diff options
| author | Sowmini Varadhan <sowmini.varadhan@oracle.com> | 2015-04-09 15:33:31 -0400 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2015-04-18 12:32:59 -0700 |
| commit | bb620c3d3925aec0ed4f21010c86df08ec18a8c7 (patch) | |
| tree | f3adfa12c95f9aa6dd844fd47fd486332bbd0a2e /arch/sparc/include/asm | |
| parent | ff7d37a502022149655c18035b99a53391be0383 (diff) | |
| download | linux-stable-bb620c3d3925aec0ed4f21010c86df08ec18a8c7.tar.gz linux-stable-bb620c3d3925aec0ed4f21010c86df08ec18a8c7.tar.bz2 linux-stable-bb620c3d3925aec0ed4f21010c86df08ec18a8c7.zip | |
sparc: Make sparc64 use scalable lib/iommu-common.c functions
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>
Diffstat (limited to 'arch/sparc/include/asm')
| -rw-r--r-- | arch/sparc/include/asm/iommu_64.h | 7 |
1 files changed, 3 insertions, 4 deletions
diff --git a/arch/sparc/include/asm/iommu_64.h b/arch/sparc/include/asm/iommu_64.h index 2b9321ab064d..cd0d69fa7592 100644 --- a/arch/sparc/include/asm/iommu_64.h +++ b/arch/sparc/include/asm/iommu_64.h @@ -16,6 +16,7 @@ #define IOPTE_WRITE 0x0000000000000002UL #define IOMMU_NUM_CTXS 4096 +#include <linux/iommu-common.h> struct iommu_arena { unsigned long *map; @@ -24,11 +25,10 @@ struct iommu_arena { }; struct iommu { + struct iommu_map_table tbl; spinlock_t lock; - struct iommu_arena arena; - void (*flush_all)(struct iommu *); + u32 dma_addr_mask; iopte_t *page_table; - u32 page_table_map_base; unsigned long iommu_control; unsigned long iommu_tsbbase; unsigned long iommu_flush; @@ -40,7 +40,6 @@ struct iommu { unsigned long dummy_page_pa; unsigned long ctx_lowest_free; DECLARE_BITMAP(ctx_bitmap, IOMMU_NUM_CTXS); - u32 dma_addr_mask; }; struct strbuf { |