x86/segments: Introduce the 'CPUNODE' naming to better document the segment limit CPU/node NR trick

We have a special segment descriptor entry in the GDT, whose sole purpose is to
encode the CPU and node numbers in its limit (size) field. There are user-space
instructions that allow the reading of the limit field, which gives us a really
fast way to read the CPU and node IDs from the vDSO for example.

But the naming of related functionality does not make this clear, at all:

	VDSO_CPU_SIZE
	VDSO_CPU_MASK
	__CPU_NUMBER_SEG
	GDT_ENTRY_CPU_NUMBER
	vdso_encode_cpu_node
	vdso_read_cpu_node

There's a number of problems:

 - The 'VDSO_CPU_SIZE' doesn't really make it clear that these are number
   of bits, nor does it make it clear which 'CPU' this refers to, i.e.
   that this is about a GDT entry whose limit encodes the CPU and node number.

 - Furthermore, the 'CPU_NUMBER' naming is actively misleading as well,
   because the segment limit encodes not just the CPU number but the
   node ID as well ...

So use a better nomenclature all around: name everything related to this trick
as 'CPUNODE', to make it clear that this is something special, and add
_BITS to make it clear that these are number of bits, and propagate this to
every affected name:

	VDSO_CPU_SIZE         =>  VDSO_CPUNODE_BITS
	VDSO_CPU_MASK         =>  VDSO_CPUNODE_MASK
	__CPU_NUMBER_SEG      =>  __CPUNODE_SEG
	GDT_ENTRY_CPU_NUMBER  =>  GDT_ENTRY_CPUNODE
	vdso_encode_cpu_node  =>  vdso_encode_cpunode
	vdso_read_cpu_node    =>  vdso_read_cpunode

This, beyond being less confusing, also makes it easier to grep for all related
functionality:

  $ git grep -i cpunode arch/x86

Also, while at it, fix "return is not a function" style sloppiness in vdso_encode_cpunode().

Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Chang S. Bae <chang.seok.bae@intel.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>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Link: http://lkml.kernel.org/r/1537312139-5580-2-git-send-email-chang.seok.bae@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/entry/vdso/vgetcpu.c

@@ -13,7 +13,7 @@
 notrace long
 __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
 {
-	vdso_read_cpu_node(cpu, node);
+	vdso_read_cpunode(cpu, node);
 	return 0;
 }
 

arch/x86/include/asm/segment.h

@@ -186,7 +186,7 @@
 #define GDT_ENTRY_TLS_MIN		12
 #define GDT_ENTRY_TLS_MAX		14
 
-#define GDT_ENTRY_CPU_NUMBER		15
+#define GDT_ENTRY_CPUNODE		15
 
 /*
  * Number of entries in the GDT table:
@@ -206,7 +206,7 @@
 #define __USER_DS			(GDT_ENTRY_DEFAULT_USER_DS*8 + 3)
 #define __USER32_DS			__USER_DS
 #define __USER_CS			(GDT_ENTRY_DEFAULT_USER_CS*8 + 3)
-#define __CPU_NUMBER_SEG		(GDT_ENTRY_CPU_NUMBER*8 + 3)
+#define __CPUNODE_SEG			(GDT_ENTRY_CPUNODE*8 + 3)
 
 #endif
 
@@ -227,24 +227,24 @@
 #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
+#define VDSO_CPUNODE_BITS		12
+#define VDSO_CPUNODE_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)
+static inline unsigned long vdso_encode_cpunode(int cpu, unsigned long node)
 {
-	return ((node << VDSO_CPU_SIZE) | cpu);
+	return (node << VDSO_CPUNODE_BITS) | cpu;
 }
 
-static inline void vdso_read_cpu_node(unsigned *cpu, unsigned *node)
+static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node)
 {
 	unsigned int p;
 
 	/*
-	 * Load CPU and node number from GDT.  LSL is faster than RDTSCP
+	 * Load CPU and node number from the 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.
@@ -254,12 +254,12 @@ static inline void vdso_read_cpu_node(unsigned *cpu, unsigned *node)
 	alternative_io ("lsl %[seg],%[p]",
 			".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */
 			X86_FEATURE_RDPID,
-			[p] "=a" (p), [seg] "r" (__CPU_NUMBER_SEG));
+			[p] "=a" (p), [seg] "r" (__CPUNODE_SEG));
 
 	if (cpu)
-		*cpu = (p & VDSO_CPU_MASK);
+		*cpu = (p & VDSO_CPUNODE_MASK);
 	if (node)
-		*node = (p >> VDSO_CPU_SIZE);
+		*node = (p >> VDSO_CPUNODE_BITS);
 }
 
 #endif /* !__ASSEMBLY__ */

arch/x86/kernel/cpu/common.c

@@ -1672,7 +1672,7 @@ static void wait_for_master_cpu(int cpu)
 #ifdef CONFIG_X86_64
 static void setup_getcpu(int cpu)
 {
-	unsigned long cpudata = vdso_encode_cpu_node(cpu, early_cpu_to_node(cpu));
+	unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
 	struct desc_struct d = { };
 
 	if (static_cpu_has(X86_FEATURE_RDTSCP))
@@ -1688,7 +1688,7 @@ static void setup_getcpu(int cpu)
 	d.p = 1;		/* Present */
 	d.d = 1;		/* 32-bit */
 
-	write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_CPU_NUMBER, &d, DESCTYPE_S);
+	write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_CPUNODE, &d, DESCTYPE_S);
 }
 #endif