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
Git-commit: ffebbaedc8616cffe648202e364dce6a045d65a2
Patch-mainline: v4.20-rc1
References: fate#325585

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>
Acked-by: Borislav Petkov <bp@suse.de>
---
 arch/x86/entry/vdso/vgetcpu.c  |    9 +--------
 arch/x86/entry/vdso/vma.c      |   19 +++++++------------
 arch/x86/include/asm/segment.h |   41 +++++++++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/vgtod.h   |   26 --------------------------
 4 files changed, 49 insertions(+), 46 deletions(-)

--- a/arch/x86/entry/vdso/vgetcpu.c
+++ b/arch/x86/entry/vdso/vgetcpu.c
@@ -13,14 +13,7 @@
 notrace long
 __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
 {
-	unsigned int p;
-
-	p = __getcpu();
-
-	if (cpu)
-		*cpu = p & VGETCPU_CPU_MASK;
-	if (node)
-		*node = p >> 12;
+	vdso_read_cpu_node(cpu, node);
 	return 0;
 }
 
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -342,20 +342,15 @@ static void vgetcpu_cpu_init(void *arg)
 {
 	int cpu = smp_processor_id();
 	struct desc_struct d = { };
-	unsigned long node = 0;
-#ifdef CONFIG_NUMA
-	node = cpu_to_node(cpu);
-#endif
+	unsigned long cpudata = vdso_encode_cpu_node(cpu, cpu_to_node(cpu));
+
 	if (static_cpu_has(X86_FEATURE_RDTSCP))
-		write_rdtscp_aux((node << 12) | cpu);
+		write_rdtscp_aux(cpudata);
+
+	/* Store CPU and node number in limit */
+	d.limit0 = cpudata;
+	d.limit = cpudata >> 16;
 
-	/*
-	 * Store cpu number in limit so that it can be loaded
-	 * quickly in user space in vgetcpu. (12 bits for the CPU
-	 * and 8 bits for the node)
-	 */
-	d.limit0 = cpu | ((node & 0xf) << 12);
-	d.limit = node >> 4;
 	d.type = 5;		/* RO data, expand down, accessed */
 	d.dpl = 3;		/* Visible to user code */
 	d.s = 1;		/* Not a system segment */
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -223,6 +223,47 @@
 #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__
 
 /*
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -76,30 +76,4 @@ static inline void gtod_write_end(struct
 	++s->seq;
 }
 
-#ifdef CONFIG_X86_64
-
-#define VGETCPU_CPU_MASK 0xfff
-
-static inline unsigned int __getcpu(void)
-{
-	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));
-
-	return p;
-}
-
-#endif /* CONFIG_X86_64 */
-
 #endif /* _ASM_X86_VGTOD_H */