diff options
| author | Zoltan Kiss <zoltan.kiss@citrix.com> | 2013-09-04 21:11:05 +0100 |
|---|---|---|
| committer | Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> | 2013-10-02 12:53:26 -0400 |
| commit | 2b2b614dd24e4e6474fcf2dcf69c95c908838959 (patch) | |
| tree | 9874899c477d237e1ec207834fc730c1151088f5 /lib/swiotlb.c | |
| parent | 04b772d2b819f0dda2163e3193fa7cd447a6245c (diff) | |
| download | linux-stable-2b2b614dd24e4e6474fcf2dcf69c95c908838959.tar.gz linux-stable-2b2b614dd24e4e6474fcf2dcf69c95c908838959.tar.bz2 linux-stable-2b2b614dd24e4e6474fcf2dcf69c95c908838959.zip | |
tracing/events: Add bounce tracing to swiotbl
Ftrace is currently not able to detect when SWIOTLB has to do double buffering.
Under Xen you can only see it indirectly in function_graph, when
xen_swiotlb_map_page() doesn't stop after range_straddles_page_boundary(), but
calls spinlock functions, memcpy() and xen_phys_to_bus() as well. This patch
introduces the swiotlb:swiotlb_bounced event, which also prints out the
following informations to help you find out why bouncing happened:
dev_name: 0000:08:00.0 dma_mask=ffffffffffffffff dev_addr=9149f000 size=32768
swiotlb_force=0
If you use Xen, and (dev_addr + size + 1) > dma_mask, the buffer is out of the
device's DMA range. If swiotlb_force == 1, you should really change the kernel
parameters. Otherwise, the buffer is not contiguous in mfn space.
Signed-off-by: Zoltan Kiss <zoltan.kiss@citrix.com>
[v1: Don't print 'swiotlb_force=X', just print swiotlb_force if it is enabled]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Diffstat (limited to 'lib/swiotlb.c')
| -rw-r--r-- | lib/swiotlb.c | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 4e8686c7e5a4..f0d841907da6 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -38,6 +38,8 @@ #include <linux/bootmem.h> #include <linux/iommu-helper.h> +#include <trace/events/swiotlb.h> + #define OFFSET(val,align) ((unsigned long) \ ( (val) & ( (align) - 1))) @@ -726,6 +728,8 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, if (dma_capable(dev, dev_addr, size) && !swiotlb_force) return dev_addr; + trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); + /* Oh well, have to allocate and map a bounce buffer. */ map = map_single(dev, phys, size, dir); if (map == SWIOTLB_MAP_ERROR) { |