In iperf experiments running linux as the Tx side (TCP client) with 10 threads results in a severe performance drop when TSO is disabled, indicating a weakness in the software that can be avoided by using the scalable IOMMU arena DMA allocation. Baseline numbers before this patch: with default settings (TSO enabled) : 9-9.5 Gbps Disable TSO using ethtool- drops badly: 2-3 Gbps. After this patch, iperf client with 10 threads, can give a throughput of at least 8.5 Gbps, even when TSO is disabled. Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: David S. Miller <davem@davemloft.net>
		
			
				
	
	
		
			51 lines
		
	
	
	
		
			1.3 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			51 lines
		
	
	
	
		
			1.3 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
/* iommu_common.h: UltraSparc SBUS/PCI common iommu declarations.
 | 
						|
 *
 | 
						|
 * Copyright (C) 1999, 2008 David S. Miller (davem@davemloft.net)
 | 
						|
 */
 | 
						|
 | 
						|
#ifndef _IOMMU_COMMON_H
 | 
						|
#define _IOMMU_COMMON_H
 | 
						|
 | 
						|
#include <linux/kernel.h>
 | 
						|
#include <linux/types.h>
 | 
						|
#include <linux/sched.h>
 | 
						|
#include <linux/mm.h>
 | 
						|
#include <linux/scatterlist.h>
 | 
						|
#include <linux/device.h>
 | 
						|
#include <linux/iommu-helper.h>
 | 
						|
 | 
						|
#include <asm/iommu.h>
 | 
						|
#include <asm/scatterlist.h>
 | 
						|
 | 
						|
/*
 | 
						|
 * These give mapping size of each iommu pte/tlb.
 | 
						|
 */
 | 
						|
#define IO_PAGE_SHIFT			13
 | 
						|
#define IO_PAGE_SIZE			(1UL << IO_PAGE_SHIFT)
 | 
						|
#define IO_PAGE_MASK			(~(IO_PAGE_SIZE-1))
 | 
						|
#define IO_PAGE_ALIGN(addr)		ALIGN(addr, IO_PAGE_SIZE)
 | 
						|
 | 
						|
#define IO_TSB_ENTRIES			(128*1024)
 | 
						|
#define IO_TSB_SIZE			(IO_TSB_ENTRIES * 8)
 | 
						|
 | 
						|
/*
 | 
						|
 * This is the hardwired shift in the iotlb tag/data parts.
 | 
						|
 */
 | 
						|
#define IOMMU_PAGE_SHIFT		13
 | 
						|
 | 
						|
#define SG_ENT_PHYS_ADDRESS(SG)	(__pa(sg_virt((SG))))
 | 
						|
 | 
						|
static inline int is_span_boundary(unsigned long entry,
 | 
						|
				   unsigned long shift,
 | 
						|
				   unsigned long boundary_size,
 | 
						|
				   struct scatterlist *outs,
 | 
						|
				   struct scatterlist *sg)
 | 
						|
{
 | 
						|
	unsigned long paddr = SG_ENT_PHYS_ADDRESS(outs);
 | 
						|
	int nr = iommu_num_pages(paddr, outs->dma_length + sg->length,
 | 
						|
				 IO_PAGE_SIZE);
 | 
						|
 | 
						|
	return iommu_is_span_boundary(entry, nr, shift, boundary_size);
 | 
						|
}
 | 
						|
 | 
						|
#endif /* _IOMMU_COMMON_H */
 |