aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/iommu.c
diff options
context:
space:
mode:
authorAnton Blanchard <anton@samba.org>2012-06-03 19:43:02 +0000
committerBenjamin Herrenschmidt <benh@kernel.crashing.org>2012-07-03 14:14:47 +1000
commit0e4bc95d87394364f408627067238453830bdbf3 (patch)
treeb5dbbb86a43e9fb0db8a865b770da5fad07c89c3 /arch/powerpc/kernel/iommu.c
parentc1703e85a7b20ffcefd5360e2542460737ecc15c (diff)
downloadkernel_goldelico_gta04-0e4bc95d87394364f408627067238453830bdbf3.zip
kernel_goldelico_gta04-0e4bc95d87394364f408627067238453830bdbf3.tar.gz
kernel_goldelico_gta04-0e4bc95d87394364f408627067238453830bdbf3.tar.bz2
powerpc/iommu: Reduce spinlock coverage in iommu_alloc and iommu_free
We currently hold the IOMMU spinlock around tce_build and tce_flush. This causes our spinlock hold times to be much higher than required and can impact multiqueue adapters. This patch moves tce_build and tce_flush outside of the lock in iommu_alloc, and tce_flush outside of the lock in iommu_free. Some performance numbers were obtained with a Chelsio T3 adapter on two POWER7 boxes, running a 100 session TCP round robin test. Performance improved 32% with this patch applied. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Diffstat (limited to 'arch/powerpc/kernel/iommu.c')
-rw-r--r--arch/powerpc/kernel/iommu.c15
1 files changed, 5 insertions, 10 deletions
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 359f078..9c8967f 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -170,13 +170,11 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
int build_fail;
spin_lock_irqsave(&(tbl->it_lock), flags);
-
entry = iommu_range_alloc(dev, tbl, npages, NULL, mask, align_order);
+ spin_unlock_irqrestore(&(tbl->it_lock), flags);
- if (unlikely(entry == DMA_ERROR_CODE)) {
- spin_unlock_irqrestore(&(tbl->it_lock), flags);
+ if (unlikely(entry == DMA_ERROR_CODE))
return DMA_ERROR_CODE;
- }
entry += tbl->it_offset; /* Offset into real TCE table */
ret = entry << IOMMU_PAGE_SHIFT; /* Set the return dma address */
@@ -192,9 +190,10 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
* not altered.
*/
if (unlikely(build_fail)) {
+ spin_lock_irqsave(&(tbl->it_lock), flags);
__iommu_free(tbl, ret, npages);
-
spin_unlock_irqrestore(&(tbl->it_lock), flags);
+
return DMA_ERROR_CODE;
}
@@ -202,8 +201,6 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
if (ppc_md.tce_flush)
ppc_md.tce_flush(tbl);
- spin_unlock_irqrestore(&(tbl->it_lock), flags);
-
/* Make sure updates are seen by hardware */
mb();
@@ -244,8 +241,8 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
unsigned long flags;
spin_lock_irqsave(&(tbl->it_lock), flags);
-
__iommu_free(tbl, dma_addr, npages);
+ spin_unlock_irqrestore(&(tbl->it_lock), flags);
/* Make sure TLB cache is flushed if the HW needs it. We do
* not do an mb() here on purpose, it is not needed on any of
@@ -253,8 +250,6 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
*/
if (ppc_md.tce_flush)
ppc_md.tce_flush(tbl);
-
- spin_unlock_irqrestore(&(tbl->it_lock), flags);
}
int iommu_map_sg(struct device *dev, struct iommu_table *tbl,