It turns out the kernel relies on barrier() to force a reload of the
percpu offset value.  Since we can't easily modify the definition of
barrier() to include "tp" as an output register, we instead provide a
definition of __my_cpu_offset as extended assembly that includes a fake
stack read to hazard against barrier(), forcing gcc to know that it
must reread "tp" and recompute anything based on "tp" after a barrier.
This fixes observed hangs in the slub allocator when we are looping
on a percpu cmpxchg_double.
A similar fix for ARMv7 was made in June in change 509eb76ebf.
Cc: stable@vger.kernel.org
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
		
	
			
		
			
				
	
	
		
			52 lines
		
	
	
	
		
			1.8 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			52 lines
		
	
	
	
		
			1.8 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
/*
 | 
						|
 * Copyright 2010 Tilera Corporation. All Rights Reserved.
 | 
						|
 *
 | 
						|
 *   This program is free software; you can redistribute it and/or
 | 
						|
 *   modify it under the terms of the GNU General Public License
 | 
						|
 *   as published by the Free Software Foundation, version 2.
 | 
						|
 *
 | 
						|
 *   This program is distributed in the hope that it will be useful, but
 | 
						|
 *   WITHOUT ANY WARRANTY; without even the implied warranty of
 | 
						|
 *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
 | 
						|
 *   NON INFRINGEMENT.  See the GNU General Public License for
 | 
						|
 *   more details.
 | 
						|
 */
 | 
						|
 | 
						|
#ifndef _ASM_TILE_PERCPU_H
 | 
						|
#define _ASM_TILE_PERCPU_H
 | 
						|
 | 
						|
register unsigned long my_cpu_offset_reg asm("tp");
 | 
						|
 | 
						|
#ifdef CONFIG_PREEMPT
 | 
						|
/*
 | 
						|
 * For full preemption, we can't just use the register variable
 | 
						|
 * directly, since we need barrier() to hazard against it, causing the
 | 
						|
 * compiler to reload anything computed from a previous "tp" value.
 | 
						|
 * But we also don't want to use volatile asm, since we'd like the
 | 
						|
 * compiler to be able to cache the value across multiple percpu reads.
 | 
						|
 * So we use a fake stack read as a hazard against barrier().
 | 
						|
 * The 'U' constraint is like 'm' but disallows postincrement.
 | 
						|
 */
 | 
						|
static inline unsigned long __my_cpu_offset(void)
 | 
						|
{
 | 
						|
	unsigned long tp;
 | 
						|
	register unsigned long *sp asm("sp");
 | 
						|
	asm("move %0, tp" : "=r" (tp) : "U" (*sp));
 | 
						|
	return tp;
 | 
						|
}
 | 
						|
#define __my_cpu_offset __my_cpu_offset()
 | 
						|
#else
 | 
						|
/*
 | 
						|
 * We don't need to hazard against barrier() since "tp" doesn't ever
 | 
						|
 * change with PREEMPT_NONE, and with PREEMPT_VOLUNTARY it only
 | 
						|
 * changes at function call points, at which we are already re-reading
 | 
						|
 * the value of "tp" due to "my_cpu_offset_reg" being a global variable.
 | 
						|
 */
 | 
						|
#define __my_cpu_offset my_cpu_offset_reg
 | 
						|
#endif
 | 
						|
 | 
						|
#define set_my_cpu_offset(tp) (my_cpu_offset_reg = (tp))
 | 
						|
 | 
						|
#include <asm-generic/percpu.h>
 | 
						|
 | 
						|
#endif /* _ASM_TILE_PERCPU_H */
 |